{"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/tidying-deep-saliency-prediction","title":"Tidying Deep Saliency Prediction Architectures","arxiv_id":"2003.04942","date":"2020-03-10","proceeding":null,"authors":["Navyasri Reddy","Samyak Jain","Pradeep Yarlagadda","Vineet Gandhi"],"abstract":"Learning computational models for visual attention (saliency estimation) is an effort to inch machines/robots closer to human visual cognitive abilities. Data-driven efforts have dominated the landscape since the introduction of deep neural network architectures. In deep learning research, the choices in architecture design are often empirical and frequently lead to more complex models than necessary. The complexity, in turn, hinders the application requirements. In this paper, we identify four key components of saliency models, i.e., input features, multi-level integration, readout architecture, and loss functions. We review the existing state of the art models on these four components and propose novel and simpler alternatives. As a result, we propose two novel end-to-end architectures called SimpleNet and MDNSal, which are neater, minimal, more interpretable and achieve state of the art performance on public saliency benchmarks. SimpleNet is an optimized encoder-decoder architecture and brings notable performance gains on the SALICON dataset (the largest saliency benchmark). MDNSal is a parametric model that directly predicts parameters of a GMM distribution and is aimed to bring more interpretability to the prediction maps. The proposed saliency models can be inferred at 25fps, making them suitable for real-time applications. Code and pre-trained models are available at https://github.com/samyak0210/saliency.","url_abs":"https://arxiv.org/abs/2003.04942v1","url_pdf":"https://arxiv.org/pdf/2003.04942v1.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":"tidying-deep-saliency-prediction","repo_url":"https://github.com/samyak0210/saliency","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"prediction","task_name":"Prediction"},{"task_slug":"saliency-prediction","task_name":"Saliency Prediction"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"interpretability","method_name":"Interpretability"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"simplenet","method_name":"SimpleNet"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2003.04942","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.04942"}},"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/samyak0210/saliency","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":5},"by_repo_kind":{"official":{"samples":5,"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":"db8695ed1227ee7a","entry":"blur","repo":"samyak0210/saliency","repo_kind":"official","path":"SimpleNet/utils.py","file_url":"https://github.com/samyak0210/saliency/blob/HEAD/SimpleNet/utils.py","link_basis":"first_harvest_node","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":"db8695ed1227ee7a"}},{"code_sha256_prefix":"e09e9ba79db12754","entry":"im2heat","repo":"samyak0210/saliency","repo_kind":"official","path":"SimpleNet/utils.py","file_url":"https://github.com/samyak0210/saliency/blob/HEAD/SimpleNet/utils.py","link_basis":"first_harvest_node","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":"e09e9ba79db12754"}},{"code_sha256_prefix":"3004c401c9721c76","entry":"kldiv","repo":"samyak0210/saliency","repo_kind":"official","path":"SimpleNet/loss.py","file_url":"https://github.com/samyak0210/saliency/blob/HEAD/SimpleNet/loss.py","link_basis":"first_harvest_node","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":"3004c401c9721c76"}},{"code_sha256_prefix":"b4b8b9db7d61bd9c","entry":"normalize_map","repo":"samyak0210/saliency","repo_kind":"official","path":"SimpleNet/loss.py","file_url":"https://github.com/samyak0210/saliency/blob/HEAD/SimpleNet/loss.py","link_basis":"first_harvest_node","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":"b4b8b9db7d61bd9c"}},{"code_sha256_prefix":"ebb55898e1043956","entry":"similarity","repo":"samyak0210/saliency","repo_kind":"official","path":"SimpleNet/loss.py","file_url":"https://github.com/samyak0210/saliency/blob/HEAD/SimpleNet/loss.py","link_basis":"first_harvest_node","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":"ebb55898e1043956"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}