Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
169 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Towards Diverse Binary Segmentation via A Simple yet General Gated Network (2303.10396v2)

Published 18 Mar 2023 in cs.CV

Abstract: In many binary segmentation tasks, most CNNs-based methods use a U-shape encoder-decoder network as their basic structure. They ignore two key problems when the encoder exchanges information with the decoder: one is the lack of interference control mechanism between them, the other is without considering the disparity of the contributions from different encoder levels. In this work, we propose a simple yet general gated network (GateNet) to tackle them all at once. With the help of multi-level gate units, the valuable context information from the encoder can be selectively transmitted to the decoder. In addition, we design a gated dual branch structure to build the cooperation among the features of different levels and improve the discrimination ability of the network. Furthermore, we introduce a "Fold" operation to improve the atrous convolution and form a novel folded atrous convolution, which can be flexibly embedded in ASPP or DenseASPP to accurately localize foreground objects of various scales. GateNet can be easily generalized to many binary segmentation tasks, including general and specific object segmentation and multi-modal segmentation. Without bells and whistles, our network consistently performs favorably against the state-of-the-art methods under 10 metrics on 33 datasets of 10 binary segmentation tasks.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (290)
  1. Frequency-tuned salient region detection. In CVPR, pages 1597–1604, 2009.
  2. Pyramid methods in image processing. RCA Eng., 29, 11 1983.
  3. Gated feedback refinement network for dense image labeling. In CVPR, pages 3751–3759, 2017.
  4. Contour detection and hierarchical image segmentation. IEEE TPAMI, 33:898–916, 2010.
  5. Wm-dova maps for accurate polyp highlighting in colonoscopy: Validation vs. saliency maps from physicians. CMIG, 43:99–111, 2015.
  6. Using guided self-attention with local information for polyp segmentation. In International Conference on Medical Image Computing and Computer-Assisted Intervention, pages 629–638, 2022.
  7. Improved saliency detection in rgb-d images using two-phase depth estimation and selective deep fusion. IEEE TIP, 29:4296–4307, 2020.
  8. Tom-net: Learning transparent object matting from a single image. In CVPR, pages 9233–9241, 2018.
  9. Rgbd salient object detection via disentangled cross-modal fusion. IEEE TIP, 29:8407–8416, 2020.
  10. Progressively complementarity-aware fusion network for rgb-d salient object detection. In CVPR, pages 3051–3060, 2018.
  11. Three-stream attention-aware network for rgb-d salient object detection. IEEE TIP, 28:2825–2835, 2019.
  12. Multi-modal fusion network with multi-scale multi-path and cross-modal interactions for rgb-d salient object detection. Pattern Recognition, 86:376–385, 2019.
  13. Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. IEEE TPAMI, 40:834–848, 2017.
  14. Encoder-decoder with atrous separable convolution for semantic image segmentation. In ECCV, pages 801–818, 2018.
  15. Rgb-d salient object detection via 3d convolutional neural networks. In AAAI, pages 1063–1071, 2021.
  16. Progressively guided alternate refinement network for rgb-d salient object detection. In ECCV, pages 520–538, 2020.
  17. Reverse attention for salient object detection. In ECCV, pages 234–250, 2018.
  18. Dpanet: Depth potentiality-aware gated attention network for rgb-d salient object detection. IEEE TIP, 30:7012–7024, 2020.
  19. Global context-aware progressive aggregation network for salient object detection. In AAAI, pages 10599–10606, 2020.
  20. Masked-attention mask transformer for universal image segmentation. In CVPR, pages 1290–1299, 2022.
  21. Learnable oriented-derivative network for polyp segmentation. In MICCAI, pages 720–730, 2021.
  22. A highly efficient model to study the semantics of salient object detection. IEEE TPAMI, 44:8006–8021, 2021.
  23. Global contrast based salient region detection. IEEE TPAMI, 37:569–582, 2014.
  24. Depth-induced gap-reducing network for rgb-d salient object detection: an interaction, guidance and refinement approach. IEEE TMM, 2022.
  25. Depth enhanced saliency detection method. In ICIMCS, page 23, 2014.
  26. François Chollet. Xception: Deep learning with depthwise separable convolutions. In CVPR, pages 1251–1258, 2017.
  27. Cir-net: Cross-modality interaction and refinement for rgb-d salient object detection. IEEE TIP, 31:6800–6815, 2022.
  28. Frequency perception network for camouflaged object detection. arXiv preprint arXiv:2308.08924, 2023.
  29. RRNet: Relational reasoning network with parallel multi-scale attention for salient object detection in optical remote sensing images. IEEE TGRS, 60:1558–1644, 2022.
