Domain Adaptation for Learned Image Compression with Supervised Adapters
Abstract: In Learned Image Compression (LIC), a model is trained at encoding and decoding images sampled from a source domain, often outperforming traditional codecs on natural images; yet its performance may be far from optimal on images sampled from different domains. In this work, we tackle the problem of adapting a pre-trained model to multiple target domains by plugging into the decoder an adapter module for each of them, including the source one. Each adapter improves the decoder performance on a specific domain, without the model forgetting about the images seen at training time. A gate network computes the weights to optimally blend the contributions from the adapters when the bitstream is decoded. We experimentally validate our method over two state-of-the-art pre-trained models, observing improved rate-distortion efficiency on the target domains without penalties on the source domain. Furthermore, the gate's ability to find similarities with the learned target domains enables better encoding efficiency also for images outside them.
- Siwei Ma et al., “Image and video compression with neural networks: A review,” Transactions on Circuits and Systems, 2019.
- Jizheng Xu et al., “Overview of the emerging hevc screen content coding extension,” IEEE Transactions on Circuits and Systems for Video Technology, 2015.
- Koki Tsubota et al., “Universal deep image compression via content-adaptive optimization with adapters,” in IEEE W. C. on Applications of Computer Vision, 2023.
- Johannes Ballé et al., “End-to-end optimized image compression,” in 5th International Conference on Learning Representations, 2017.
- Alberto Presta et al., “A differentiable entropy model for learned image compression,” in International Conference on Image Analysis and Processing, 2023.
- Johannes Ballé et al., “Variational image compression with a scale hyperprior,” in International Conference on Learning Representations (ICLR), 2018.
- David Minnen et al., “Joint autoregressive and hierarchical priors for learned image compression,” Advances in neural information processing systems, 2018.
- “Channel-wise autoregressive entropy models for learned image compression,” in International Conference on Image Processing), 2020.
- Zhengxue Cheng et al., “Learned image compression with discretized gaussian mixture likelihoods and attention modules,” in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2020.
- Renjie Zou et al., “The devil is in the details: Window-based attention for image compression,” in IEEE conference on computer vision and pattern recognition, 2022.
- Ming Lu et al., “Transformer-based image compression,” in 2022 Data Compression Conference (DCC). IEEE, 2022.
- Jinming Liu et al., “Learned image compression with mixed transformer-cnn architectures,” in IEEE/CVF Conf. on Computer Vision and Pattern Recognition, 2023.
- Sudeep Katakol et al., “Danice: Domain adaptation without forgetting in neural image compression,” in IEEE Conf. on Computer Vision and Pattern Recognition, 2021.
- Johannes Ballé et al., “Density modeling of images using a generalized normalization transformation,” in 4th International Conference on Learning Representations, 2016.
- Yi-Lin Sung et al., “Vl-adapter: Parameter-efficient transfer learning for vision-and-language tasks,” in IEEE Conf. on Computer Vision and Pattern Recognition, 2022.
- Jean Bégaint et al., “Compressai: a pytorch library and evaluation platform for end-to-end compression research,” arXiv preprint arXiv:2011.03029, 2020.
- Alina Kuznetsova et al., “The open images dataset v4: Unified image classification, object detection, and visual relationship detection at scale,” International Journal of Computer Vision, vol. 128, no. 7, pp. 1956–1981, 2020.
- Haohan Wang et al., “Learning robust global representations by penalizing local predictive power,” in Advances in Neural Information Processing Systems, 2019.
- Michael Wilber et al., “Bam! the behance artistic media dataset for recognition beyond photography,” in IEEE international conference on computer vision, 2017.
- Rich Franzen, “Kodak lossless true color image suite,” source: http://r0k. us/graphics/kodak, vol. 4, no. 2, pp. 9, 1999.
- George Toderici et al., “Workshop and challenge on learned image compression (clic2020),” in CVPR, 2020.
- Xingchao Peng et al., “Moment matching for multi-source domain adaptation,” in Proceedings of the IEEE International Conference on Computer Vision, 2019.
- Ajoy Mondal et al., “Iiit-ar-13k: new dataset for graphical object detection in documents,” in 14th IAPR International Workshop, 2020.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.