{"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-novel-region-of-interest-extraction-layer","title":"A novel Region of Interest Extraction Layer for Instance Segmentation","arxiv_id":"2004.13665","date":"2020-04-28","proceeding":null,"authors":["Leonardo Rossi","Akbar Karimi","Andrea Prati"],"abstract":"Given the wide diffusion of deep neural network architectures for computer vision tasks, several new applications are nowadays more and more feasible. Among them, a particular attention has been recently given to instance segmentation, by exploiting the results achievable by two-stage networks (such as Mask R-CNN or Faster R-CNN), derived from R-CNN. In these complex architectures, a crucial role is played by the Region of Interest (RoI) extraction layer, devoted to extracting a coherent subset of features from a single Feature Pyramid Network (FPN) layer attached on top of a backbone. This paper is motivated by the need to overcome the limitations of existing RoI extractors which select only one (the best) layer from FPN. Our intuition is that all the layers of FPN retain useful information. Therefore, the proposed layer (called Generic RoI Extractor - GRoIE) introduces non-local building blocks and attention mechanisms to boost the performance. A comprehensive ablation study at component level is conducted to find the best set of algorithms and parameters for the GRoIE layer. Moreover, GRoIE can be integrated seamlessly with every two-stage architecture for both object detection and instance segmentation tasks. Therefore, the improvements brought about by the use of GRoIE in different state-of-the-art architectures are also evaluated. The proposed layer leads up to gain a 1.1% AP improvement on bounding box detection and 1.7% AP improvement on instance segmentation. The code is publicly available on GitHub repository at https://github.com/IMPLabUniPr/mmdetection/tree/groie_dev","url_abs":"https://arxiv.org/abs/2004.13665v2","url_pdf":"https://arxiv.org/pdf/2004.13665v2.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-novel-region-of-interest-extraction-layer","repo_url":"https://github.com/open-mmlab/mmdetection/tree/master/configs/groie","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"a-novel-region-of-interest-extraction-layer","repo_url":"https://github.com/IMPLabUniPr/mmdetection","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"a-novel-region-of-interest-extraction-layer","repo_url":"https://github.com/IMPLabUniPr/mmdetection-groie","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"a-novel-region-of-interest-extraction-layer","repo_url":"https://github.com/Gugan0905/steel-defect-detection","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"a-novel-region-of-interest-extraction-layer","repo_url":"https://github.com/open-mmlab/mmdetection","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"instance-segmentation","task_name":"Instance Segmentation"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"fpn","method_name":"FPN"},{"method_slug":"groie","method_name":"GRoIE"},{"method_slug":"mask-r-cnn","method_name":"Mask R-CNN"},{"method_slug":"non-local-block","method_name":"Non-Local Block"},{"method_slug":"non-local-operation","method_name":"Non-Local Operation"},{"method_slug":"rpn","method_name":"RPN"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"roi-align","method_name":"RoIAlign"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[{"slug":"groie","name":"GRoIE","full_name":"Generic RoI Extractor"}],"results":[{"leaderboard":"/sota/instance-segmentation-on-coco-minival","task":"Instance Segmentation","dataset":"COCO minival","model":"GCnet (ResNet-50-FPN, GRoIE)","rank_in_archive_order":84,"of":93,"metrics":{"AP50":"59.3","AP75":"39.8","APL":"51.2","APM":"41","APS":"20.2","mask AP":"37.2"},"uses_additional_data":false},{"leaderboard":"/sota/instance-segmentation-on-coco-minival","task":"Instance Segmentation","dataset":"COCO minival","model":"Mask R-CNN (ResNet-50-FPN, GRoIE)","rank_in_archive_order":88,"of":93,"metrics":{"AP50":"57.1","AP75":"38.0","APL":"48.7","APM":"39","APS":"19.1","mask AP":"35.8"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-coco-minival","task":"Object Detection","dataset":"COCO minival","model":"Mask R-CNN (ResNet-50-FPN, GRoIE)","rank_in_archive_order":196,"of":220,"metrics":{"AP50":"59.9","AP75":"41.7","APL":"49.7","APM":"42.1","APS":"22.9","box AP":"38.4"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-coco-minival","task":"Object Detection","dataset":"COCO minival","model":"Faster R-CNN (ResNet-50-FPN, GRoIE)","rank_in_archive_order":203,"of":220,"metrics":{"AP50":"59.2","AP75":"40.6","APL":"47.8","APM":"41.5","APS":"22.3","box AP":"37.5"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2004.13665","atlas_url":"https://app.syntology.ai/?focus=2004.13665","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":"2004.13665"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2004.13665\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2004.13665"},"call":"get_concepts_for_paper(arxiv_id=\"2004.13665\")"}],"by_repo":[{"repo":"open-mmlab/mmdetection","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2401.02361"],"harvested_for_calls":[{"arxiv_id":"2401.02361","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2401.02361"},"call":"get_harvested_code_for_paper(arxiv_id=\"2401.02361\")"}]},{"repo":"IMPLabUniPr/mmdetection","kind":"named_in_paper","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"IMPLabUniPr/mmdetection-groie","kind":"named_in_paper","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"Gugan0905/steel-defect-detection","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","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":"a4ddbaebfe108299383a57496645c7ef41a27d221342373534196f6e22d0e880","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}