  30. The cityscapes dataset for semantic urban scene understanding. In CVPR, pages 3213–3223, 2016.
  31. Defocus blur detection via depth distillation. In ECCV, pages 747–763, 2020.
  32. Recurrent multi-scale transformer for high-resolution salient object detection. arXiv preprint arXiv:2308.03826, 2023.
  33. R3net: Recurrent residual refinement network for saliency detection. In IJCAI, pages 684–690, 2018.
  34. Argan: Attentive recurrent generative adversarial network for shadow detection and removal. In ICCV, pages 10213–10222, 2019.
  35. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929, 2020.
  36. An empirical study of training end-to-end vision-and-language transformers. In CVPR, pages 18166–18176, 2022.
  37. The pascal visual object classes (voc) challenge. IJCV, 88(2):303–338, 2010.
  38. Structure-measure: A new way to evaluate foreground maps. In ICCV, pages 4548–4557, 2017.
  39. Enhanced-alignment measure for binary foreground map evaluation. arXiv preprint arXiv:1805.10421, 2018.
  40. Concealed object detection. IEEE TPAMI, 44:6024–6042, 2021.
  41. Camouflaged object detection. In CVPR, pages 2777–2787, 2020.
  42. Pranet: Parallel reverse attention network for polyp segmentation. In MICCAI, pages 263–273, 2020.
  43. Rethinking rgb-d salient object detection: Models, data sets, and large-scale benchmarks. IEEE TNNLS, 32:2075–2089, 2020.
  44. Bbs-net: Rgb-d salient object detection with a bifurcated backbone strategy network. In ECCV, pages 275–292, 2020.
  45. Rfenet: Towards reciprocal feature evolution for glass segmentation. arXiv preprint arXiv:2307.06099, 2023.
  46. From captions to visual concepts and back. In CVPR, pages 1473–1482, 2015.
  47. Robust shadow detection by exploring effective shadow contexts. In ACM MM, pages 2927–2935, 2021.
  48. Selective feature aggregation network with area-boundary constraints for polyp segmentation. In MICCAI, pages 302–310, 2019.
  49. Attentive feedback network for boundary-aware salient object detection. In CVPR, pages 1623–1632, 2019.
  50. Jl-dcf: Joint learning and densely-cooperative fusion framework for rgb-d salient object detection. In CVPR, pages 3052–3062, 2020.
  51. Res2net: A new multi-scale backbone architecture. IEEE TPAMI, 43:652–662, 2019.
  52. Highly efficient salient object detection with 100k parameters. In ECCV, pages 702–721, 2020.
  53. inas: Integral nas for device-aware salient object detection. In ICCV, pages 4934–4944, 2021.
  54. Orsi salient object detection via bidimensional attention and full-stage semantic guidance. IEEE TGRS, 61:1–13, 2023.
  55. Learning semantic associations for mirror detection. In CVPR, pages 5941–5950, 2022.
  56. Camouflaged object detection with feature decomposition and edge reconstruction. In CVPR, pages 22046–22055, 2023.
  57. Enhanced boundary learning for glass-like object segmentation. In ICCV, pages 15859–15868, 2021.
  58. Deep residual learning for image recognition. In CVPR, pages 770–778, 2016.
  59. Deeply supervised salient object detection with short connections. In CVPR, pages 3203–3212, 2017.
  60. Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861, 2017.
  61. Squeeze-and-excitation networks. In CVPR, pages 7132–7141, 2018.
  62. High-resolution iterative feedback network for camouflaged object detection. In AAAI, volume 37, pages 881–889, 2023.
  63. Direction-aware spatial context features for shadow detection and removal. IEEE TPAMI, 42:2795–2808, 2019.
  64. Revisiting shadow detection: A new benchmark dataset for complex world. IEEE TIP, 30:1925–1934, 2021.
  65. Direction-aware spatial context features for shadow detection. In CVPR, pages 7454–7462, 2018.
  66. Densely connected convolutional networks. In CVPR, pages 4700–4708, 2017.
  67. Feature shrinkage pyramid for camouflaged object detection with transformers. In CVPR, pages 5557–5566, 2023.
  68. Ccnet: Criss-cross attention for semantic segmentation. In ICCV, pages 603–612, 2019.
  69. A comprehensive study on colorectal polyp segmentation with resunet++, conditional random field and test-time augmentation. IEEE JBHI, 25:2029–2040, 2021.
