{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/denoisereid-denoising-model-for","title":"DenoiseRep: Denoising Model for Representation Learning","arxiv_id":"2406.08773","date":"2024-06-13","proceeding":null,"authors":["Zhengrui Xu","Guan'an Wang","Xiaowen Huang","Jitao Sang"],"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\". 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.","url_abs":"https://arxiv.org/abs/2406.08773v4","url_pdf":"https://arxiv.org/pdf/2406.08773v4.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"denoisereid-denoising-model-for","repo_url":"https://github.com/wangguanan/denoiserep","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"fine-grained-image-classification","task_name":"Fine-Grained Image Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-retrieval","task_name":"Image Retrieval"},{"task_slug":"image-segmentation","task_name":"Image Segmentation"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"person-re-identification","task_name":"Person Re-Identification"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"image-classification","task_name":"image-classification"},{"task_slug":"model","task_name":"model"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2406.08773","atlas_url":"https://app.syntology.ai/?focus=2406.08773","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.08773"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/wangguanan/DenoiseRep","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/wangguanan/denoiserep","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":11,"ran_honours":2,"ran_violates":1,"unverified":8},"by_repo_kind":{"official":{"samples":22,"ran":14,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"cc79b939ebdd3e56","entry":"DenoiseLayer","repo":"wangguanan/denoiserep","repo_kind":"official","path":"denoiserep_op/denoiserep/denoise_layer.py","file_url":"https://github.com/wangguanan/denoiserep/blob/HEAD/denoiserep_op/denoiserep/denoise_layer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"cc79b939ebdd3e56"}},{"code_sha256_prefix":"86b013bf84701f06","entry":"SinusoidalPositionEmbeddings","repo":"wangguanan/denoiserep","repo_kind":"official","path":"denoiserep_op/denoiserep/denoise_layer.py","file_url":"https://github.com/wangguanan/denoiserep/blob/HEAD/denoiserep_op/denoiserep/denoise_layer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"86b013bf84701f06"}},{"code_sha256_prefix":"742e7c8b503f4e2f","entry":"_linear_beta_schedule","repo":"wangguanan/denoiserep","repo_kind":"official","path":"denoiserep_op/denoiserep/denoise_layer.py","file_url":"https://github.com/wangguanan/denoiserep/blob/HEAD/denoiserep_op/denoiserep/denoise_layer.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"742e7c8b503f4e2f"}},{"code_sha256_prefix":"973ac6b787475389","entry":"auto_resume_helper","repo":"wangguanan/DenoiseRep","repo_kind":"official","path":"Classification/imagenet/Swin-Transformer/utils_simmim.py","file_url":"https://github.com/wangguanan/DenoiseRep/blob/HEAD/Classification/imagenet/Swin-Transformer/utils_simmim.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"973ac6b787475389"}},{"code_sha256_prefix":"9fe330952c4ee761","entry":"build_optimizer","repo":"wangguanan/DenoiseRep","repo_kind":"official","path":"Classification/imagenet/Swin-Transformer/optimizer.py","file_url":"https://github.com/wangguanan/DenoiseRep/blob/HEAD/Classification/imagenet/Swin-Transformer/optimizer.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9fe330952c4ee761"}},{"code_sha256_prefix":"016895042cc7e7ef","entry":"build_scheduler","repo":"wangguanan/DenoiseRep","repo_kind":"official","path":"Classification/imagenet/Swin-Transformer/lr_scheduler.py","file_url":"https://github.com/wangguanan/DenoiseRep/blob/HEAD/Classification/imagenet/Swin-Transformer/lr_scheduler.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"016895042cc7e7ef"}},{"code_sha256_prefix":"414c3f1f64f991c2","entry":"count_conv2d_layers","repo":"wangguanan/DenoiseRep","repo_kind":"official","path":"denoiserep_op/denoiserep/denoise_conv2d.py","file_url":"https://github.com/wangguanan/DenoiseRep/blob/HEAD/denoiserep_op/denoiserep/denoise_conv2d.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"414c3f1f64f991c2"}},{"code_sha256_prefix":"1d9b9dbedc11ca9d","entry":"count_linear_layers","repo":"wangguanan/DenoiseRep","repo_kind":"official","path":"denoiserep_op/denoiserep/denoise_linear.py","file_url":"https://github.com/wangguanan/DenoiseRep/blob/HEAD/denoiserep_op/denoiserep/denoise_linear.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1d9b9dbedc11ca9d"}},{"code_sha256_prefix":"588f3ddb7ae2b2a1","entry":"count_vit_linear_layers","repo":"wangguanan/DenoiseRep","repo_kind":"official","path":"denoiserep_op/denoiserep/denoise_linear.py","file_url":"https://github.com/wangguanan/DenoiseRep/blob/HEAD/denoiserep_op/denoiserep/denoise_linear.