Few-Shot Domain Adaptation for Learned Image Compression

• URL: http://arxiv.org/abs/2409.11111v1
• Date: Tue, 17 Sep 2024 12:05:29 GMT
• Title: Few-Shot Domain Adaptation for Learned Image Compression
• Authors: Tianyu Zhang, Haotian Zhang, Yuqi Li, Li Li, Dong Liu,
• Abstract summary: Learned image compression (LIC) has achieved state-of-the-art rate-distortion performance. LIC models usually suffer from significant performance degradation when applied to out-of-training-domain images. We propose a few-shot domain adaptation method for LIC by integrating plug-and-play adapters into pre-trained models.
• Score: 24.37696296367332
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Learned image compression (LIC) has achieved state-of-the-art rate-distortion performance, deemed promising for next-generation image compression techniques. However, pre-trained LIC models usually suffer from significant performance degradation when applied to out-of-training-domain images, implying their poor generalization capabilities. To tackle this problem, we propose a few-shot domain adaptation method for LIC by integrating plug-and-play adapters into pre-trained models. Drawing inspiration from the analogy between latent channels and frequency components, we examine domain gaps in LIC and observe that out-of-training-domain images disrupt pre-trained channel-wise decomposition. Consequently, we introduce a method for channel-wise re-allocation using convolution-based adapters and low-rank adapters, which are lightweight and compatible to mainstream LIC schemes. Extensive experiments across multiple domains and multiple representative LIC schemes demonstrate that our method significantly enhances pre-trained models, achieving comparable performance to H.266/VVC intra coding with merely 25 target-domain samples. Additionally, our method matches the performance of full-model finetune while transmitting fewer than $2\%$ of the parameters.

Related papers

• CALLIC: Content Adaptive Learning for Lossless Image Compression [64.47244912937204]
  CALLIC sets a new state-of-the-art (SOTA) for learned lossless image compression. We propose a content-aware autoregressive self-attention mechanism by leveraging convolutional gating operations. During encoding, we decompose pre-trained layers, including depth-wise convolutions, using low-rank matrices and then adapt the incremental weights on testing image by Rate-guided Progressive Fine-Tuning (RPFT) RPFT fine-tunes with gradually increasing patches that are sorted in descending order by estimated entropy, optimizing learning process and reducing adaptation time.
  arXiv  Detail & Related papers  (2024-12-23T10:41:18Z)
• Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think [72.48325960659822]
  One main bottleneck in training large-scale diffusion models for generation lies in effectively learning these representations. We study this by introducing a straightforward regularization called REPresentation Alignment (REPA), which aligns the projections of noisy input hidden states in denoising networks with clean image representations obtained from external, pretrained visual encoders. The results are striking: our simple strategy yields significant improvements in both training efficiency and generation quality when applied to popular diffusion and flow-based transformers, such as DiTs and SiTs.
  arXiv  Detail & Related papers  (2024-10-09T14:34:53Z)
• Effective Diffusion Transformer Architecture for Image Super-Resolution [63.254644431016345]
  We design an effective diffusion transformer for image super-resolution (DiT-SR) In practice, DiT-SR leverages an overall U-shaped architecture, and adopts a uniform isotropic design for all the transformer blocks. We analyze the limitation of the widely used AdaLN, and present a frequency-adaptive time-step conditioning module.
  arXiv  Detail & Related papers  (2024-09-29T07:14:16Z)
• A Rate-Distortion-Classification Approach for Lossy Image Compression [0.0]
  In lossy image compression, the objective is to achieve minimal signal distortion while compressing images to a specified bit rate. To bridge the gap between image compression and visual analysis, we propose a Rate-Distortion-Classification (RDC) model for lossy image compression.
  arXiv  Detail & Related papers  (2024-05-06T14:11:36Z)
• DGNet: Dynamic Gradient-Guided Network for Water-Related Optics Image Enhancement [77.0360085530701]
  Underwater image enhancement (UIE) is a challenging task due to the complex degradation caused by underwater environments. Previous methods often idealize the degradation process, and neglect the impact of medium noise and object motion on the distribution of image features. Our approach utilizes predicted images to dynamically update pseudo-labels, adding a dynamic gradient to optimize the network's gradient space.
  arXiv  Detail & Related papers  (2023-12-12T06:07:21Z)
• Progressive Learning with Visual Prompt Tuning for Variable-Rate Image Compression [60.689646881479064]
  We propose a progressive learning paradigm for transformer-based variable-rate image compression. Inspired by visual prompt tuning, we use LPM to extract prompts for input images and hidden features at the encoder side and decoder side, respectively. Our model outperforms all current variable image methods in terms of rate-distortion performance and approaches the state-of-the-art fixed image compression methods trained from scratch.
  arXiv  Detail & Related papers  (2023-11-23T08:29:32Z)
• Frequency-Aware Transformer for Learned Image Compression [64.28698450919647]
  We propose a frequency-aware transformer (FAT) block that for the first time achieves multiscale directional ananlysis for Learned Image Compression (LIC) The FAT block comprises frequency-decomposition window attention (FDWA) modules to capture multiscale and directional frequency components of natural images. We also introduce frequency-modulation feed-forward network (FMFFN) to adaptively modulate different frequency components, improving rate-distortion performance.
  arXiv  Detail & Related papers  (2023-10-25T05:59:25Z)
• Dynamic Low-Rank Instance Adaptation for Universal Neural Image Compression [33.92792778925365]
  We propose a low-rank adaptation approach to address the rate-distortion drop observed in out-of-domain datasets. Our proposed method exhibits universality across diverse image datasets.
  arXiv  Detail & Related papers  (2023-08-15T12:17:46Z)
• LLIC: Large Receptive Field Transform Coding with Adaptive Weights for Learned Image Compression [27.02281402358164]
  We propose Large Receptive Field Transform Coding with Adaptive Weights for Learned Image Compression. We introduce a few large kernelbased depth-wise convolutions to reduce more redundancy while maintaining modest complexity. Our LLIC models achieve state-of-the-art performances and better trade-offs between performance and complexity.
  arXiv  Detail & Related papers  (2023-04-19T11:19:10Z)
• Learned Image Compression with Mixed Transformer-CNN Architectures [21.53261818914534]
  We propose an efficient parallel Transformer-CNN Mixture (TCM) block with a controllable complexity. Inspired by the recent progress of entropy estimation models and attention modules, we propose a channel-wise entropy model with parameter-efficient swin-transformer-based attention. Experimental results demonstrate our proposed method achieves state-of-the-art rate-distortion performances.
  arXiv  Detail & Related papers  (2023-03-27T08:19:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.