Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
119 tokens/sec
GPT-4o
56 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
6 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

DiffuMask: Synthesizing Images with Pixel-level Annotations for Semantic Segmentation Using Diffusion Models (2303.11681v4)

Published 21 Mar 2023 in cs.CV

Abstract: Collecting and annotating images with pixel-wise labels is time-consuming and laborious. In contrast, synthetic data can be freely available using a generative model (e.g., DALL-E, Stable Diffusion). In this paper, we show that it is possible to automatically obtain accurate semantic masks of synthetic images generated by the Off-the-shelf Stable Diffusion model, which uses only text-image pairs during training. Our approach, called DiffuMask, exploits the potential of the cross-attention map between text and image, which is natural and seamless to extend the text-driven image synthesis to semantic mask generation. DiffuMask uses text-guided cross-attention information to localize class/word-specific regions, which are combined with practical techniques to create a novel high-resolution and class-discriminative pixel-wise mask. The methods help to reduce data collection and annotation costs obviously. Experiments demonstrate that the existing segmentation methods trained on synthetic data of DiffuMask can achieve a competitive performance over the counterpart of real data (VOC 2012, Cityscapes). For some classes (e.g., bird), DiffuMask presents promising performance, close to the stateof-the-art result of real data (within 3% mIoU gap). Moreover, in the open-vocabulary segmentation (zero-shot) setting, DiffuMask achieves a new SOTA result on Unseen class of VOC 2012. The project website can be found at https://weijiawu.github.io/DiffusionMask/.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (67)
  1. Efficient interactive annotation of segmentation datasets with polygon-rnn++. In Proceedings of the IEEE conference on Computer Vision and Pattern Recognition, pages 859–868, 2018.
  2. Learning pixel-level semantic affinity with image-level supervision for weakly supervised semantic segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 4981–4990, 2018.
  3. Towards single stage weakly supervised semantic segmentation. arXiv preprint arXiv:2106.10309, 2021.
  4. Exploiting a joint embedding space for generalized zero-shot semantic segmentation. In Proc. ICCV, 2021.
  5. Romain Beaumont. Clip retrieval: Easily compute clip embeddings and build a clip retrieval system with them. GitHub, 2022.
  6. This dataset does not exist: training models from generated images. In ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 1–5. IEEE, 2020.
  7. Yolov4: Optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934, 2020.
  8. Zero-shot semantic segmentation. NeurIPS, 2019.
  9. Beat the mturkers: Automatic image labeling from weak 3d supervision. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 3198–3205, 2014.
  10. Understanding and utilizing deep neural networks trained with noisy labels. In International Conference on Machine Learning, pages 1062–1070. PMLR, 2019.
  11. Masked-attention mask transformer for universal image segmentation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 1290–1299, 2022.
  12. Sign: Spatial-information incorporated generative network for generalized zero-shot semantic segmentation. In Proc. ICCV, 2021.
  13. Self-ensembling with gan-based data augmentation for domain adaptation in semantic segmentation. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 6830–6840, 2019.
  14. The cityscapes dataset for semantic urban scene understanding. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 3213–3223, 2016.
  15. Unsupervised learning of scene structure for synthetic data generation, Sept. 9 2021. US Patent App. 17/117,425.
  16. Decoupling zero-shot semantic segmentation. In Proc. CVPR, 2022.
  17. Nice: Non-linear independent components estimation. arXiv preprint arXiv:1410.8516, 2014.
  18. The pascal visual object classes (voc) challenge. International journal of computer vision, 88(2):303–338, 2010.
  19. Neural-sim: Learning to generate training data with nerf. In European Conference on Computer Vision, pages 477–493. Springer, 2022.
  20. Dall-e for detection: Language-driven context image synthesis for object detection. arXiv preprint arXiv:2206.09592, 2022.
  21. Training deep neural-networks using a noise adaptation layer. In Proc. Int. Conf. Learn. Representations, 2017.
  22. Generative adversarial networks. Communications of the ACM, 63(11):139–144, 2020.
  23. Mix-of-show: Decentralized low-rank adaptation for multi-concept customization of diffusion models. arXiv preprint arXiv:2305.18292, 2023.
  24. Context-aware feature generation for zero-shot semantic segmentation. In ACM MM, 2020.
  25. Imagenet auto-annotation with segmentation propagation. International Journal of Computer Vision, 110(3):328–348, 2014.
  26. Mask r-cnn. In Proceedings of the IEEE international conference on computer vision, pages 2961–2969, 2017.
  27. Is synthetic data from generative models ready for image recognition? arXiv preprint arXiv:2210.07574, 2022.
  28. Meta-sim: Learning to generate synthetic datasets. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 4551–4560, 2019.
  29. Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114, 2013.
