Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
156 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

IA2U: A Transfer Plugin with Multi-Prior for In-Air Model to Underwater (2312.06955v2)

Published 12 Dec 2023 in cs.CV

Abstract: In underwater environments, variations in suspended particle concentration and turbidity cause severe image degradation, posing significant challenges to image enhancement (IE) and object detection (OD) tasks. Currently, in-air image enhancement and detection methods have made notable progress, but their application in underwater conditions is limited due to the complexity and variability of these environments. Fine-tuning in-air models saves high overhead and has more optional reference work than building an underwater model from scratch. To address these issues, we design a transfer plugin with multiple priors for converting in-air models to underwater applications, named IA2U. IA2U enables efficient application in underwater scenarios, thereby improving performance in Underwater IE and OD. IA2U integrates three types of underwater priors: the water type prior that characterizes the degree of image degradation, such as color and visibility; the degradation prior, focusing on differences in details and textures; and the sample prior, considering the environmental conditions at the time of capture and the characteristics of the photographed object. Utilizing a Transformer-like structure, IA2U employs these priors as query conditions and a joint task loss function to achieve hierarchical enhancement of task-level underwater image features, therefore considering the requirements of two different tasks, IE and OD. Experimental results show that IA2U combined with an in-air model can achieve superior performance in underwater image enhancement and object detection tasks. The code will be made publicly available.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (44)
  1. Sea-thru: A method for removing water from underwater images. In CVPR, pages 1682–1691, 2019.
  2. Diving into haze-lines: Color restoration of underwater images. In BMVC, page 2, 2017.
  3. Cascade r-cnn: Delving into high quality object detection. In CVPR, pages 6154–6162, 2018.
  4. Mmdetection: Open mmlab detection toolbox and benchmark. arXiv preprint arXiv:1906.07155, 2019.
  5. Simple baselines for image restoration. In ECCV, pages 17–33. Springer, 2022.
  6. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929, 2020.
  7. Tood: Task-aligned one-stage object detection. In ICCV, pages 3490–3499, 2021.
  8. Rethinking general underwater object detection: Datasets, challenges, and solutions. Neurocomputing, 517:243–256, 2023.
  9. Underwater ranker: Learn which is better and how to be better. In AAAI, pages 720–709, 2023.
  10. Featenhancer: Enhancing hierarchical features for object detection and beyond under low-light vision. In ICCV, pages 6725–6735, 2023.
  11. Deep residual learning for image recognition. In CVPR, pages 770–778, 2016.
  12. Contrastive semi-supervised learning for underwater image restoration via reliable bank. In CVPR, pages 18145–18155, 2023.
  13. J.S. Jaffe. Computer modeling and the design of optimal underwater imaging systems. IEEE JOE, 15(2):101–111, 1990.
  14. Five a+ network: You only need 9k parameters for underwater image enhancement. arXiv preprint arXiv:2305.08824, 2023.
  15. A perception-aware decomposition and fusion framework for underwater image enhancement. IEEE TCSVT, 33(3):988–1002, 2023.
  16. Probabilistic anchor assignment with iou prediction for object detection. In ECCV, pages 355–371. Springer, 2020.
  17. Underwater scene prior inspired deep underwater image and video enhancement. PR, 98:107038, 2020a.
  18. An underwater image enhancement benchmark dataset and beyond. IEEE TIP, 29:4376–4389, 2020b.
  19. Underwater image enhancement via medium transmission-guided multi-color space embedding. IEEE TIP, 30:4985–5000, 2021.
  20. Focal loss for dense object detection. In ICCV, pages 2999–3007, 2017.
  21. Scale-aware modulation meet transformer. In ICCV, pages 6015–6026, 2023.
  22. Twin adversarial contrastive learning for underwater image enhancement and beyond. IEEE TIP, 31:4922–4936, 2022.
  23. Swin transformer: Hierarchical vision transformer using shifted windows. In ICCV, pages 10012–10022, 2021.
  24. Making a “completely blind” image quality analyzer. IEEE Sign. Process. Letters, 20(3):209–212, 2012.
  25. Shallow-uwnet: Compressed model for underwater image enhancement. In AAAI, pages 15853–15854, 2021.
  26. U-shape transformer for underwater image enhancement. IEEE TIP, 32:3066–3079, 2023.
  27. Sguie-net: Semantic attention guided underwater image enhancement with multi-scale perception. IEEE TIP, 31:6816–6830, 2022.
  28. Ffa-net: Feature fusion attention network for single image dehazing. In AAAI, pages 11908–11915, 2020.
  29. Faster r-cnn: Towards real-time object detection with region proposal networks. IEEE TPAMI, 39(6):1137–1149, 2017.
  30. Fcos: Fully convolutional one-stage object detection. In ICCV, pages 9626–9635, 2019.
  31. Instance normalization: The missing ingredient for fast stylization, 2017.
  32. Attention is all you need. NeurIPS, 30, 2017.
  33. Learning semantic-aware knowledge guidance for low-light image enhancement. In CVPR, pages 1662–1671, 2023.
  34. An underwater color image quality evaluation metric. IEEE TIP, 24(12):6062–6071, 2015.
  35. An underwater image vision enhancement algorithm based on contour bougie morphology. IEEE TGRS, 59(10):8117–8128, 2021.
  36. Tebcf: real-world underwater image texture enhancement model based on blurriness and color fusion. IEEE TGRS, 60:1–15, 2022.
  37. Restormer: Efficient transformer for high-resolution image restoration. In CVPR, pages 5728–5739, 2022.
  38. The unreasonable effectiveness of deep features as a perceptual metric. In CVPR, pages 586–595, 2018.
  39. Bridging the gap between anchor-based and anchor-free detection via adaptive training sample selection. In CVPR, pages 9759–9768, 2020.
  40. Underwater image enhancement via minimal color loss and locally adaptive contrast enhancement. IEEE TIP, 31:3997–4010, 2022.
  41. Ugif-net: An efficient fully guided information flow network for underwater image enhancement. IEEE TGRS, 61:1–17, 2023a.
  42. Underwater camera: Improving visual perception via adaptive dark pixel prior and color correction. IJCV, pages 1–19, 2023b.
  43. Conditional prompt learning for vision-language models. In CVPR, pages 16816–16825, 2022.
  44. Underwater image enhancement with hyper-laplacian reflectance priors. IEEE TIP, 31:5442–5455, 2022.

Summary

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

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