{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/a-simple-episodic-linear-probe-improves","title":"A Simple Episodic Linear Probe Improves Visual Recognition in the Wild","arxiv_id":null,"date":"2022-01-01","proceeding":"CVPR 2022 1","authors":["Yuanzhi Liang","Linchao Zhu","Xiaohan Wang","Yi Yang"],"abstract":"    Understanding network generalization and feature discrimination is an open research problem in visual recognition. Many studies have been conducted to assess the quality of feature representations. One of the simple strategies is to utilize a linear probing classifier to quantitatively evaluate the class accuracy under the obtained features. The typical linear probe is only applied as a proxy at the inference time, but its efficacy in measuring features' suitability for linear classification is largely neglected in training. In this paper, we propose an episodic linear probing (ELP) classifier to reflect the generalization of visual representations in an online manner. ELP is trained with detached features from the network and re-initialized episodically. It demonstrates the discriminability of the visual representations in training. Then, an ELP-suitable Regularization term (ELP-SR) is introduced to reflect the distances of probability distributions between ELP classifier and the main classifier. ELP-SR leverages a re-scaling factor to regularize each sample in training, which modulates the loss function adaptively and encourages the features to be discriminative and generalized. We observe significant improvements in three real-world visual recognition tasks, including fine-grained visual classification, long-tailed visual recognition, and generic object recognition. The performance gains show the effectiveness of our method in improving network generalization and feature discrimination.    ","url_abs":"http://openaccess.thecvf.com//content/CVPR2022/html/Liang_A_Simple_Episodic_Linear_Probe_Improves_Visual_Recognition_in_the_CVPR_2022_paper.html","url_pdf":"http://openaccess.thecvf.com//content/CVPR2022/papers/Liang_A_Simple_Episodic_Linear_Probe_Improves_Visual_Recognition_in_the_CVPR_2022_paper.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":"a-simple-episodic-linear-probe-improves","repo_url":"https://github.com/akira-l/ELP","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"a-simple-episodic-linear-probe-improves","repo_url":"https://github.com/JDAI-CV/DCL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"fine-grained-image-classification","task_name":"Fine-Grained Image Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"long-tail-learning","task_name":"Long-tail Learning"},{"task_slug":"object-recognition","task_name":"Object Recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/fine-grained-image-classification-on-cub-200-1","task":"Fine-Grained Image Classification","dataset":"CUB-200-2011","model":"ELP","rank_in_archive_order":17,"of":30,"metrics":{"Accuracy":"88.8"},"uses_additional_data":false},{"leaderboard":"/sota/fine-grained-image-classification-on-fgvc","task":"Fine-Grained Image Classification","dataset":"FGVC Aircraft","model":"ELP","rank_in_archive_order":39,"of":57,"metrics":{"Accuracy":"92.7"},"uses_additional_data":false},{"leaderboard":"/sota/fine-grained-image-classification-on-stanford","task":"Fine-Grained Image Classification","dataset":"Stanford Cars","model":"ELP","rank_in_archive_order":49,"of":83,"metrics":{"Accuracy":"94.2"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"ELP (naive ResNet50)","rank_in_archive_order":924,"of":1060,"metrics":{"Top 1 Accuracy":"76.13"},"uses_additional_data":false},{"leaderboard":"/sota/long-tail-learning-on-cifar-10-lt-r-10","task":"Long-tail Learning","dataset":"CIFAR-10-LT (ρ=10)","model":"ELP","rank_in_archive_order":32,"of":50,"metrics":{"Error Rate":"11.3"},"uses_additional_data":false},{"leaderboard":"/sota/long-tail-learning-on-cifar-10-lt-r-100","task":"Long-tail Learning","dataset":"CIFAR-10-LT (ρ=100)","model":"ELP","rank_in_archive_order":25,"of":28,"metrics":{"Error Rate":"22"},"uses_additional_data":false},{"leaderboard":"/sota/long-tail-learning-on-cifar-100-lt-r-10","task":"Long-tail Learning","dataset":"CIFAR-100-LT (ρ=10)","model":"ELP","rank_in_archive_order":26,"of":31,"metrics":{"Error Rate":"40.9"},"uses_additional_data":false},{"leaderboard":"/sota/long-tail-learning-on-cifar-100-lt-r-100","task":"Long-tail Learning","dataset":"CIFAR-100-LT (ρ=100)","model":"ELP","rank_in_archive_order":60,"of":66,"metrics":{"Error Rate":"57.6"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"no_arxiv_id","checked_against":null,"by_repo":[{"repo":"akira-l/ELP","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"JDAI-CV/DCL","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"51755908d39e68accd3000c1b396e788c009ef63d51b9ffdce9394ba2a6df19c","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}