{"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/grounding-dino-1-5-advance-the-edge-of-open","title":"Grounding DINO 1.5: Advance the \"Edge\" of Open-Set Object Detection","arxiv_id":"2405.10300","date":"2024-05-16","proceeding":null,"authors":["Tianhe Ren","Qing Jiang","Shilong Liu","Zhaoyang Zeng","Wenlong Liu","Han Gao","Hongjie Huang","Zhengyu Ma","Xiaoke Jiang","Yihao Chen","Yuda Xiong","Hao Zhang","Feng Li","Peijun Tang","Kent Yu","Lei Zhang"],"abstract":"This paper introduces Grounding DINO 1.5, a suite of advanced open-set object detection models developed by IDEA Research, which aims to advance the \"Edge\" of open-set object detection. The suite encompasses two models: Grounding DINO 1.5 Pro, a high-performance model designed for stronger generalization capability across a wide range of scenarios, and Grounding DINO 1.5 Edge, an efficient model optimized for faster speed demanded in many applications requiring edge deployment. The Grounding DINO 1.5 Pro model advances its predecessor by scaling up the model architecture, integrating an enhanced vision backbone, and expanding the training dataset to over 20 million images with grounding annotations, thereby achieving a richer semantic understanding. The Grounding DINO 1.5 Edge model, while designed for efficiency with reduced feature scales, maintains robust detection capabilities by being trained on the same comprehensive dataset. Empirical results demonstrate the effectiveness of Grounding DINO 1.5, with the Grounding DINO 1.5 Pro model attaining a 54.3 AP on the COCO detection benchmark and a 55.7 AP on the LVIS-minival zero-shot transfer benchmark, setting new records for open-set object detection. Furthermore, the Grounding DINO 1.5 Edge model, when optimized with TensorRT, achieves a speed of 75.2 FPS while attaining a zero-shot performance of 36.2 AP on the LVIS-minival benchmark, making it more suitable for edge computing scenarios. Model examples and demos with API will be released at https://github.com/IDEA-Research/Grounding-DINO-1.5-API","url_abs":"https://arxiv.org/abs/2405.10300v2","url_pdf":"https://arxiv.org/pdf/2405.10300v2.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":"grounding-dino-1-5-advance-the-edge-of-open","repo_url":"https://github.com/idea-research/grounding-dino-1.5-api","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"grounding-dino-1-5-advance-the-edge-of-open","repo_url":"https://github.com/idea-research/grounded-sam-2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"grounding-dino-1-5-advance-the-edge-of-open","repo_url":"https://github.com/mit-han-lab/efficientvit","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"edge-computing","task_name":"Edge-computing"},{"task_slug":"few-shot-object-detection","task_name":"Few-Shot Object Detection"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"zero-shot-object-detection","task_name":"Zero-Shot Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"dino","method_name":"DINO"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"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":"residual-connection","method_name":"Residual Connection"},{"method_slug":"speed","method_name":"SPEED"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"vision-transformer","method_name":"Vision Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/few-shot-object-detection-on-odinw-13","task":"Few-Shot Object Detection","dataset":"ODinW-13","model":"Grounding DINO 1.5 Pro","rank_in_archive_order":1,"of":3,"metrics":{"Average Score":"66.3"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-object-detection-on-odinw-35","task":"Few-Shot Object Detection","dataset":"ODinW-35","model":"Grounding DINO 1.5 Pro","rank_in_archive_order":1,"of":3,"metrics":{"Average Score":"54.7"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-lvis-v1-0-minival","task":"Object Detection","dataset":"LVIS v1.0 minival","model":"Grounding