# Lightweight Adaptive Feature De-drifting for Compressed Image Classification

arXiv: https://arxiv.org/abs/2401.01724 · HTML: https://mlsanity.com/paper/2401.01724/

## Key facts

- Cited by 46 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 69 references that are in the map.
- First posted on arXiv 3 Jan 2024.

## Builds on (most cited first, 30 of 39)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [Restormer: Efficient Transformer for High-Resolution Image Restoration](https://mlsanity.com/paper/2111.09881/) (2021)
- [Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising](https://mlsanity.com/paper/1608.03981/) (2016)
- [Accurate Image Super-Resolution Using Very Deep Convolutional Networks](https://mlsanity.com/paper/1511.04587/) (2015)
- [RepVGG: Making VGG-style ConvNets Great Again](https://mlsanity.com/paper/2101.03697/) (2021)
- [Dreaming to Distill: Data-free Knowledge Transfer via DeepInversion](https://mlsanity.com/paper/1912.08795/) (2019)
- [Learning Enriched Features for Real Image Restoration and Enhancement](https://mlsanity.com/paper/2003.06792/) (2020)
- [Fast, Accurate, and Lightweight Super-Resolution with Cascading Residual Network](https://mlsanity.com/paper/1803.08664/) (2018)
- [MemNet: A Persistent Memory Network for Image Restoration](https://mlsanity.com/paper/1708.02209/) (2017)
- [Residual Non-local Attention Networks for Image Restoration](https://mlsanity.com/paper/1903.10082/) (2019)
- [Residual Dense Network for Image Restoration](https://mlsanity.com/paper/1812.10477/) (2018)
- [Efficient and Explicit Modelling of Image Hierarchies for Image Restoration](https://mlsanity.com/paper/2303.00748/) (2023)
- [Compression Artifacts Reduction by a Deep Convolutional Network](https://mlsanity.com/paper/1504.06993/) (2015)
- [Zero-Shot Knowledge Distillation in Deep Networks](https://mlsanity.com/paper/1905.08114/) (2019)
- [Unsupervised Domain Adaptation of Object Detectors: A Survey](https://mlsanity.com/paper/2105.13502/) (2021)
- [Diverse Branch Block: Building a Convolution as an Inception-like Unit](https://mlsanity.com/paper/2103.13425/) (2021)
- [Source-Free Unsupervised Domain Adaptation: A Survey](https://mlsanity.com/paper/2301.00265/) (2022)
- [A critical analysis of self-supervision, or what we can learn from a single image](https://mlsanity.com/paper/1904.13132/) (2019)
- [Towards Flexible Blind JPEG Artifacts Removal](https://mlsanity.com/paper/2109.14573/) (2021)
- [DHP: Differentiable Meta Pruning via HyperNetworks](https://mlsanity.com/paper/2003.13683/) (2020)
- [Learning with Privileged Information for Efficient Image Super-Resolution](https://mlsanity.com/paper/2007.07524/) (2020)
- [When Image Denoising Meets High-Level Vision Tasks: A Deep Learning Approach](https://mlsanity.com/paper/1706.04284/) (2017)
- [Deep Generative Adversarial Compression Artifact Removal](https://mlsanity.com/paper/1704.02518/) (2017)