  70. Kvasir-seg: A segmented polyp dataset. In MMM, pages 451–462, 2020.
  71. Fast camouflaged object detection via edge-based reversible re-calibration network. Pattern Recognition, 123:108414, 2022.
  72. Calibrated rgb-d salient object detection. In CVPR, pages 9471–9481, 2021.
  73. Accurate rgb-d salient object detection via collaborative learning. In ECCV, pages 52–69, 2020.
  74. Segment, magnify and reiterate: Detecting camouflaged objects the hard way. In CVPR, pages 4713–4722, 2022.
  75. cmsalgan: Rgb-d salient object detection with cross-view generative adversarial networks. IEEE TMM, 23:1343–1353, 2020.
  76. Ma-ganet: A multi-attention generative adversarial network for defocus blur detection. IEEE TIP, 31:3494–3508, 2022.
  77. Cdnet: Complementary depth network for rgb-d salient object detection. IEEE TIP, 30:3376–3390, 2021.
  78. Depth saliency based on anisotropic center-surround difference. In ICIP, pages 1115–1119, 2014.
  79. Estimating geo-temporal location of stationary cameras using shadow trajectories. In ECCV, pages 318–331, 2008.
  80. Recurrent iterative gating networks for semantic segmentation. In WACV, pages 1070–1079, 2019.
  81. Recursive contour-saliency blending network for accurate salient object detection. In WACV, pages 2940–2950, 2022.
  82. Attentive feedback feature pyramid network for shadow detection. IEEE SPL, 27:1964–1968, 2020.
  83. Uacanet: Uncertainty augmented context attention for polyp segmentation. In ACM MM, pages 2167–2175, 2021.
  84. Adam: A method for stochastic optimization. In ICLR, 2015.
  85. A+ d net: Training a shadow detector with adversarial shadow attenuation. In ECCV, pages 662–678, 2018.
  86. Anabranch network for camouflaged object segmentation. CVIU, 184:45–56, 2019.
  87. Deeply-supervised nets. In Artificial intelligence and statistics, pages 562–570. PMLR, 2015.
  88. Spsn: Superpixel prototype sampling network for rgb-d salient object detection. In ECCV, pages 630–647, 2022.
  89. Uncertainty-aware joint salient object and camouflaged object detection. In CVPR, pages 10071–10081, 2021.
  90. A parallel down-up fusion network for salient object detection in optical remote sensing images. Neurocomputing, 415:411–420, 2020.
  91. Nested network with two-stream pyramid for salient object detection in optical remote sensing images. IEEE TGRS, 57:9156–9166, 2019.
  92. Rgb-d salient object detection with cross-modality modulation and selection. In ECCV, pages 225–241, 2020.
  93. Hierarchical alternate interaction network for rgb-d salient object detection. IEEE TIP, 30:3528–3542, 2021.
  94. Multi-content complementation network for salient object detection in optical remote sensing images. IEEE TGRS, 60:1–13, 2022.
  95. Icnet: Information conversion network for rgb-d based salient object detection. IEEE TIP, 29:4873–4884, 2020.
  96. Cross-modal weighting network for rgb-d salient object detection. In ECCV, pages 665–681, 2020.
  97. Lightweight salient object detection in optical remote-sensing images via semantic matching and edge alignment. IEEE TGRS, 61:1–11, 2023.
  98. Visual saliency based on multiscale deep features. In CVPR, pages 5455–5463, 2015.
  99. Delving into calibrated depth for accurate rgb-d salient object detection. IJCV, 131:855–876, 2023.
  100. From global to local: Multi-patch and multi-scale contrastive similarity learning for unsupervised defocus blur detection. IEEE TIP, 32:1158–1169, 2023.
  101. Saliency detection on light field. In CVPR, pages 2806–2813, 2014.
  102. Findnet: Can you find me? boundary-and-texture enhancement network for camouflaged object detection. IEEE TIP, 31:6396–6411, 2022.
