{"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/revisiting-image-pyramid-structure-for-high","title":"Revisiting Image Pyramid Structure for High Resolution Salient Object Detection","arxiv_id":"2209.09475","date":"2022-09-20","proceeding":null,"authors":["Taehun Kim","Kunhee Kim","Joonyeong Lee","Dongmin Cha","Jiho Lee","Daijin Kim"],"abstract":"Salient object detection (SOD) has been in the spotlight recently, yet has been studied less for high-resolution (HR) images. Unfortunately, HR images and their pixel-level annotations are certainly more labor-intensive and time-consuming compared to low-resolution (LR) images and annotations. Therefore, we propose an image pyramid-based SOD framework, Inverse Saliency Pyramid Reconstruction Network (InSPyReNet), for HR prediction without any of HR datasets. We design InSPyReNet to produce a strict image pyramid structure of saliency map, which enables to ensemble multiple results with pyramid-based image blending. For HR prediction, we design a pyramid blending method which synthesizes two different image pyramids from a pair of LR and HR scale from the same image to overcome effective receptive field (ERF) discrepancy. Our extensive evaluations on public LR and HR SOD benchmarks demonstrate that InSPyReNet surpasses the State-of-the-Art (SotA) methods on various SOD metrics and boundary accuracy.","url_abs":"https://arxiv.org/abs/2209.09475v3","url_pdf":"https://arxiv.org/pdf/2209.09475v3.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":"revisiting-image-pyramid-structure-for-high","repo_url":"https://github.com/plemeri/inspyrenet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"revisiting-image-pyramid-structure-for-high","repo_url":"https://github.com/plemeri/transparent-background","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"revisiting-image-pyramid-structure-for-high","repo_url":"https://github.com/john-mnz/ComfyUI-Inspyrenet-Rembg","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"dichotomous-image-segmentation","task_name":"Dichotomous Image Segmentation"},{"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":"high","task_name":"Vocal Bursts Intensity Prediction"}],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"axial-attention","method_name":"Axial Attention"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"laplacian-pyramid","method_name":"Laplacian Pyramid"},{"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":"softmax","method_name":"Softmax"},{"method_slug":"vision-transformer","method_name":"Vision Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/dichotomous-image-segmentation-on-dis-te1","task":"Dichotomous Image Segmentation","dataset":"DIS-TE1","model":"InSPyReNet (HR scale)","rank_in_archive_order":4,"of":22,"metrics":{"E-measure":"0.894","HCE":"110","MAE":"0.045","S-Measure":"0.873","max F-Measure":"0.845","weighted F-measure":"0.788"},"uses_additional_data":false},{"leaderboard":"/sota/dichotomous-image-segmentation-on-dis-te1","task":"Dichotomous Image Segmentation","dataset":"DIS-TE1","model":"InSPyReNet","rank_in_archive_order":5,"of":22,"metrics":{"HCE":"148","S-Measure":"0.862","max F-Measure":"0.834"},"uses_additional_data":false},{"leaderboard":"/sota/dichotomous-image-segmentation-on-dis-te2","task":"Dichotomous Image Segmentation","dataset":"DIS-TE2","model":"InSPyReNet (HR scale)","rank_in_archive_order":4,"of":22,"metrics":{"HCE":"255","S-Measure":"0.905","max F-Measure":"0.894"},"uses_additional_data":false},{"leaderboard":"/sota/dichotomous-image-segmentation-on-dis-te2","task":"Dichotomous Image Segmentation","dataset":"DIS-TE2","model":"InSPyReNet","rank_in_archive_order":5,"of":22,"metrics":{"E-measure":"0.925","HCE":"316","MAE":"0.038","S-Measure":"0.893","max F-Measure":"0.881","weighted F-measure":"0.834"},"uses_additional_data":false},{"leaderboard":"/sota/dichotomous-image-segmentation-on-dis-te3","task":"Dichotomous Image Segmentation","dataset":"DIS-TE3","model":"InSPyReNet (HR scale)","rank_in_archive_order":4,"of":22,"metrics":{"E-measure":"0.938","HCE":"522","MAE":"0.034","S-Measure":"0.918","max F-Measure":"0.919","weighted F-measure":"0.871"},"uses_additional_data":false},{"leaderboard":"/sota/dichotomous-image-segmentation-on-dis-te3","task":"Dichotomous Image Segmentation","dataset":"DIS-TE3","model":"InSPyReNet","rank_in_archive_order":5,"of":22,"metrics":{"E-measure":"0.938","HCE":"582","MAE":"0.038","S-Measure":"0.902","max F-Measure":"0.904","weighted F-measure":"0.856"},"uses_additional_data":false},{"leaderboard":"/sota/dichotomous-image-segmentation-on-dis-te4","task":"Dichotomous Image