DINO 1.5 Pro","rank_in_archive_order":3,"of":6,"metrics":{"box AP":"68.1"},"uses_additional_data":true},{"leaderboard":"/sota/object-detection-on-lvis-v1-0-val","task":"Object Detection","dataset":"LVIS v1.0 val","model":"Grounding DINO 1.5 Pro","rank_in_archive_order":2,"of":15,"metrics":{"box AP":"63.5","box APr":"64.0"},"uses_additional_data":true},{"leaderboard":"/sota/object-detection-on-odinw-full-shot-13-tasks","task":"Object Detection","dataset":"ODinW Full-Shot 13 Tasks","model":"Grounding DINO 1.5 Pro","rank_in_archive_order":2,"of":8,"metrics":{"AP":"72.4"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-odinw-full-shot-35-tasks","task":"Object Detection","dataset":"ODinW Full-shot 35 Tasks","model":"Grounding DINO 1.5 Pro","rank_in_archive_order":1,"of":2,"metrics":{"AP":"72.4"},"uses_additional_data":true},{"leaderboard":"/sota/zero-shot-object-detection-on-lvis-v1-0","task":"Zero-Shot Object Detection","dataset":"LVIS v1.0 minival","model":"Grounding DINO 1.6 Pro (without LVIS data)","rank_in_archive_order":2,"of":11,"metrics":{"AP":"57.7"},"uses_additional_data":true},{"leaderboard":"/sota/zero-shot-object-detection-on-lvis-v1-0","task":"Zero-Shot Object Detection","dataset":"LVIS v1.0 minival","model":"Grounding DINO 1.5 Pro (without LVIS data)","rank_in_archive_order":3,"of":11,"metrics":{"AP":"55.7"},"uses_additional_data":true},{"leaderboard":"/sota/zero-shot-object-detection-on-lvis-v1-0-val","task":"Zero-Shot Object Detection","dataset":"LVIS v1.0 val","model":"Grounding DINO 1.6 Pro (without LVIS data)","rank_in_archive_order":2,"of":9,"metrics":{"AP":"51.1"},"uses_additional_data":true},{"leaderboard":"/sota/zero-shot-object-detection-on-lvis-v1-0-val","task":"Zero-Shot Object Detection","dataset":"LVIS v1.0 val","model":"Grounding DINO 1.5 Pro (without LVIS data)","rank_in_archive_order":3,"of":9,"metrics":{"AP":"47.7"},"uses_additional_data":true},{"leaderboard":"/sota/zero-shot-object-detection-on-mscoco","task":"Zero-Shot Object Detection","dataset":"MSCOCO","model":"Grounding DINO 1.6 Pro (without COCO data)","rank_in_archive_order":1,"of":7,"metrics":{"AP":"55.4"},"uses_additional_data":true},{"leaderboard":"/sota/zero-shot-object-detection-on-mscoco","task":"Zero-Shot Object Detection","dataset":"MSCOCO","model":"Grounding DINO 1.5 Pro (without COCO data)","rank_in_archive_order":3,"of":7,"metrics":{"AP":"54.3"},"uses_additional_data":true},{"leaderboard":"/sota/zero-shot-object-detection-on-odinw","task":"Zero-Shot Object Detection","dataset":"ODinW","model":"Grounding DINO 1.5 Pro","rank_in_archive_order":2,"of":5,"metrics":{"Average Score":"30.2"},"uses_additional_data":true}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2405.10300","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.10300"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/idea-research/grounded-sam-2","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mit-han-lab/efficientvit","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/idea-research/grounding-dino-1.5-api","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":1,"unverified":1},"by_repo_kind":{"official":{"samples":2,"ran":1,"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":"99bec20b2fa588c5","entry":"resize_image_with_aspect_ratio","repo":"idea-research/grounding-dino-1.5-api","repo_kind":"official","path":"gradio_app.py","file_url":"https://github.com/idea-research/grounding-dino-1.5-api/blob/HEAD/gradio_app.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":"99bec20b2fa588c5"}},{"code_sha256_prefix":"b7ec463c59fa4f64","entry":"visualize","repo":"idea-research/grounding-dino-1.5-api","repo_kind":"official","path":"gdino/visualize.py","file_url":"https://github.com/idea-research/grounding-dino-1.5-api/blob/HEAD/gdino/visualize.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":"b7ec463c59fa4f64"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}