  103. The secrets of salient object segmentation. In CVPR, pages 280–287, 2014.
  104. Mmnet: Multi-stage and multi-scale fusion network for rgb-d salient object detection. In ACM MM, pages 2436–2444, 2020.
  105. Shadow detection via predicting the confidence maps of shadow detection methods. In ACM MM, pages 704–712, 2021.
  106. Rich context aggregation with reflection prior for glass surface detection. In CVPR, pages 13415–13424, 2021.
  107. Progressive mirror detection. In CVPR, pages 3697–3705, 2020.
  108. Feature pyramid networks for object detection. In CVPR, pages 2117–2125, 2017.
  109. A simple pooling-based design for real-time salient object detection. In CVPR, pages 3917–3926, 2019.
  110. Poolnet+: Exploring the potential of pooling for salient object detection. IEEE TPAMI, 45:887–904, 2022.
  111. Dhsnet: Deep hierarchical saliency network for salient object detection. In CVPR, pages 678–686, 2016.
  112. Picanet: Learning pixel-wise contextual attention for saliency detection. In CVPR, pages 3089–3098, 2018.
  113. Learning selective self-mutual attention for rgb-d saliency detection. In CVPR, pages 13756–13765, 2020.
  114. Visual saliency transformer. In ICCV, pages 4722–4732, 2021.
  115. Learning to detect a salient object. IEEE TPAMI, 33:353–367, 2010.
  116. Ggrnet: Global graph reasoning network for salient object detection in optical remote sensing images. In PRCV, pages 584–596, 2021.
  117. Employing deep part-object relationships for salient object detection. In ICCV, pages 1232–1241, 2019.
  118. Swin transformer: Hierarchical vision transformer using shifted windows. In CVPR, pages 10012–10022, 2021.
  119. Tritransnet: Rgb-d salient object detection with a triplet transformer embedding network. In ACM MM, pages 4481–4490, 2021.
  120. Boosting camouflaged object detection with dual-task interactive transformer. In ICPR, pages 140–146, 2022.
  121. Fully convolutional networks for semantic segmentation. In CVPR, pages 3431–3440, 2015.
  122. Cascade graph neural networks for rgb-d salient object detection. In ECCV, pages 346–364, 2020.
  123. Simultaneously localize, segment and rank the camouflaged objects. In CVPR, pages 11591–11601, 2021.
  124. Pyramidal feature shrinking for salient object detection. In AAAI, pages 2311–2318, 2021.
  125. Boosting broader receptive fields for salient object detection. IEEE TIP, 32:1026–1038, 2023.
  126. How to evaluate foreground maps? In CVPR, pages 248–255, 2014.
  127. Depth-aware mirror segmentation. In CVPR, pages 3044–3053, 2021.
  128. Camouflaged object segmentation with distraction mining. In CVPR, pages 8772–8781, 2021.
  129. Don’t hit me! glass detection in real-world scenes. In CVPR, pages 3687–3696, 2020.
  130. Ccbanet: Cascading context and balancing attention for polyp segmentation. In MICCAI, pages 633–643, 2021.
  131. Leveraging stereopsis for saliency analysis. In CVPR, pages 454–461, 2012.
  132. Hierarchical dynamic filtering network for rgb-d salient object detection. In ECCV, pages 235–252, 2020.
  133. Zoom in and out: A mixed-scale triplet network for camouflaged object detection. In CVPR, pages 2160–2170, 2022.
  134. Multi-scale interactive network for salient object detection. In CVPR, pages 9413–9422, 2020.
  135. Caver: Cross-modal view-mixed transformer for bi-modal salient object detection. IEEE TIP, 32:892–904, 2023.
  136. C3: Concentrated-comprehensive convolution and its application to semantic segmentation. arXiv preprint arXiv:1812.04920, 2018.
  137. Osformer: One-stage camouflaged instance segmentation with transformers. In ECCV, pages 19–37, 2022.
  138. Large kernel matters–improve semantic segmentation by global convolutional network. In CVPR, pages 4353–4361, 2017.
  139. Rgbd salient object detection: A benchmark and algorithms. In ECCV, pages 92–109, 2014.
  140. Saliency filters: Contrast based filtering for salient region detection. In CVPR, pages 733–740, 2012.
  141. Depth-induced multi-scale recurrent attention network for saliency detection. In ICCV, pages 7254–7263, 2019.
  142. A2dele: Adaptive and attentive depth distiller for efficient rgb-d salient object detection. In CVPR, pages 9060–9069, 2020.
