{"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-long-tailed-recognition-baseline-via","title":"A Simple Long-Tailed Recognition Baseline via Vision-Language Model","arxiv_id":"2111.14745","date":"2021-11-29","proceeding":null,"authors":["Teli Ma","Shijie Geng","Mengmeng Wang","Jing Shao","Jiasen Lu","Hongsheng Li","Peng Gao","Yu Qiao"],"abstract":"The visual world naturally exhibits a long-tailed distribution of open classes, which poses great challenges to modern visual systems. Existing approaches either perform class re-balancing strategies or directly improve network modules to address the problem. However, they still train models with a finite set of predefined labels, limiting their supervision information and restricting their transferability to novel instances. Recent advances in large-scale contrastive visual-language pretraining shed light on a new pathway for visual recognition. With open-vocabulary supervisions, pretrained contrastive vision-language models learn powerful multimodal representations that are promising to handle data deficiency and unseen concepts. By calculating the semantic similarity between visual and text inputs, visual recognition is converted to a vision-language matching problem. Inspired by this, we propose BALLAD to leverage contrastive vision-language models for long-tailed recognition. We first continue pretraining the vision-language backbone through contrastive learning on a specific long-tailed target dataset. Afterward, we freeze the backbone and further employ an additional adapter layer to enhance the representations of tail classes on balanced training samples built with re-sampling strategies. Extensive experiments have been conducted on three popular long-tailed recognition benchmarks. As a result, our simple and effective approach sets the new state-of-the-art performances and outperforms competitive baselines with a large margin. Code is released at https://github.com/gaopengcuhk/BALLAD.","url_abs":"https://arxiv.org/abs/2111.14745v1","url_pdf":"https://arxiv.org/pdf/2111.14745v1.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-long-tailed-recognition-baseline-via","repo_url":"https://github.com/gaopengcuhk/ballad","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"long-tail-learning","task_name":"Long-tail Learning"},{"task_slug":"semantic-similarity","task_name":"Semantic Similarity"},{"task_slug":"semantic-textual-similarity","task_name":"Semantic Textual Similarity"}],"methods":[{"method_slug":"adapter","method_name":"Adapter"},{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/long-tail-learning-on-cifar-100-lt-r-100","task":"Long-tail Learning","dataset":"CIFAR-100-LT (ρ=100)","model":"BALLAD (ViT-B/16)","rank_in_archive_order":5,"of":66,"metrics":{"Error Rate":"22.2"},"uses_additional_data":true},{"leaderboard":"/sota/long-tail-learning-on-imagenet-lt","task":"Long-tail Learning","dataset":"ImageNet-LT","model":"BALLAD(ResNet-50×16)","rank_in_archive_order":6,"of":69,"metrics":{"Top-1 Accuracy":"76.5"},"uses_additional_data":false},{"leaderboard":"/sota/long-tail-learning-on-imagenet-lt","task":"Long-tail Learning","dataset":"ImageNet-LT","model":"BALLAD(ViT-B-16)","rank_in_archive_order":7,"of":69,"metrics":{"Top-1 Accuracy":"75.7"},"uses_additional_data":false},{"leaderboard":"/sota/long-tail-learning-on-imagenet-lt","task":"Long-tail Learning","dataset":"ImageNet-LT","model":"BALLAD(ResNet-101)","rank_in_archive_order":8,"of":69,"metrics":{"Top-1 Accuracy":"70.5"},"uses_additional_data":false},{"leaderboard":"/sota/long-tail-learning-on-imagenet-lt","task":"Long-tail Learning","dataset":"ImageNet-LT","model":"BALLAD(ResNet-50)","rank_in_archive_order":10,"of":69,"metrics":{"Top-1 Accuracy":"67.2"},"uses_additional_data":false},{"leaderboard":"/sota/long-tail-learning-on-places-lt","task":"Long-tail Learning","dataset":"Places-LT","model":"BALLAD(ViT-B-16)","rank_in_archive_order":5,"of":29,"metrics":{"Top-1 Accuracy":"49.5"},"uses_additional_data":true},{"leaderboard":"/sota/long-tail-learning-on-places-lt","task":"Long-tail Learning","dataset":"Places-LT","model":"BALLAD(ResNet-50×16)","rank_in_archive_order":6,"of":29,"metrics":{"Top-1 Accuracy":"49.3"},"uses_additional_data":true},{"leaderboard":"/sota/long-tail-learning-on-places-lt","task":"Long-tail Learning","dataset":"Places-LT","model":"BALLAD(ResNet-101)","rank_in_archive_order":8,"of":29,"metrics":{"Top-1 Accuracy":"47.9"},"uses_additional_data":true},{"leaderboard":"/sota/long-tail-learning-on-places-lt","task":"Long-tail Learning","dataset":"Places-LT","model":"BALLAD(ResNet-50)","rank_in_archive_order":10,"of":29,"metrics":{"Top-1 Accuracy":"46.5"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2111.14745","atlas_url":"https://app.syntology.ai/?focus=2111.14745","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2111.14745"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2111.14745\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2111.14745"},"call":"get_concepts_for_paper(arxiv_id=\"2111.14745\")"}],"by_repo":[{"repo":"gaopengcuhk/ballad","kind":"official","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":"a2e3c623ec7f281578517cba9d7f23eea73c8afcbf30524ea1e9f39c47535462","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}