Segmentation","dataset":"DIS-TE4","model":"InSPyReNet (HR scale)","rank_in_archive_order":3,"of":22,"metrics":{"E-measure":"0.926","HCE":"2336","MAE":"0.042","S-Measure":"0.905","max F-Measure":"0.905","weighted F-measure":"0.848"},"uses_additional_data":false},{"leaderboard":"/sota/dichotomous-image-segmentation-on-dis-te4","task":"Dichotomous Image Segmentation","dataset":"DIS-TE4","model":"InSPyReNet","rank_in_archive_order":5,"of":22,"metrics":{"E-measure":"0.926","HCE":"2243","MAE":"0.046","S-Measure":"0.891","max F-Measure":"0.892","weighted F-measure":"0.840"},"uses_additional_data":false},{"leaderboard":"/sota/dichotomous-image-segmentation-on-dis-vd","task":"Dichotomous Image Segmentation","dataset":"DIS-VD","model":"InSPyReNet (HR scale)","rank_in_archive_order":6,"of":24,"metrics":{"HCE":"904","S-Measure":"0.900","max F-Measure":"0.889"},"uses_additional_data":false},{"leaderboard":"/sota/dichotomous-image-segmentation-on-dis-vd","task":"Dichotomous Image Segmentation","dataset":"DIS-VD","model":"InSPyReNet","rank_in_archive_order":7,"of":24,"metrics":{"E-measure":"0.921","HCE":"905","MAE":"0.043","S-Measure":"0.887","max F-Measure":"0.876","weighted F-measure":"0.826"},"uses_additional_data":false},{"leaderboard":"/sota/rgb-salient-object-detection-on-davis-s","task":"RGB Salient Object Detection","dataset":"DAVIS-S","model":"InSPyReNet (DUTS, HRSOD)","rank_in_archive_order":5,"of":12,"metrics":{"F-measure":"0.976","S-measure":"0.972","mBA":"0.770"},"uses_additional_data":true},{"leaderboard":"/sota/rgb-salient-object-detection-on-davis-s","task":"RGB Salient Object Detection","dataset":"DAVIS-S","model":"InSPyReNet","rank_in_archive_order":7,"of":12,"metrics":{"F-measure":"0.959","MAE":"0.009","S-measure":"0.962","mBA":"0.743"},"uses_additional_data":false},{"leaderboard":"/sota/salient-object-detection-on-dut-omron","task":"RGB Salient Object Detection","dataset":"DUT-OMRON","model":"InSPyReNet","rank_in_archive_order":3,"of":18,"metrics":{"F-measure":"0.832","MAE":"0.045","S-Measure":"0.875"},"uses_additional_data":false},{"leaderboard":"/sota/salient-object-detection-on-duts-te","task":"RGB Salient Object Detection","dataset":"DUTS-TE","model":"InSPyReNet","rank_in_archive_order":6,"of":31,"metrics":{"MAE":"0.024","S-Measure":"0.931","max F-measure":"0.892"},"uses_additional_data":false},{"leaderboard":"/sota/salient-object-detection-on-ecssd","task":"RGB Salient Object Detection","dataset":"ECSSD","model":"InSPyReNet","rank_in_archive_order":2,"of":14,"metrics":{"F-measure":"0.96","MAE":"0.031","S-Measure":"0.936"},"uses_additional_data":false},{"leaderboard":"/sota/salient-object-detection-on-hku-is","task":"RGB Salient Object Detection","dataset":"HKU-IS","model":"InSPyReNet","rank_in_archive_order":1,"of":14,"metrics":{"F-measure":"0.955","MAE":"0.028","S-Measure":"0.944"},"uses_additional_data":false},{"leaderboard":"/sota/rgb-salient-object-detection-on-hrsod","task":"RGB Salient Object Detection","dataset":"HRSOD","model":"InSPyReNet (DUTS, HRSOD)","rank_in_archive_order":4,"of":14,"metrics":{"MAE":"0.014","S-Measure":"0.960","mBA":"0.766","max F-Measure":"0.957"},"uses_additional_data":true},{"leaderboard":"/sota/rgb-salient-object-detection-on-hrsod","task":"RGB Salient Object Detection","dataset":"HRSOD","model":"InSPyReNet (HRSOD, UHRSD)","rank_in_archive_order":7,"of":14,"metrics":{"MAE":"0.018","S-Measure":"0.956","mBA":"0.771","max F-Measure":"0.956"},"uses_additional_data":true},{"leaderboard":"/sota/rgb-salient-object-detection-on-hrsod","task":"RGB Salient Object Detection","dataset":"HRSOD","model":"InSPyReNet","rank_in_archive_order":9,"of":14,"metrics":{"MAE":"0.016","S-Measure":"0.952","mBA":"0.738","max F-Measure":"0.949"},"uses_additional_data":false},{"leaderboard":"/sota/salient-object-detection-on-pascal-s","task":"RGB Salient Object Detection","dataset":"PASCAL-S","model":"InSPyReNet","rank_in_archive_order":2,"of":13,"metrics":{"F-measure":"0.893","MAE":"0.048","S-Measure":"0.893"},"uses_additional_data":false},{"leaderboard":"/sota/rgb-salient-object-detection-on-uhrsd","task":"RGB Salient Object Detection","dataset":"UHRSD","model":"InSPyReNet (HRSOD, UHRSD)","rank_in_archive_order":3,"of":12,"metrics":{"MAE":"0.020","S-Measure":"0.953","mBA":"0.812","max F-Measure":"0.957"},"uses_additional_data":true},{"leaderboard":"/sota/rgb-salient-object-detection-on-uhrsd","task":"RGB Salient Object Detection","dataset":"UHRSD","model":"InSPyReNet (DUTS, HRSOD)","rank_in_archive_order":7,"of":12,"metrics":{"S-Measure":"0.936","mBA":"0.785"},"uses_additional_data":true},{"leaderboard":"/sota/rgb-salient-object-detection-on-uhrsd","task":"RGB Salient