  143. U2-net: Going deeper with nested u-structure for salient object detection. Pattern Recognition, 106:107404, 2020.
  144. Basnet: Boundary-aware salient object detection. In CVPR, pages 7479–7489, 2019.
  145. Deep texture-aware features for camouflaged object detection. IEEE TCSVT, 2021.
  146. Region-based saliency detection and its application in object recognition. IEEE TCSVT, 24(5):769–779, 2013.
  147. U-net: Convolutional networks for biomedical image segmentation. In MICCAI, pages 234–241, 2015.
  148. Unsupervised salience learning for person re-identification. In CVPR, 2013.
  149. Anat Caspi Linda Shapiro Sachin Mehta, Mohammad Rastegari and Hannaneh Hajishirzi. Espnet: Efficient spatial pyramid of dilated convolutions for semantic segmentation. In ECCV, 2018.
  150. Mobilenetv2: Inverted residuals and linear bottlenecks. In CVPR, pages 4510–4520, 2018.
  151. Hrenet: A hard region enhancement network for polyp segmentation. In MICCAI, pages 559–568, 2021.
  152. Aprnet: Alternative prediction refinement network for polyp segmentation. In IEEE EMBC, pages 3114–3117, 2021.
  153. Task-relevant feature replenishment for cross-centre polyp segmentation. In MICCAI, pages 599–608, 2022.
  154. Discriminative blur detection features. In CVPR, pages 2965–2972, 2014.
  155. Toward embedded detection of polyps in wce images for early diagnosis of colorectal cancer. IJCARS, 9:283–293, 2014.
  156. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556, 2014.
  157. Scene context-aware salient object detection. In ICCV, pages 4156–4166, 2021.
  158. Animal camouflage analysis: Chameleon database. Unpublished Manuscript, 2018.
  159. Improving rgb-d salient object detection via modality-aware decoder. IEEE TIP, 31:6124–6138, 2022.
  160. Animal camouflage: current issues and new perspectives. Philosophical Transactions of the Royal Society B: Biological Sciences, 364:423–427, 2009.
  161. Selectivity or invariance: Boundary-aware salient object detection. In ICCV, pages 3799–3808, 2019.
  162. Catnet: A cascaded and aggregated transformer network for rgb-d salient object detection. IEEE TMM, 2023.
  163. Deep rgb-d saliency detection with depth-sensitive attention and automatic multi-modal fusion. In CVPR, pages 1407–1417, 2021.
  164. Boundary-guided camouflaged object detection. arXiv preprint arXiv:2207.00794, 2022.
  165. Automated polyp detection in colonoscopy videos using shape and context information. IEEE TMI, 35:630–644, 2015.
  166. Densely connected multidilated convolutional networks for dense prediction tasks. In CVPR, pages 993–1002, 2021.
  167. Efficientnet: Rethinking model scaling for convolutional neural networks. In ICML, pages 6105–6114, 2019.
  168. Hrtransnet: Hrformer-driven two-modality salient object detection. IEEE TCSVT, 33:728–742, 2022.
  169. Br2net: Defocus blur detection via a bidirectional channel attention residual refining network. IEEE TMM, 23:624–635, 2020.
  170. Defusionnet: Defocus blur detection via recurrently fusing and refining discriminative multi-scale deep features. IEEE TPAMI, 44:955–968, 2020.
  171. R2mrf: Defocus blur detection via recurrently refining multi-scale residual features. In AAAI, pages 12063–12070, 2020.
  172. Defusionnet: Defocus blur detection via recurrently fusing and refining multi-scale deep features. In CVPR, pages 2700–2709, 2019.
  173. Disentangled high quality salient object detection. In ICCV, pages 3580–3590, 2021.
  174. Training data-efficient image transformers & distillation through attention. In ICML, pages 10347–10357, 2021.
  175. Orsi salient object detection via multiscale joint region and boundary model. IEEE TGRS, 60:1–13, 2022.
  176. Attention is all you need. In NeurIPS, page 5998–6008, 2017.
  177. A benchmark for endoluminal scene segmentation of colonoscopy images. JHE, 2017, 2017.
  178. Leave-one-out kernel optimization for shadow detection. In ICCV, pages 3388–3396, 2015.
  179. Large-scale training of shadow detectors with noisily-annotated shadow examples. In ECCV, pages 816–832, 2016.
  180. Progressive feature polishing network for salient object detection. In AAAI, pages 12128–12135, 2020.
  181. Learning discriminative cross-modality features for rgb-d saliency detection. IEEE TIP, 31:1285–1297, 2022.
  182. Stacked conditional generative adversarial networks for jointly learning shadow detection and shadow removal. In CVPR, pages 1788–1797, 2018.
