{"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/parallel-residual-bi-fusion-feature-pyramid","title":"Parallel Residual Bi-Fusion Feature Pyramid Network for Accurate Single-Shot Object Detection","arxiv_id":"2012.01724","date":"2020-12-03","proceeding":null,"authors":["Ping-Yang Chen","Ming-Ching Chang","Jun-Wei Hsieh","Yong-Sheng Chen"],"abstract":"This paper proposes the Parallel Residual Bi-Fusion Feature Pyramid Network (PRB-FPN) for fast and accurate single-shot object detection. Feature Pyramid (FP) is widely used in recent visual detection, however the top-down pathway of FP cannot preserve accurate localization due to pooling shifting. The advantage of FP is weakened as deeper backbones with more layers are used. In addition, it cannot keep up accurate detection of both small and large objects at the same time. To address these issues, we propose a new parallel FP structure with bi-directional (top-down and bottom-up) fusion and associated improvements to retain high-quality features for accurate localization. We provide the following design improvements: (1) A parallel bifusion FP structure with a bottom-up fusion module (BFM) to detect both small and large objects at once with high accuracy. (2) A concatenation and re-organization (CORE) module provides a bottom-up pathway for feature fusion, which leads to the bi-directional fusion FP that can recover lost information from lower-layer feature maps. (3) The CORE feature is further purified to retain richer contextual information. Such CORE purification in both top-down and bottom-up pathways can be finished in only a few iterations. (4) The adding of a residual design to CORE leads to a new Re-CORE module that enables easy training and integration with a wide range of deeper or lighter backbones. The proposed network achieves state-of-the-art performance on the UAVDT17 and MS COCO datasets. Code is available at https://github.com/pingyang1117/PRBNet_PyTorch.","url_abs":"https://arxiv.org/abs/2012.01724v5","url_pdf":"https://arxiv.org/pdf/2012.01724v5.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":"parallel-residual-bi-fusion-feature-pyramid","repo_url":"https://github.com/pingyang1117/PRBNet_PyTorch","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"multi-object-tracking","task_name":"Multi-Object Tracking"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"real-time-object-detection","task_name":"Real-Time Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/object-detection-on-uavdt","task":"Object Detection","dataset":"UAVDT","model":"PRB-FPN","rank_in_archive_order":1,"of":8,"metrics":{"mAP":"76.55"},"uses_additional_data":false},{"leaderboard":"/sota/real-time-object-detection-on-coco","task":"Real-Time Object Detection","dataset":"COCO (Common Objects in Context)","model":"PRB-FPN6-E-ELAN(1280)","rank_in_archive_order":5,"of":82,"metrics":{"FPS (V100, b=1)":"31","box AP":"56.9"},"uses_additional_data":false},{"leaderboard":"/sota/real-time-object-detection-on-coco","task":"Real-Time Object Detection","dataset":"COCO (Common Objects in Context)","model":"PRB-FPN-MSP","rank_in_archive_order":31,"of":82,"metrics":{"FPS (V100, b=1)":"94","box AP":"53.3"},"uses_additional_data":false},{"leaderboard":"/sota/real-time-object-detection-on-coco","task":"Real-Time Object Detection","dataset":"COCO (Common Objects in Context)","model":"PRB-FPN-ELAN","rank_in_archive_order":43,"of":82,"metrics":{"FPS (V100, b=1)":"70","box AP":"52.5"},"uses_additional_data":false},{"leaderboard":"/sota/real-time-object-detection-on-coco","task":"Real-Time Object Detection","dataset":"COCO (Common Objects in Context)","model":"PRB-FPN-CSP","rank_in_archive_order":46,"of":82,"metrics":{"FPS (V100, b=1)":"113","box AP":"51.8"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2012.01724","atlas_url":"https://app.syntology.ai/?focus=2012.01724","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":"2012.01724"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2012.01724\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2012.01724"},"call":"get_concepts_for_paper(arxiv_id=\"2012.01724\")"}],"by_repo":[{"repo":"pingyang1117/PRBNet_PyTorch","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":"9f432c85e2a63dc6e8b29db7710b7f52bae39dd7742347c423f266a3cc2d9040","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}