{"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/transalnet-visual-saliency-prediction-using","title":"TranSalNet: Towards perceptually relevant visual saliency prediction","arxiv_id":"2110.03593","date":"2021-10-07","proceeding":null,"authors":["Jianxun Lou","Hanhe Lin","David Marshall","Dietmar Saupe","Hantao Liu"],"abstract":"Visual saliency prediction using transformers - Convolutional neural networks (CNNs) have significantly advanced computational modelling for saliency prediction. However, accurately simulating the mechanisms of visual attention in the human cortex remains an academic challenge. It is critical to integrate properties of human vision into the design of CNN architectures, leading to perceptually more relevant saliency prediction. Due to the inherent inductive biases of CNN architectures, there is a lack of sufficient long-range contextual encoding capacity. This hinders CNN-based saliency models from capturing properties that emulate viewing behaviour of humans. Transformers have shown great potential in encoding long-range information by leveraging the self-attention mechanism. In this paper, we propose a novel saliency model that integrates transformer components to CNNs to capture the long-range contextual visual information. Experimental results show that the transformers provide added value to saliency prediction, enhancing its perceptual relevance in the performance. Our proposed saliency model using transformers has achieved superior results on public benchmarks and competitions for saliency prediction models. The source code of our proposed saliency model TranSalNet is available at: https://github.com/LJOVO/TranSalNet","url_abs":"https://arxiv.org/abs/2110.03593v3","url_pdf":"https://arxiv.org/pdf/2110.03593v3.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":"transalnet-visual-saliency-prediction-using","repo_url":"https://github.com/ljovo/transalnet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"prediction","task_name":"Prediction"},{"task_slug":"saliency-prediction","task_name":"Saliency Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/saliency-prediction-on-mit300","task":"Saliency Prediction","dataset":"MIT300","model":"TranSalNet","rank_in_archive_order":2,"of":2,"metrics":{"AUC-Judd":"0.8734","CC":"0.807","KLD":"1.0141","NSS":"2.4134","SIM":"0.6895","sAUC":"0.7467"},"uses_additional_data":false},{"leaderboard":"/sota/saliency-prediction-on-saleci","task":"Saliency Prediction","dataset":"SALECI","model":"Transalnet","rank_in_archive_order":5,"of":5,"metrics":{"KL":"0.873"},"uses_additional_data":false},{"leaderboard":"/sota/saliency-prediction-on-salicon","task":"Saliency Prediction","dataset":"SALICON","model":"TranSalNet","rank_in_archive_order":5,"of":5,"metrics":{"AUC":"0.868","CC":"0.907","KLD":"0.373","NSS":"2.014","SIM":"0.803","sAUC":"0.747"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2110.03593","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.03593"}},"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/ljovo/transalnet","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":2,"ran":4,"unverified":5},"by_repo_kind":{"official":{"samples":11,"ran":6,"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":"2a80220dabcb742a","entry":"conv1x1","repo":"ljovo/transalnet","repo_kind":"official","path":"utils/resnet.py","file_url":"https://github.com/ljovo/transalnet/blob/HEAD/utils/resnet.py","link_basis":"harvester_set","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":"2a80220dabcb742a"}},{"code_sha256_prefix":"600ff2c45e0de056","entry":"conv3x3","repo":"ljovo/transalnet","repo_kind":"official","path":"utils/resnet.py","file_url":"https://github.com/ljovo/transalnet/blob/HEAD/utils/resnet.py","link_basis":"harvester_set","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":"600ff2c45e0de056"}},{"code_sha256_prefix":"774d792a6525842a","entry":"loss_CC","repo":"ljovo/transalnet","repo_kind":"official","path":"utils/loss_function.py","file_url":"https://github.com/ljovo/transalnet/blob/HEAD/utils/loss_function.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"774d792a6525842a"}},{"code_sha256_prefix":"e9183c75893d49f0","entry":"loss_KLdiv","repo":"ljovo/transalnet","repo_kind":"official","path":"utils/loss_function.py","file_url":"https://github.com/ljovo/transalnet/blob/HEAD/utils/loss_function.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e9183c75893d49f0"}},{"code_sha256_prefix":"9596d79dd2070fff","entry":"loss_similarity","repo":"ljovo/transalnet","repo_kind":"official","path":"utils/loss_function.py","file_url":"https://github.com/ljovo/transalnet/blob/HEAD/utils/loss_function.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9596d79dd2070fff"}},{"code_sha256_prefix":"ebfa76e7f72447ce","entry":"postprocess_img","repo":"ljovo/transalnet","repo_kind":"official","path":"utils/data_process.py","file_url":"https://github.com/ljovo/transalnet/blob/HEAD/utils/data_process.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":"ebfa76e7f72447ce"}},{"code_sha256_prefix":"8fbb6e8ffe5752f5","entry":"densenet121","repo":"ljovo/transalnet","repo_kind":"official","path":"utils/densenet.py","file_url":"https://github.com/ljovo/transalnet/blob/HEAD/utils/densenet.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":"8fbb6e8ffe5752f5"}},{"code_sha256_prefix":"84c7817fbe252d76","entry":"densenet161","repo":"ljovo/transalnet","repo_kind":"official","path":"utils/densenet.py","file_url":"https://github.com/ljovo/transalnet/blob/HEAD/utils/densenet.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":"84c7817fbe252d76"}},{"code_sha256_prefix":"d14cf2b8e9e2a0ef","entry":"densenet169","repo":"ljovo/transalnet","repo_kind":"official","path":"utils/densenet.py","file_url":"https://github.com/ljovo/transalnet/blob/HEAD/utils/densenet.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":"d14cf2b8e9e2a0ef"}},{"code_sha256_prefix":"ed2103d493d0a213","entry":"preprocess_img","repo":"ljovo/transalnet","repo_kind":"official","path":"utils/data_process.py","file_url":"https://github.com/ljovo/transalnet/blob/HEAD/utils/data_process.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":"ed2103d493d0a213"}},{"code_sha256_prefix":"6823079f294e25ae","entry":"resnet18","repo":"ljovo/transalnet","repo_kind":"official","path":"utils/resnet.py","file_url":"https://github.com/ljovo/transalnet/blob/HEAD/utils/resnet.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":"6823079f294e25ae"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}