  183. Stepwise feature fusion: Local guides global. In MICCAI, pages 110–120, 2022.
  184. Learning to detect salient objects with image-level supervision. In CVPR, pages 136–145, 2017.
  185. Ems-net: Enhanced multi-scale network for polyp segmentation. In IEEE EMBC, pages 2936–2939, 2021.
  186. Adaptive fusion for rgb-d salient object detection. IEEE Access, 7:55277–55284, 2019.
  187. Hybrid feature aligned network for salient object detection in optical remote sensing imagery. IEEE TGRS, 60:1–15, 2022.
  188. Detect globally, refine locally: A novel approach to saliency detection. In CVPR, pages 3127–3135, 2018.
  189. An iterative and cooperative top-down and bottom-up inference network for salient object detection. In CVPR, pages 5968–5977, 2019.
  190. Salient object detection with pyramid attention and salient edges. In CVPR, pages 1448–1457, 2019.
  191. Pyramid vision transformer: A versatile backbone for dense prediction without convolutions. In ICCV, pages 568–578, 2021.
  192. Pvt v2: Improved baselines with pyramid vision transformer. Computational Visual Media, 8:415–424, 2022.
  193. Non-local neural networks. In CVPR, pages 7794–7803, 2018.
  194. Pixels, regions, and objects: Multiple enhancement for salient object detection. In CVPR, pages 10031–10040, 2023.
  195. Smoothed dilated convolutions for improved dense prediction. In ACM SIGKDD, pages 2486–2495, 2018.
  196. Boxpolyp: Boost generalized polyp segmentation using extra coarse bounding box annotations. In MICCAI, pages 67–77, 2022.
  197. Shallow attention network for polyp segmentation. In MICCAI, pages 699–708, 2021.
  198. F3net: Fusion, feedback and focus for salient object detection. In AAAI, pages 12321–12328, 2020.
  199. Label decoupling framework for salient object detection. In CVPR, pages 13025–13034, 2020.
  200. Dynamic selective network for rgb-d salient object detection. IEEE TIP, 30:9179–9192, 2021.
  201. Cvt: Introducing convolutions to vision transformers. In ICCV, pages 22–31, 2021.
  202. Precise yet efficient semantic calibration and refinement in convnets for real-time polyp segmentation from colonoscopy videos. In AAAI, pages 2916–2924, 2021.
  203. Camera calibration and geo-location estimation from two shadow trajectories. CVIU, 114:915–927, 2010.
  204. A mutual learning method for salient object detection with intertwined multi-supervision. In CVPR, pages 8150–8159, 2019.
  205. Tree-structured kronecker convolutional network for semantic segmentation. In ICME, pages 940–945, 2019.
  206. Mobilesal: Extremely efficient rgb-d salient object detection. IEEE TPAMI, 44:10261–10269, 2021.
  207. Edn: Salient object detection via extremely-downsampled network. IEEE TIP, 31:3125–3136, 2022.
  208. Cascaded partial decoder for fast and accurate salient object detection. In CVPR, pages 3907–3916, 2019.
  209. Stacked cross refinement network for edge-aware salient object detection. In ICCV, pages 7264–7273, 2019.
  210. Source-free depth for object pop-out. In ICCV, pages 1032–1042, 2023.
  211. Pyramid grafting network for one-stage high resolution saliency detection. In CVPR, pages 11717–11726, 2022.
  212. Segformer: Simple and efficient design for semantic segmentation with transformers. In NeurIPS, pages 12077–12090, 2021.
  213. Segmenting transparent objects in the wild. In ECCV, pages 696–711, 2020.
  214. Segmenting transparent objects in the wild with transformer. In IJCAI, pages 1194–1200, 2021.
  215. Aggregated residual transformations for deep neural networks. In CVPR, pages 1492–1500, 2017.
  216. Locate globally, segment locally: A progressive architecture with knowledge review network for salient object detection. In AAAI, pages 3004–3012, 2021.
