{"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/salgan-visual-saliency-prediction-with","title":"SalGAN: Visual Saliency Prediction with Generative Adversarial Networks","arxiv_id":"1701.01081","date":"2017-01-04","proceeding":null,"authors":["Junting Pan","Cristian Canton Ferrer","Kevin McGuinness","Noel E. O'Connor","Jordi Torres","Elisa Sayrol","Xavier Giro-i-Nieto"],"abstract":"We introduce SalGAN, a deep convolutional neural network for visual saliency\nprediction trained with adversarial examples. The first stage of the network\nconsists of a generator model whose weights are learned by back-propagation\ncomputed from a binary cross entropy (BCE) loss over downsampled versions of\nthe saliency maps. The resulting prediction is processed by a discriminator\nnetwork trained to solve a binary classification task between the saliency maps\ngenerated by the generative stage and the ground truth ones. Our experiments\nshow how adversarial training allows reaching state-of-the-art performance\nacross different metrics when combined with a widely-used loss function like\nBCE. Our results can be reproduced with the source code and trained models\navailable at https://imatge-upc.github.io/saliency-salgan-2017/.","url_abs":"http://arxiv.org/abs/1701.01081v3","url_pdf":"http://arxiv.org/pdf/1701.01081v3.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":"salgan-visual-saliency-prediction-with","repo_url":"https://github.com/imatge-upc/salgan","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"salgan-visual-saliency-prediction-with","repo_url":"https://github.com/imatge-upc/saliency-2019-SalBCE","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"salgan-visual-saliency-prediction-with","repo_url":"https://github.com/imatge-upc/saliency-salgan-2017","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"salgan-visual-saliency-prediction-with","repo_url":"https://github.com/wangxiao5791509/cmSalGAN_PyTorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"binary-classification","task_name":"Binary Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"prediction","task_name":"Prediction"},{"task_slug":"saliency-prediction","task_name":"Saliency Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1701.01081","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1701.01081"}},"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/imatge-upc/saliency-salgan-2017","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/imatge-upc/salgan","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/wangxiao5791509/cmSalGAN_PyTorch","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/imatge-upc/saliency-2019-SalBCE","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":2,"unverified":4},"by_repo_kind":{"listed":{"samples":6,"ran":2,"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":"039e9f0f0dfbfaca","entry":"match_hist","repo":"imatge-upc/saliency-2019-SalBCE","repo_kind":"listed","path":"src/evaluation/tools.py","file_url":"https://github.com/imatge-upc/saliency-2019-SalBCE/blob/HEAD/src/evaluation/tools.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"039e9f0f0dfbfaca"}},{"code_sha256_prefix":"d3d86d1943c5ac37","entry":"normalize","repo":"imatge-upc/saliency-2019-SalBCE","repo_kind":"listed","path":"src/evaluation/tools.py","file_url":"https://github.com/imatge-upc/saliency-2019-SalBCE/blob/HEAD/src/evaluation/tools.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d3d86d1943c5ac37"}},{"code_sha256_prefix":"af7c99315a3cb578","entry":"augmentData","repo":"imatge-upc/saliency-2019-SalBCE","repo_kind":"listed","path":"src/dataloader/datasetDHF1K.py","file_url":"https://github.com/imatge-upc/saliency-2019-SalBCE/blob/HEAD/src/dataloader/datasetDHF1K.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":"af7c99315a3cb578"}},{"code_sha256_prefix":"59586ad0baafd71a","entry":"imageProcessing","repo":"imatge-upc/saliency-2019-SalBCE","repo_kind":"listed","path":"src/dataloader/datasetSALICON.py","file_url":"https://github.com/imatge-upc/saliency-2019-SalBCE/blob/HEAD/src/dataloader/datasetSALICON.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":"59586ad0baafd71a"}},{"code_sha256_prefix":"36e1d7722f053ab7","entry":"imageProcessing","repo":"imatge-upc/saliency-2019-SalBCE","repo_kind":"listed","path":"src/dataloader/datasetSALICON_adv.py","file_url":"https://github.com/imatge-upc/saliency-2019-SalBCE/blob/HEAD/src/dataloader/datasetSALICON_adv.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":"36e1d7722f053ab7"}},{"code_sha256_prefix":"459f8d7969d62144","entry":"img_name","repo":"imatge-upc/saliency-2019-SalBCE","repo_kind":"listed","path":"src/dataloader/datasetDHF1K.py","file_url":"https://github.com/imatge-upc/saliency-2019-SalBCE/blob/HEAD/src/dataloader/datasetDHF1K.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":"459f8d7969d62144"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}