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"588f3ddb7ae2b2a1"}},{"code_sha256_prefix":"eec1e7cba51d5e8e","entry":"get_grad_norm","repo":"wangguanan/DenoiseRep","repo_kind":"official","path":"Classification/imagenet/Swin-Transformer/utils.py","file_url":"https://github.com/wangguanan/DenoiseRep/blob/HEAD/Classification/imagenet/Swin-Transformer/utils.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"eec1e7cba51d5e8e"}},{"code_sha256_prefix":"59c3a4f0d92e6970","entry":"load_checkpoint","repo":"wangguanan/DenoiseRep","repo_kind":"official","path":"Classification/imagenet/Swin-Transformer/utils.py","file_url":"https://github.com/wangguanan/DenoiseRep/blob/HEAD/Classification/imagenet/Swin-Transformer/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"59c3a4f0d92e6970"}},{"code_sha256_prefix":"8c60d1a4218dfd1b","entry":"load_checkpoint","repo":"wangguanan/DenoiseRep","repo_kind":"official","path":"Classification/imagenet/Swin-Transformer/utils_simmim.py","file_url":"https://github.com/wangguanan/DenoiseRep/blob/HEAD/Classification/imagenet/Swin-Transformer/utils_simmim.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8c60d1a4218dfd1b"}},{"code_sha256_prefix":"6ba8cee9f5daea41","entry":"pair","repo":"wangguanan/DenoiseRep","repo_kind":"official","path":"Classification/cifar-10/vision-transformers-cifar10/models/vit.py","file_url":"https://github.com/wangguanan/DenoiseRep/blob/HEAD/Classification/cifar-10/vision-transformers-cifar10/models/vit.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6ba8cee9f5daea41"}},{"code_sha256_prefix":"b33222a09fc93bec","entry":"set_weight_decay","repo":"wangguanan/DenoiseRep","repo_kind":"official","path":"Classification/imagenet/Swin-Transformer/optimizer.py","file_url":"https://github.com/wangguanan/DenoiseRep/blob/HEAD/Classification/imagenet/Swin-Transformer/optimizer.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b33222a09fc93bec"}},{"code_sha256_prefix":"f39904cfad74aa8e","entry":"_extract","repo":"wangguanan/denoiserep","repo_kind":"official","path":"denoiserep_op/denoiserep/denoise_layer.py","file_url":"https://github.com/wangguanan/denoiserep/blob/HEAD/denoiserep_op/denoiserep/denoise_layer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f39904cfad74aa8e"}},{"code_sha256_prefix":"0c32459bef92ff8c","entry":"auto_resume_helper","repo":"wangguanan/DenoiseRep","repo_kind":"official","path":"Classification/imagenet/Swin-Transformer/utils.py","file_url":"https://github.com/wangguanan/DenoiseRep/blob/HEAD/Classification/imagenet/Swin-Transformer/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0c32459bef92ff8c"}},{"code_sha256_prefix":"b0a5beb34716d5a6","entry":"check_keywords_in_name","repo":"wangguanan/DenoiseRep","repo_kind":"official","path":"Classification/imagenet/Swin-Transformer/optimizer.py","file_url":"https://github.com/wangguanan/DenoiseRep/blob/HEAD/Classification/imagenet/Swin-Transformer/optimizer.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b0a5beb34716d5a6"}},{"code_sha256_prefix":"80450600f7f09b0a","entry":"create_logger","repo":"wangguanan/DenoiseRep","repo_kind":"official","path":"Classification/imagenet/Swin-Transformer/logger.py","file_url":"https://github.com/wangguanan/DenoiseRep/blob/HEAD/Classification/imagenet/Swin-Transformer/logger.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"80450600f7f09b0a"}},{"code_sha256_prefix":"6233cec4ca021c61","entry":"fuse_parameters","repo":"wangguanan/DenoiseRep","repo_kind":"official","path":"denoiserep_op/denoiserep/denoise_layer.py","file_url":"https://github.com/wangguanan/DenoiseRep/blob/HEAD/denoiserep_op/denoiserep/denoise_layer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6233cec4ca021c61"}},{"code_sha256_prefix":"b3d06a45875ffab2","entry":"get_config","repo":"wangguanan/DenoiseRep","repo_kind":"official","path":"Classification/imagenet/Swin-Transformer/config.py","file_url":"https://github.com/wangguanan/DenoiseRep/blob/HEAD/Classification/imagenet/Swin-Transformer/config.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b3d06a45875ffab2"}},{"code_sha256_prefix":"366afd054c0b5902","entry":"get_ploss","repo":"wangguanan/DenoiseRep","repo_kind":"official","path":"denoiserep_op/denoiserep/denoise_layer.py","file_url":"https://github.com/wangguanan/DenoiseRep/blob/HEAD/denoiserep_op/denoiserep/denoise_layer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"366afd054c0b5902"}},{"code_sha256_prefix":"0b3a64a417dd8616","entry":"update_config","repo":"wangguanan/DenoiseRep","repo_kind":"official","path":"Classification/imagenet/Swin-Transformer/config.py","file_url":"https://github.com/wangguanan/DenoiseRep/blob/HEAD/Classification/imagenet/Swin-Transformer/config.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0b3a64a417dd8616"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}