{"url":"/task/novel-object-detection","name":"Novel Object Detection","slug":"novel-object-detection","description_markdown":"Novel Object Detection is a challenging task introduced by Fomenko et.al.  in their paper \"Learning to Discover and Detect Objects\". The goal in this task is to measure mAP performance on known as well as novel classes, where the known classes correspond to the 80 COCO classes, and the novel classes are the remaining 1123 classes from LVIS dataset. Thus, during training the model can only be trained with annotations from COCO dataset, but during evaluation/inference it is expected to BOTH classify and detect objects belonging to ALL the classes in the LVIS dataset.","categories":[{"name":"Computer Vision","url":"/area/computer-vision"},{"name":"Methodology","url":"/area/methodology"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":53,"papers_with_code":24,"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":1,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/novel-object-detection-on-lvis-v1-0-val","slug":"novel-object-detection-on-lvis-v1-0-val","dataset":"LVIS v1.0 val","dataset_url":"/dataset/lvis","rows_in_archive":5,"metrics":["All mAP","Known mAP","Novel mAP"],"first_row_in_archive_order":{"model":"Cooperative Foundational Models","paper_title":"Enhancing Novel Object Detection via Cooperative Foundational Models","paper_url":"/paper/enhancing-novel-object-detection-via","paper_date":"2023-11-19","arxiv_id":"2311.12068","code_links":[{"title":"rohit901/cooperative-foundational-models","url":"https://github.com/rohit901/cooperative-foundational-models"}],"syntology":null}}],"datasets":[{"url":"/dataset/lvis","name":"LVIS","full_name":"","num_papers_in_archive":551}],"subtasks":[],"parent_tasks":[{"url":"/task/2d-object-detection","name":"2D Object Detection"}],"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":24,"of":24,"tagged_in_all":53,"items":[{"url":"/paper/mamba-yolo-ssms-based-yolo-for-object","title":"Mamba YOLO: A Simple Baseline for Object Detection with State Space Model","date":"2024-06-09","arxiv_id":"2406.05835","repositories_listed":2,"syntology":null},{"url":"/paper/codenet-algorithm-hardware-co-design-for","title":"CoDeNet: Efficient Deployment of Input-Adaptive Object Detection on Embedded FPGAs","date":"2020-06-12","arxiv_id":"2006.08357","repositories_listed":2,"syntology":null},{"url":"/paper/grid-r-cnn","title":"Grid R-CNN","date":"2018-11-29","arxiv_id":"1811.12030","repositories_listed":2,"syntology":{"n":3,"n_ran":0,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/multi-branch-auxiliary-fusion-yolo-with-re","title":"Multi-Branch Auxiliary Fusion YOLO with Re-parameterization Heterogeneous Convolutional for accurate object detection","date":"2024-07-05","arxiv_id":"2407.04381","repositories_listed":1,"syntology":null},{"url":"/paper/knowledge-distillation-in-yolox-vit-for-side","title":"Knowledge Distillation in YOLOX-ViT for Side-Scan Sonar Object Detection","date":"2024-03-14","arxiv_id":"2403.09313","repositories_listed":1,"syntology":null},{"url":"/paper/fine-grained-prototypes-distillation-for-few","title":"Fine-Grained Prototypes Distillation for Few-Shot Object Detection","date":"2024-01-15","arxiv_id":"2401.07629","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-novel-object-detection-via","title":"Enhancing Novel Object Detection via Cooperative Foundational Models","date":"2023-11-19","arxiv_id":"2311.12068","repositories_listed":1,"syntology":null},{"url":"/paper/beyond-the-benchmark-detecting-diverse","title":"Beyond the Benchmark: Detecting Diverse Anomalies in Videos","date":"2023-10-03","arxiv_id":"2310.01904","repositories_listed":1,"syntology":null},{"url":"/paper/dst-det-simple-dynamic-self-training-for-open","title":"DST-Det: Simple Dynamic Self-Training for Open-Vocabulary Object Detection","date":"2023-10-02","arxiv_id":"2310.01393","repositories_listed":1,"syntology":null},{"url":"/paper/chasing-day-and-night-towards-robust-and","title":"Chasing Day and Night: Towards Robust and Efficient All-Day Object Detection Guided by an Event Camera","date":"2023-09-17","arxiv_id":"2309.09297","repositories_listed":1,"syntology":null},{"url":"/paper/desco-learning-object-recognition-with-rich","title":"DesCo: Learning Object Recognition with Rich Language Descriptions","date":"2023-06-24","arxiv_id":"2306.14060","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_unverified":1,"n_pointer_only":4}},{"url":"/paper/learning-to-discover-and-detect-objects","title":"Learning to Discover and Detect Objects","date":"2022-10-19","arxiv_id":"2210.10774","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/scaling-novel-object-detection-with-weakly","title":"Scaling Novel Object Detection with Weakly Supervised Detection Transformers","date":"2022-07-11","arxiv_id":"2207.05205","repositories_listed":1,"syntology":null},{"url":"/paper/cvt-assd-convolutional-vision-transformer","title":"CvT-ASSD: Convolutional vision-Transformer Based Attentive Single Shot MultiBox Detector","date":"2021-10-24","arxiv_id":"2110.12364","repositories_listed":1,"syntology":null},{"url":"/paper/a-unified-objective-for-novel-class-discovery","title":"A Unified Objective for Novel Class Discovery","date":"2021-08-19","arxiv_id":"2108.08536","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/sarnet-a-dataset-for-deep-learning-assisted","title":"SaRNet: A Dataset for Deep Learning Assisted Search and Rescue with Satellite Imagery","date":"2021-07-26","arxiv_id":"2107.12469","repositories_listed":1,"syntology":null},{"url":"/paper/instance-segmentation-of-microscopic","title":"Instance Segmentation of Microscopic Foraminifera","date":"2021-05-15","arxiv_id":"2105.14191","repositories_listed":1,"syntology":null},{"url":"/paper/universal-prototype-augmentation-for-few-shot","title":"Universal-Prototype Enhancing for Few-Shot Object Detection","date":"2021-03-01","arxiv_id":"2103.01077","repositories_listed":1,"syntology":null},{"url":"/paper/open-world-semi-supervised-learning-1","title":"Open-World Semi-Supervised Learning","date":"2021-02-06","arxiv_id":"2102.03526","repositories_listed":1,"syntology":null},{"url":"/paper/automatic-signboard-detection-from-natural","title":"Automatic Signboard Detection and Localization in Densely Populated Developing Cities","date":"2020-03-04","arxiv_id":"2003.01936","repositories_listed":1,"syntology":null},{"url":"/paper/toward-self-supervised-object-detection-in","title":"Learning to Detect and Retrieve Objects from Unlabeled Videos","date":"2019-05-27","arxiv_id":"1905.11137","repositories_listed":1,"syntology":null},{"url":"/paper/cad-net-a-context-aware-detection-network-for","title":"CAD-Net: A Context-Aware Detection Network for Objects in Remote Sensing Imagery","date":"2019-03-03","arxiv_id":"1903.00857","repositories_listed":1,"syntology":null},{"url":"/paper/geometry-based-region-proposals-for-real-time","title":"Geometry-Based Region Proposals for Real-Time Robot Detection of Tabletop Objects","date":"2017-03-14","arxiv_id":"1703.04665","repositories_listed":1,"syntology":null},{"url":"/paper/t-cnn-tubelets-with-convolutional-neural","title":"T-CNN: Tubelets with Convolutional Neural Networks for Object Detection from Videos","date":"2016-04-09","arxiv_id":"1604.02532","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}}],"syntology_records":5,"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"}}