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". 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 fuses 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.

翻译：去噪模型已被证明是一种强大的生成模型，但在判别任务中的探索尚少。表征学习在判别任务中至关重要，其定义为“学习数据的表征（或特征），使得在构建分类器或其他预测器时更容易提取有用信息”。本文提出一种新颖的面向表征学习的去噪模型（DenoiseRep），通过联合特征提取与去噪来提升特征判别力。DenoiseRep将主干网络中的每个嵌入层视为一个去噪层，将级联的嵌入层处理为逐级递归去噪特征的过程。这统一了特征提取与去噪的框架：前者将特征从低层到高层逐步嵌入，后者则逐级递归地对特征进行去噪。随后，DenoiseRep融合了特征提取层与去噪层的参数，并从理论上证明了融合前后的等价性，从而实现无需额外计算的特征去噪。DenoiseRep是一种无标签算法，可渐进提升特征质量，同时在有标签时也能与标签信息互补。在多种判别性视觉任务上的实验结果——包括重识别（Market-1501、DukeMTMC-reID、MSMT17、CUHK-03、vehicleID）、图像分类（ImageNet、UB200、Oxford-Pet、Flowers）、目标检测（COCO）、图像分割（ADE20K）——均显示出稳定的显著性能提升。我们还在CNN（ResNet）与Transformer（ViT、Swin、Vmamda）架构上验证了其有效性。