{"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/f3net-fusion-feedback-and-focus-for-salient","title":"F3Net: Fusion, Feedback and Focus for Salient Object Detection","arxiv_id":"1911.11445","date":"2019-11-26","proceeding":null,"authors":["Jun Wei","Shuhui Wang","Qingming Huang"],"abstract":"Most of existing salient object detection models have achieved great progress by aggregating multi-level features extracted from convolutional neural networks. However, because of the different receptive fields of different convolutional layers, there exists big differences between features generated by these layers. Common feature fusion strategies (addition or concatenation) ignore these differences and may cause suboptimal solutions. In this paper, we propose the F3Net to solve above problem, which mainly consists of cross feature module (CFM) and cascaded feedback decoder (CFD) trained by minimizing a new pixel position aware loss (PPA). Specifically, CFM aims to selectively aggregate multi-level features. Different from addition and concatenation, CFM adaptively selects complementary components from input features before fusion, which can effectively avoid introducing too much redundant information that may destroy the original features. Besides, CFD adopts a multi-stage feedback mechanism, where features closed to supervision will be introduced to the output of previous layers to supplement them and eliminate the differences between features. These refined features will go through multiple similar iterations before generating the final saliency maps. Furthermore, different from binary cross entropy, the proposed PPA loss doesn't treat pixels equally, which can synthesize the local structure information of a pixel to guide the network to focus more on local details. Hard pixels from boundaries or error-prone parts will be given more attention to emphasize their importance. F3Net is able to segment salient object regions accurately and provide clear local details. Comprehensive experiments on five benchmark datasets demonstrate that F3Net outperforms state-of-the-art approaches on six evaluation metrics.","url_abs":"https://arxiv.org/abs/1911.11445v1","url_pdf":"https://arxiv.org/pdf/1911.11445v1.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":"f3net-fusion-feedback-and-focus-for-salient","repo_url":"https://github.com/weijun88/F3Net","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"f3net-fusion-feedback-and-focus-for-salient","repo_url":"https://github.com/PanoAsh/ASOD60K","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"f3net-fusion-feedback-and-focus-for-salient","repo_url":"https://github.com/PanoAsh/SHD360","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"f3net-fusion-feedback-and-focus-for-salient","repo_url":"https://github.com/StamatisKourkoutas/Brain_Tumor_Segmentation_US_Images","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"camouflaged-object-segmentation","task_name":"Camouflaged Object Segmentation"},{"task_slug":"dichotomous-image-segmentation","task_name":"Dichotomous Image Segmentation"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"salient-object-detection","task_name":"RGB Salient Object Detection"},{"task_slug":"salient-object-detection-1","task_name":"Salient Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/camouflaged-object-segmentation-on-pcod-1200","task":"Camouflaged Object Segmentation","dataset":"PCOD_1200","model":"F3Net","rank_in_archive_order":8,"of":16,"metrics":{"S-Measure":"0.885"},"uses_additional_data":false},{"leaderboard":"/sota/dichotomous-image-segmentation-on-dis-te1","task":"Dichotomous Image Segmentation","dataset":"DIS-TE1","model":"F3Net","rank_in_archive_order":16,"of":22,"metrics":{"E-measure":"0.783","HCE":"244","MAE":"0.095","S-Measure":"0.721","max F-Measure":"0.640","weighted F-measure":"0.549"},"uses_additional_data":false},{"leaderboard":"/sota/dichotomous-image-segmentation-on-dis-te2","task":"Dichotomous Image Segmentation","dataset":"DIS-TE2","model":"F3Net","rank_in_archive_order":16,"of":22,"metrics":{"E-measure":"0.820","HCE":"542","MAE":"0.097","S-Measure":"0.755","max F-Measure":"0.712","weighted F-measure":"0.620"},"uses_additional_data":false},{"leaderboard":"/sota/dichotomous-image-segmentation-on-dis-te3","task":"Dichotomous Image Segmentation","dataset":"DIS-TE3","model":"F3Net","rank_in_archive_order":17,"of":22,"metrics":{"E-measure":"0.848","HCE":"1059","MAE":"0.092","S-Measure":"0.773","max F-Measure":"0.743","weighted F-measure":"0.656"},"uses_additional_data":false},{"leaderboard":"/sota/dichotomous-image-segmentation-on-dis-te4","task":"Dichotomous Image Segmentation","dataset":"DIS-TE4","model":"F3Net","rank_in_archive_order":18,"of":22,"metrics":{"E-measure":"0.825","HCE":"3760","MAE":"0.107","S-Measure":"0.752","max F-Measure":"0.721","weighted F-measure":"0.633"},"uses_additional_data":false},{"leaderboard":"/sota/dichotomous-image-segmentation-on-dis-vd","task":"Dichotomous Image Segmentation","dataset":"DIS-VD","model":"F3Net","rank_in_archive_order":19,"of":24,"metrics":{"E-measure":"0.800","HCE":"1567","MAE":"0.107","S-Measure":"0.733","max F-Measure":"0.685","weighted F-measure":"0.595"},"uses_additional_data":false},{"leaderboard":"/sota/salient-object-detection-on-dut-omron-2","task":"Salient Object Detection","dataset":"DUT-OMRON","model":"F3Net","rank_in_archive_order":7,"of":8,"metrics":{"E-measure":"0.869","MAE":"0.052","S-measure":"0.838","max_F1":"0.813"},"uses_additional_data":false},{"leaderboard":"/sota/salient-object-detection-on-duts-te-1","task":"Salient Object Detection","dataset":"DUTS-TE","model":"F3Net","rank_in_archive_order":7,"of":8,"metrics":{"E-measure":"0.901","MAE":"0.035","Smeasure":"0.888","max_F1":"0.891"},"uses_additional_data":false},{"leaderboard":"/sota/salient-object-detection-on-ecssd-1","task":"Salient Object Detection","dataset":"ECSSD","model":"F3Net","rank_in_archive_order":7,"of":10,"metrics":{"E-measure":"0.927","MAE":"0.033","S-measure":"0.924","max_F1":"0.945"},"uses_additional_data":false},{"leaderboard":"/sota/salient-object-detection-on-hku-is-1","task":"Salient Object Detection","dataset":"HKU-IS","model":"F3Net","rank_in_archive_order":8,"of":9,"metrics":{"E-measure":"0.952","MAE":"0.028","S-measure":"0.917","max_F1":"0.936"},"uses_additional_data":false},{"leaderboard":"/sota/salient-object-detection-on-pascal-s-1","task":"Salient Object Detection","dataset":"PASCAL-S","model":"F3Net","rank_in_archive_order":8,"of":10,"metrics":{"E-measure":"0.858","MAE":"0.061","S-measure":"0.854","max_F1":"0.871"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1911.11445","atlas_url":"https://app.syntology.ai/?focus=1911.11445","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":"1911.11445"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1911.11445\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1911.11445"},"call":"get_concepts_for_paper(arxiv_id=\"1911.11445\")"}],"by_repo":[{"repo":"weijun88/F3Net","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"PanoAsh/ASOD60K","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"PanoAsh/SHD360","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"StamatisKourkoutas/Brain_Tumor_Segmentation_US_Images","kind":"listed","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":"ed37ae7caaee64763bbe55800aaf207be958ed62a5ed8cc11d8dc045549610bf","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}