## Built on by (most cited first, 30 of 46)

- [Robust Watermarking Using Generative Priors Against Image Editing: From Benchmarking to Advances](https://mlsanity.com/paper/2410.18775/) (2024)
- [Pixel to Gaussian: Ultra-Fast Continuous Super-Resolution with 2D Gaussian Modeling](https://mlsanity.com/paper/2503.06617/) (2025)
- [Efficient Real-world Image Super-Resolution Via Adaptive Directional Gradient Convolution](https://mlsanity.com/paper/2405.07023/) (2024)
- [Towards Universal Modal Tracking with Online Dense Temporal Token Learning](https://mlsanity.com/paper/2507.20177/) (2025)
- [Directing Mamba to Complex Textures: An Efficient Texture-Aware State Space Model for Image Restoration](https://mlsanity.com/paper/2501.16583/) (2025)
- [Unveiling Hidden Details: A RAW Data-Enhanced Paradigm for Real-World Super-Resolution](https://mlsanity.com/paper/2411.10798/) (2024)
- [Exploring Decoupled Spatio-Temporal Consistency Learning and Self-Prompting Evolution for Self-Supervised Tracking](https://mlsanity.com/paper/2507.21606/) (2025)
- [Multi-Reward as Condition for Instruction-based Image Editing](https://mlsanity.com/paper/2411.04713/) (2024)
- [PMQ-VE: Progressive Multi-Frame Quantization for Video Enhancement](https://mlsanity.com/paper/2505.12266/) (2025)
- [Data-free Knowledge Distillation with Diffusion Models](https://mlsanity.com/paper/2504.00870/) (2025)
- [Multi-Scale Representation Learning for Image Restoration with State-Space Model](https://mlsanity.com/paper/2408.10145/) (2024)
- [LUVE : Latent-Cascaded Ultra-High-Resolution Video Generation with Dual Frequency Experts](https://mlsanity.com/paper/2602.11564/) (2026)
- [RobustGS: Unified Boosting of Feedforward 3D Gaussian Splatting under Low-Quality Conditions](https://mlsanity.com/paper/2508.03077/) (2025)
- [Progressive Compositionality in Text-to-Image Generative Models](https://mlsanity.com/paper/2410.16719/) (2024)
- [S3Mamba: Arbitrary-Scale Super-Resolution via Scaleable State Space Model](https://mlsanity.com/paper/2411.11906/) (2024)
- [FC3DNet: A Fully Connected Encoder-Decoder for Efficient Demoir'eing](https://mlsanity.com/paper/2406.14912/) (2024)
- [Intra and Inter Parser-Prompted Transformers for Effective Image Restoration](https://mlsanity.com/paper/2503.14037/) (2025)
- [DaLPSR: Leverage Degradation-Aligned Language Prompt for Real-World Image Super-Resolution](https://mlsanity.com/paper/2406.16477/) (2024)
- [Dual-domain Modulation Network for Lightweight Image Super-Resolution](https://mlsanity.com/paper/2503.10047/) (2025)
- [EventMamba: Enhancing Spatio-Temporal Locality with State Space Models for Event-Based Video Reconstruction](https://mlsanity.com/paper/2503.19721/) (2025)
- [Depth-Synergized Mamba Meets Memory Experts for All-Day Image Reflection Separation](https://mlsanity.com/paper/2601.00322/) (2026)
- [Enhancing Zero-Shot Brain Tumor Subtype Classification via Fine-Grained Patch-Text Alignment](https://mlsanity.com/paper/2508.01602/) (2025)
- [Seeing Through the Rain: Resolving High-Frequency Conflicts in Deraining and Super-Resolution via Diffusion Guidance](https://mlsanity.com/paper/2511.12419/) (2025)
- [DPMambaIR: All-in-One Image Restoration via Degradation-Aware Prompt State Space Model](https://mlsanity.com/paper/2504.17732/) (2025)
- [Diffusion-Based Image Editing: An Unforeseen Adversary to Robust Invisible Watermarks](https://mlsanity.com/paper/2511.05598/) (2025)
- [SSCM: A Spatial-Semantic Consistent Model for Multi-Contrast MRI Super-Resolution](https://mlsanity.com/paper/2509.18593/) (2025)
- [Vanishing Watermarks: Diffusion-Based Image Editing Undermines Robust Invisible Watermarking](https://mlsanity.com/paper/2602.20680/) (2026)
- [EventGait: Towards Robust Gait Recognition with Event Streams](https://mlsanity.com/paper/2605.22139/) (2026)
- [Event-Illumination Collaborative Low-light Image Enhancement with a High-resolution Real-world Dataset](https://mlsanity.com/paper/2605.22186/) (2026)
- [FADPNet: Frequency-Aware Dual-Path Network for Face Super-Resolution](https://mlsanity.com/paper/2506.14121/) (2025)

## Abstract (arXiv)

JPEG is a widely used compression scheme to efficiently reduce the volume of transmitted images. The artifacts appear among blocks due to the information loss, which not only affects the quality of images but also harms the subsequent high-level tasks in terms of feature drifting. High-level vision models trained on high-quality images will suffer performance degradation when dealing with compressed images, especially on mobile devices. Numerous learning-based JPEG artifact removal methods have been proposed to handle visual artifacts. However, it is not an ideal choice to use these JPEG artifact removal methods as a pre-processing for compressed image classification for the following reasons: 1. These methods are designed for human vision rather than high-level vision models; 2. These methods are not efficient enough to serve as pre-processing on resource-constrained devices. To address these issues, this paper proposes a novel lightweight AFD module to boost the performance of pre-trained image classification models when facing compressed images. First, a FDE-Net is devised to generate the spatial-wise FDM in the DCT domain. Next, the estimated FDM is transmitted to the FE-Net to generate the mapping relationship between degraded features and corresponding high-quality features. A simple but effective RepConv block equipped with structural re-parameterization is utilized in FE-Net, which enriches feature representation in the training phase while maintaining efficiency in the deployment phase. After training on limited compressed images, the AFD-Module can serve as a "plug-and-play" model for pre-trained classification models to improve their performance on compressed images. Experiments demonstrate that our proposed AFD module can comprehensively improve the accuracy of the pre-trained classification models and significantly outperform the existing methods.