Object Detection","dataset":"UHRSD","model":"InSPyReNet","rank_in_archive_order":9,"of":12,"metrics":{"MAE":"0.029","S-Measure":"0.932","mBA":"0.741","max F-Measure":"0.938"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2209.09475","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.09475"}},"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/plemeri/transparent-background","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/plemeri/inspyrenet","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/john-mnz/ComfyUI-Inspyrenet-Rembg","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_fixture":1,"ran_draft_wrong":2,"unverified":8},"by_repo_kind":{"official":{"samples":9,"ran":3,"repositories":2},"listed":{"samples":2,"ran":0,"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":"144d10b49baeb8a6","entry":"window_partition","repo":"plemeri/transparent-background","repo_kind":"official","path":"transparent_background/backbones/SwinTransformer.py","file_url":"https://github.com/plemeri/transparent-background/blob/HEAD/transparent_background/backbones/SwinTransformer.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":2,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"144d10b49baeb8a6"}},{"code_sha256_prefix":"1eadaf408af1168c","entry":"get_format","repo":"plemeri/inspyrenet","repo_kind":"official","path":"run/Inference.py","file_url":"https://github.com/plemeri/inspyrenet/blob/HEAD/run/Inference.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1eadaf408af1168c"}},{"code_sha256_prefix":"61bf152e6a42a184","entry":"window_reverse","repo":"plemeri/transparent-background","repo_kind":"official","path":"transparent_background/backbones/SwinTransformer.py","file_url":"https://github.com/plemeri/transparent-background/blob/HEAD/transparent_background/backbones/SwinTransformer.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"61bf152e6a42a184"}},{"code_sha256_prefix":"514e23fec6c636e1","entry":"SwinT","repo":"plemeri/transparent-background","repo_kind":"official","path":"transparent_background/backbones/SwinTransformer.py","file_url":"https://github.com/plemeri/transparent-background/blob/HEAD/transparent_background/backbones/SwinTransformer.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"514e23fec6c636e1"}},{"code_sha256_prefix":"ad87b881b49f3704","entry":"get_format","repo":"plemeri/transparent-background","repo_kind":"official","path":"transparent_background/utils.py","file_url":"https://github.com/plemeri/transparent-background/blob/HEAD/transparent_background/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ad87b881b49f3704"}},{"code_sha256_prefix":"614f3ec915d613e1","entry":"is_float","repo":"plemeri/transparent-background","repo_kind":"official","path":"transparent_background/gui.py","file_url":"https://github.com/plemeri/transparent-background/blob/HEAD/transparent_background/gui.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"614f3ec915d613e1"}},{"code_sha256_prefix":"e8b1d6c6640e3379","entry":"load_config","repo":"plemeri/transparent-background","repo_kind":"official","path":"transparent_background/utils.py","file_url":"https://github.com/plemeri/transparent-background/blob/HEAD/transparent_background/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e8b1d6c6640e3379"}},{"code_sha256_prefix":"ddd740751dbbd55b","entry":"pil2tensor","repo":"john-mnz/ComfyUI-Inspyrenet-Rembg","repo_kind":"listed","path":"Inspyrenet_Rembg.py","file_url":"https://github.com/john-mnz/ComfyUI-Inspyrenet-Rembg/blob/HEAD/Inspyrenet_Rembg.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ddd740751dbbd55b"}},{"code_sha256_prefix":"b0d5bca317b4e704","entry":"sort","repo":"plemeri/transparent-background","repo_kind":"official","path":"transparent_background/utils.py","file_url":"https://github.com/plemeri/transparent-background/blob/HEAD/transparent_background/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b0d5bca317b4e704"}},{"code_sha256_prefix":"ee8ddf2c7607bd81","entry":"tensor2pil","repo":"john-mnz/ComfyUI-Inspyrenet-Rembg","repo_kind":"listed","path":"Inspyrenet_Rembg.py","file_url":"https://github.com/john-mnz/ComfyUI-Inspyrenet-Rembg/blob/HEAD/Inspyrenet_Rembg.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ee8ddf2c7607bd81"}},{"code_sha256_prefix":"32148520ac8a75d3","entry":"to_base64","repo":"plemeri/transparent-background","repo_kind":"official","path":"transparent_background/Remover.py","file_url":"https://github.com/plemeri/transparent-background/blob/HEAD/transparent_background/Remover.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"32148520ac8a75d3"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}