DenoiseRep: Denoising Model for Representation Learning

Zhengrui Xu, Xiaowen Huang

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 22 functions out of this paper's own repositories and ran 14 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

Repositories linked to this paper

• wangguanan/denoiserep — marked official in Papers with Code; named in the paper
• wangguanan/DenoiseRep

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

The denoising model has been proven a powerful generative model but has little exploration of discriminative tasks. Representation learning is important in discriminative tasks, which is defined as "learning representations (or features) of the data that make it easier to extract useful information when building classifiers or other predictors" [4]. In this paper, we propose a novel Denoising Model for Representation Learning (DenoiseRep) to improve feature discrimination with joint feature extraction and denoising. DenoiseRep views each embedding layer in a backbone as a denoising layer, processing the cascaded embedding layers as if we are recursively denoise features step-by-step. This unifies the frameworks of feature extraction and denoising, where the former progressively embeds features from low-level to high-level, and the latter recursively denoises features step-by-step. After that, DenoiseRep fus es the parameters of feature extraction and denoising layers, and theoretically demonstrates its equivalence before and after the fusion, thus making feature denoising computation-free. DenoiseRep is a label-free algorithm that incrementally improves features but also complementary to the label if available. Experimental results on various discriminative vision tasks, including re-identification (Market-1501, DukeMTMC-reID, MSMT17, CUHK-03, vehicleID), image classification (ImageNet, UB200, Oxford-Pet, Flowers), object detection (COCO), image segmentation (ADE20K) show stability and impressive improvements. We also validate its effectiveness on the CNN (ResNet) and Transformer (ViT, Swin, Vmamda) architectures. Code is available at https://github.com/wangguanan/DenoiseRep. † Equal Contribution. ‡ Project Lead.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2406.08773")
get_code_for_paper("2406.08773")
have("2406.08773")

Connect an agent — have() is free.