{"url":"/task/object-categorization","name":"Object Categorization","slug":"object-categorization","description_markdown":"Object categorization identifies which label, from a\r\ngiven set, best corresponds to an image region defined by\r\nan input image and bounding box.","categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":80,"papers_with_code":25,"benchmarks":1,"benchmark_tables_in_archive":1,"benchmark_tables_shown":1,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":2,"subtasks":0,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/object-categorization-on-grit","slug":"object-categorization-on-grit","dataset":"GRIT","dataset_url":"/dataset/grit","rows_in_archive":4,"metrics":["Categorization (ablation)","Categorization (test)"],"first_row_in_archive_order":{"model":"Unified-IOXL","paper_title":"Unified-IO: A Unified Model for Vision, Language, and Multi-Modal Tasks","paper_url":"/paper/unified-io-a-unified-model-for-vision","paper_date":"2022-06-17","arxiv_id":"2206.08916","code_links":[],"syntology":null}}],"datasets":[{"url":"/dataset/grit","name":"GRIT","full_name":"General Robust Image Task Benchmark","num_papers_in_archive":16},{"url":"/dataset/ur5-tool-dataset","name":"UR5 Tool Dataset","full_name":"","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":25,"of":25,"tagged_in_all":80,"items":[{"url":"/paper/learning-transferable-visual-models-from","title":"Learning Transferable Visual Models From Natural Language Supervision","date":"2021-02-26","arxiv_id":"2103.00020","repositories_listed":82,"syntology":{"n":20,"n_ran":16,"n_unverified":4,"n_pointer_only":16}},{"url":"/paper/segnet-a-deep-convolutional-encoder-decoder-1","title":"SegNet: A Deep Convolutional Encoder-Decoder Architecture for Robust Semantic Pixel-Wise Labelling","date":"2015-05-27","arxiv_id":"1505.07293","repositories_listed":5,"syntology":null},{"url":"/paper/unifying-architectures-tasks-and-modalities","title":"OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework","date":"2022-02-07","arxiv_id":"2202.03052","repositories_listed":4,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/cost-effective-active-learning-for-deep-image","title":"Cost-Effective Active Learning for Deep Image Classification","date":"2017-01-13","arxiv_id":"1701.03551","repositories_listed":4,"syntology":{"n":13,"n_ran":2,"n_unverified":11,"n_pointer_only":2}},{"url":"/paper/unsupervised-domain-adaptation-through-inter","title":"Unsupervised Domain Adaptation through Inter-modal Rotation for RGB-D Object Recognition","date":"2020-04-21","arxiv_id":"2004.10016","repositories_listed":3,"syntology":{"n":10,"n_ran":5,"n_unverified":5,"n_pointer_only":4}},{"url":"/paper/brain-like-object-recognition-with-high","title":"Brain-Like Object Recognition with High-Performing Shallow Recurrent ANNs","date":"2019-09-13","arxiv_id":"1909.06161","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":3}},{"url":"/paper/part-aware-fine-grained-object-categorization","title":"Part-Aware Fine-grained Object Categorization using Weakly Supervised Part Detection Network","date":"2018-06-16","arxiv_id":"1806.06198","repositories_listed":2,"syntology":null},{"url":"/paper/data-augmentation-instead-of-explicit","title":"Data augmentation instead of explicit regularization","date":"2018-06-11","arxiv_id":"1806.03852","repositories_listed":2,"syntology":null},{"url":"/paper/deep-learning-human-mind-for-automated-visual","title":"Deep Learning Human Mind for Automated Visual Classification","date":"2016-09-01","arxiv_id":"1609.00344","repositories_listed":2,"syntology":null},{"url":"/paper/vision-cnns-trained-to-estimate-spatial","title":"Vision CNNs trained to estimate spatial latents learned similar ventral-stream-aligned representations","date":"2024-12-12","arxiv_id":"2412.09115","repositories_listed":1,"syntology":{"n":4,"n_ran":0,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/vocabulary-informed-zero-shot-and-open-set","title":"Vocabulary-informed Zero-shot and Open-set Learning","date":"2023-01-03","arxiv_id":"2301.00998","repositories_listed":1,"syntology":null},{"url":"/paper/roboflow-100-a-rich-multi-domain-object","title":"Roboflow 100: A Rich, Multi-Domain Object Detection Benchmark","date":"2022-11-24","arxiv_id":"2211.13523","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/fine-grained-object-categorization-for","title":"Enhancing Fine-Grained 3D Object Recognition using Hybrid Multi-Modal Vision Transformer-CNN Models","date":"2022-10-03","arxiv_id":"2210.04613","repositories_listed":1,"syntology":null},{"url":"/paper/grit-general-robust-image-task-benchmark","title":"GRIT: General Robust Image Task Benchmark","date":"2022-04-28","arxiv_id":"2204.13653","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/category-orthogonal-object-features-guide","title":"Category-orthogonal object features guide information processing in recurrent neural networks trained for object categorization","date":"2021-11-15","arxiv_id":"2111.07898","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/iaunet-global-context-aware-feature-learning","title":"IAUnet: Global Context-Aware Feature Learning for Person Re-Identification","date":"2020-09-02","arxiv_id":"2009.01035","repositories_listed":1,"syntology":null},{"url":"/paper/learning-physical-graph-representations-from","title":"Learning Physical Graph Representations from Visual Scenes","date":"2020-06-22","arxiv_id":"2006.12373","repositories_listed":1,"syntology":null},{"url":"/paper/learning-robust-visual-representations-using","title":"Learning robust visual representations using data augmentation invariance","date":"2019-06-11","arxiv_id":"1906.04547","repositories_listed":1,"syntology":null},{"url":"/paper/training-neural-networks-to-have-brain-like","title":"Improved object recognition using neural networks trained to mimic the brain's statistical properties","date":"2019-05-25","arxiv_id":"1905.10679","repositories_listed":1,"syntology":null},{"url":"/paper/recurrent-convolutional-fusion-for-rgb-d","title":"Recurrent Convolutional Fusion for RGB-D Object Recognition","date":"2018-06-05","arxiv_id":"1806.01673","repositories_listed":1,"syntology":null},{"url":"/paper/are-we-done-with-object-recognition-the-icub","title":"Are we done with object recognition? The iCub robot's perspective","date":"2017-09-28","arxiv_id":"1709.09882","repositories_listed":1,"syntology":null},{"url":"/paper/learning-deep-visual-object-models-from-noisy","title":"Learning Deep Visual Object Models From Noisy Web Data: How to Make it Work","date":"2017-02-28","arxiv_id":"1702.08513","repositories_listed":1,"syntology":null},{"url":"/paper/systematic-evaluation-of-cnn-advances-on-the","title":"Systematic evaluation of CNN advances on the ImageNet","date":"2016-06-07","arxiv_id":"1606.02228","repositories_listed":1,"syntology":null},{"url":"/paper/rotationnet-joint-object-categorization-and","title":"RotationNet: Joint Object Categorization and Pose Estimation Using Multiviews from Unsupervised Viewpoints","date":"2016-03-20","arxiv_id":"1603.06208","repositories_listed":1,"syntology":null},{"url":"/paper/collaborative-receptive-field-learning","title":"Collaborative Receptive Field Learning","date":"2014-02-02","arxiv_id":"1402.0170","repositories_listed":1,"syntology":null}],"syntology_records":9,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}