  217. Structured modeling of joint deep feature and prediction refinement for salient object detection. In ICCV, pages 3789–3798, 2019.
  218. Mirrornet: Bio-inspired camouflaged object segmentation. IEEE Access, 9:43290–43300, 2021.
  219. Hierarchical saliency detection. In CVPR, pages 1155–1162, 2013.
  220. Saliency detection via graph-based manifold ranking. In CVPR, pages 3166–3173, 2013.
  221. Uncertainty-guided transformer reasoning for camouflaged object detection. In ICCV, pages 4146–4155, 2021.
  222. A dendritic disinhibitory circuit mechanism for pathway-specific gating. Nature communications, 7:12815, 2016.
  223. Silt: Shadow-aware iterative label tuning for learning to detect shadows from noisy labels. In ICCV, pages 12687–12698, 2023.
  224. Denseaspp for semantic segmentation in street scenes. In CVPR, pages 3684–3692, 2018.
  225. Where is my mirror? In ICCV, pages 8809–8818, 2019.
  226. Progressive glass segmentation. IEEE TIP, 31:2920–2933, 2022.
  227. Tokens-to-token vit: Training vision transformers from scratch on imagenet. In ICCV, pages 558–567, 2021.
  228. Towards high-resolution salient object detection. In ICCV, pages 7234–7243, 2019.
  229. Mutual graph learning for camouflaged object detection. In CVPR, pages 12997–13007, 2021.
  230. Mgl: Mutual graph learning for camouflaged object detection. IEEE TIP, 32:1897–1910, 2022.
  231. Cross-modality discrepant interaction network for rgb-d salient object detection. In ACM MM, pages 2094–2102, 2021.
  232. Context encoding for semantic segmentation. In CVPR, pages 7151–7160, 2018.
  233. Uc-net: Uncertainty inspired rgb-d saliency detection via conditional variational autoencoders. In CVPR, pages 8582–8591, 2020.
  234. Rgb-d saliency detection via cascaded mutual information minimization. In ICCV, pages 4338–4347, 2021.
  235. A bi-directional message passing model for salient object detection. In CVPR, pages 1741–1750, 2018.
  236. Capsal: Leveraging captioning to boost semantics for salient object detection. In CVPR, pages 6024–6033, 2019.
  237. Asymmetric two-stream architecture for accurate rgb-d saliency detection. In ECCV, pages 374–390, 2020.
  238. Auto-msfnet: Search multi-scale fusion network for salient object detection. In ACM MM, pages 667–676, 2021.
  239. Select, supplement and focus for rgb-d saliency detection. In CVPR, pages 3472–3481, 2020.
  240. Preynet: Preying on camouflaged objects. In ACM MM, pages 5323–5332, 2022.
  241. C2dfnet: Criss-cross dynamic filter network for rgb-d salient object detection. IEEE TMM, 2022.
  242. Feature reintegration over differential treatment: A top-down and adaptive fusion network for rgb-d salient object detection. In ACM MM, pages 4107–4115, 2020.
  243. Salient object detection by lossless feature reflection. In IJCAI, page 1149–1155, 2018.
  244. Amulet: Aggregating multi-level convolutional features for salient object detection. In ICCV, pages 202–211, 2017.
  245. Dense attention fluid network for salient object detection in optical remote sensing images. IEEE TIP, 30:1305–1317, 2020.
  246. Lesion-aware dynamic kernel for polyp segmentation. In MICCAI, pages 99–109, 2022.
  247. Adaptive context selection for polyp segmentation. In MICCAI, pages 253–262, 2020.
  248. Depth quality-inspired feature manipulation for efficient rgb-d salient object detection. In ACM MM, pages 731–740, 2021.