  30. Efficient inference in fully connected crfs with gaussian edge potentials. Advances in neural information processing systems, 24, 2011.
  31. Box2seg: Attention weighted loss and discriminative feature learning for weakly supervised segmentation. In European Conference on Computer Vision, pages 290–308. Springer, 2020.
  32. Anti-adversarially manipulated attributions for weakly and semi-supervised semantic segmentation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 4071–4080, 2021.
  33. Bbam: Bounding box attribution map for weakly supervised semantic and instance segmentation. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 2643–2652, 2021.
  34. Bigdatasetgan: Synthesizing imagenet with pixel-wise annotations. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 21330–21340, 2022.
  35. Guiding text-to-image diffusion model towards grounded generation. arXiv preprint arXiv:2301.05221, 2023.
  36. Scribblesup: Scribble-supervised convolutional networks for semantic segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 3159–3167, 2016.
  37. Microsoft coco: Common objects in context. In Proc. ECCV, 2014.
  38. Fast interactive object annotation with curve-gcn. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 5257–5266, 2019.
  39. Improving robustness without sacrificing accuracy with patch gaussian augmentation. arXiv preprint arXiv:1906.02611, 2019.
  40. Learning with noisy labels. 2013.
  41. Imaginarynet: Learning object detectors without real images and annotations. arXiv preprint arXiv:2210.06886, 2022.
  42. Glide: Towards photorealistic image generation and editing with text-guided diffusion models. arXiv preprint arXiv:2112.10741, 2021.
  43. Confident learning: Estimating uncertainty in dataset labels. Journal of Artificial Intelligence Research, 70:1373–1411, 2021.
  44. A closer look at self-training for zero-label semantic segmentation. In Proc. CVPRW, 2021.
  45. Dreamfusion: Text-to-3d using 2d diffusion. arXiv preprint arXiv:2209.14988, 2022.
  46. Learning transferable visual models from natural language supervision. In International conference on machine learning, pages 8748–8763. PMLR, 2021.
  47. Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.06125, 2022.
  48. High-resolution image synthesis with latent diffusion models. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 10684–10695, 2022.
  49. U-net: Convolutional networks for biomedical image segmentation. In Medical Image Computing and Computer-Assisted Intervention–MICCAI 2015: 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III 18, pages 234–241. Springer, 2015.
  50. Learning visual words for weakly-supervised semantic segmentation. In IJCAI, volume 5, page 6, 2021.
  51. Learning affinity from attention: End-to-end weakly-supervised semantic segmentation with transformers. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 16846–16855, 2022.
  52. Photorealistic text-to-image diffusion models with deep language understanding. arXiv preprint arXiv:2205.11487, 2022.
  53. Laion-5b: An open large-scale dataset for training next generation image-text models. arXiv preprint arXiv:2210.08402, 2022.
  54. Deep unsupervised learning using nonequilibrium thermodynamics. In International Conference on Machine Learning, pages 2256–2265. PMLR, 2015.
  55. Learning from noisy labels with deep neural networks: A survey. IEEE Transactions on Neural Networks and Learning Systems, 2022.
  56. Unsupervised domain adaptation in semantic segmentation: a review. Technologies, 8(2):35, 2020.
  57. Investigating prompt engineering in diffusion models. arXiv preprint arXiv:2211.15462, 2022.
  58. Embedded discriminative attention mechanism for weakly supervised semantic segmentation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 16765–16774, 2021.
  59. Synthetic data supervised salient object detection. In Proceedings of the 30th ACM International Conference on Multimedia, pages 5557–5565, 2022.
  60. Leveraging auxiliary tasks with affinity learning for weakly supervised semantic segmentation. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 6984–6993, 2021.
  61. Cutmix: Regularization strategy to train strong classifiers with localizable features. In Proceedings of the IEEE/CVF international conference on computer vision, pages 6023–6032, 2019.
  62. Affinity attention graph neural network for weakly supervised semantic segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021.
  63. Image gans meet differentiable rendering for inverse graphics and interpretable 3d neural rendering. arXiv preprint arXiv:2010.09125, 2020.
  64. Datasetgan: Efficient labeled data factory with minimal human effort. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 10145–10155, 2021.
  65. Flowtext: Synthesizing realistic scene text video with optical flow estimation. arXiv preprint arXiv:2305.03327, 2023.
  66. Generative prompt model for weakly supervised object localization. arXiv preprint arXiv:2307.09756, 2023.
  67. Scene parsing through ade20k dataset. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 633–641, 2017.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (5)
  1. Weijia Wu (47 papers)
  2. Yuzhong Zhao (18 papers)
  3. Mike Zheng Shou (165 papers)
  4. Hong Zhou (61 papers)
  5. Chunhua Shen (404 papers)
Citations (101)
View on Semantic Scholar

Summary

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

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