  249. Saliency hierarchy modeling via generative kernels for salient object detection. In ECCV, pages 570–587, 2022.
  250. Progressive attention guided recurrent network for salient object detection. In CVPR, pages 714–722, 2018.
  251. Transfuse: Fusing transformers and cnns for medical image segmentation. In MICCAI, pages 14–24, 2021.
  252. Image-scale-symmetric cooperative network for defocus blur detection. IEEE TCSVT, 2021.
  253. Pyramid scene parsing network. In CVPR, pages 2881–2890, 2017.
  254. Pyramid scene parsing network. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 2881–2890, 2017.
  255. Contrast prior and fluid pyramid integration for rgbd salient object detection. In CVPR, pages 3922–3931, 2019.
  256. Egnet: Edge guidance network for salient object detection. In ICCV, pages 8779–8788, 2019.
  257. Is depth really necessary for salient object detection? In ACM MM, pages 1745–1754, 2020.
  258. Pyramid feature attention network for saliency detection. In CVPR, pages 3085–3094, 2019.
  259. Defocus blur detection via boosting diversity of deep ensemble networks. IEEE TIP, 30:5426–5438, 2021.
  260. Self-generated defocus blur detection via dual adversarial discriminators. In CVPR, pages 6933–6942, 2021.
  261. United defocus blur detection and deblurring via adversarial promoting learning. In ECCV, pages 569–586, 2022.
  262. Full-scene defocus blur detection with defbd+ via multi-level distillation learning. IEEE TMM, 2023.
  263. Defocus blur detection via multi-stream bottom-top-bottom fully convolutional network. In CVPR, pages 3080–3088, 2018.
  264. Enhancing diversity of defocus blur detectors via cross-ensemble network. In CVPR, pages 8905–8913, 2019.
  265. Suppress and balance: A simple gated network for salient object detection. In ECCV, pages 35–51, 2020.
  266. Automatic polyp segmentation via multi-scale subtraction network. In MICCAI, pages 120–130, 2021.
  267. A single stream network for robust and real-time rgb-d salient object detection. In ECCV, pages 646–662, 2020.
  268. Rgb-d salient object detection with ubiquitous target awareness. IEEE TIP, 30:7717–7731, 2021.
  269. Complementary trilateral decoder for fast and accurate salient object detection. In ACM MM, pages 4967–4975, 2021.
  270. Orsi salient object detection via cross-scale interaction and enlarged receptive field. IEEE GRSL, 20:1–5, 2023.
  271. Distraction-aware shadow detection. In CVPR, pages 5167–5176, 2019.
  272. Rethinking semantic segmentation from a sequence-to-sequence perspective with transformers. In CVPR, pages 6881–6890, 2021.
  273. Detecting camouflaged object in frequency domain. In CVPR, pages 4504–4513, 2022.
  274. Interactive two-stream decoder for accurate and fast saliency detection. In CVPR, pages 9141–9150, 2020.
  275. Mvsalnet: Multi-view augmentation for rgb-d salient object detection. In ECCV, pages 270–287, 2022.
  276. Specificity-preserving rgb-d saliency detection. In ICCV, pages 4681–4691, 2021.
  277. Feature aggregation and propagation network for camouflaged object detection. IEEE TIP, 31:7036–7047, 2022.
  278. Cross-level feature aggregation network for polyp segmentation. Pattern Recognition, 140:109555, 2023.
  279. Edge-aware multiscale feature integration network for salient object detection in optical remote sensing images. IEEE TGRS, 60:1–15, 2022.
  280. Multi-type self-attention guided degraded saliency detection. In AAAI, pages 13082–13089, 2020.
  281. Unet++: Redesigning skip connections to exploit multiscale features in image segmentation. IEEE TMI, 39:1856–1867, 2019.
  282. Pdnet: Prior-model guided depth-enhanced network for salient object detection. In ICME, pages 199–204, 2019.
  283. Chunbiao Zhu and Ge Li. A three-pathway psychobiological framework of salient object detection using stereoscopic technology. In ICCVW, pages 3008–3014, 2017.
  284. Learning to recognize shadows in monochromatic natural images. In CVPR, pages 223–230, 2010.
  285. Bidirectional feature pyramid network with recurrent attention residual modules for shadow detection. In ECCV, pages 121–136, 2018.
  286. Mitigating intensity bias in shadow detection via feature decomposition and reweighting. In ICCV, pages 4702–4711, 2021.
  287. Transfusion: A novel slam method focused on transparent objects. In ICCV, pages 6019–6028, 2021.
  288. A survey on efficient training of transformers. arXiv preprint arXiv:2302.01107, 2023.
  289. Deep embedding features for salient object detection. In AAAI, pages 9340–9347, 2019.
  290. Efficient smoothing of dilated convolutions for image segmentation. arXiv preprint arXiv:1903.07992, 2019.
Citations (8)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now