{"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/learning-to-zoom-a-saliency-based-sampling","title":"Learning to Zoom: a Saliency-Based Sampling Layer for Neural Networks","arxiv_id":"1809.03355","date":"2018-09-10","proceeding":"ECCV 2018 9","authors":["Adrià Recasens","Petr Kellnhofer","Simon Stent","Wojciech Matusik","Antonio Torralba"],"abstract":"We introduce a saliency-based distortion layer for convolutional neural\nnetworks that helps to improve the spatial sampling of input data for a given\ntask. Our differentiable layer can be added as a preprocessing block to\nexisting task networks and trained altogether in an end-to-end fashion. The\neffect of the layer is to efficiently estimate how to sample from the original\ndata in order to boost task performance. For example, for an image\nclassification task in which the original data might range in size up to\nseveral megapixels, but where the desired input images to the task network are\nmuch smaller, our layer learns how best to sample from the underlying high\nresolution data in a manner which preserves task-relevant information better\nthan uniform downsampling. This has the effect of creating distorted,\ncaricature-like intermediate images, in which idiosyncratic elements of the\nimage that improve task performance are zoomed and exaggerated. Unlike\nalternative approaches such as spatial transformer networks, our proposed layer\nis inspired by image saliency, computed efficiently from uniformly downsampled\ndata, and degrades gracefully to a uniform sampling strategy under uncertainty.\nWe apply our layer to improve existing networks for the tasks of human gaze\nestimation and fine-grained object classification. Code for our method is\navailable in: http://github.com/recasens/Saliency-Sampler","url_abs":"http://arxiv.org/abs/1809.03355v1","url_pdf":"http://arxiv.org/pdf/1809.03355v1.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":"learning-to-zoom-a-saliency-based-sampling","repo_url":"https://github.com/recasens/Saliency-Sampler","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"caricature","task_name":"Caricature"},{"task_slug":"gaze-estimation","task_name":"Gaze Estimation"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"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":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"spatial-transformer","method_name":"Spatial Transformer"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1809.03355","atlas_url":"https://app.syntology.ai/?focus=1809.03355","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":"1809.03355"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1809.03355\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1809.03355"},"call":"get_concepts_for_paper(arxiv_id=\"1809.03355\")"}],"by_repo":[{"repo":"recasens/Saliency-Sampler","kind":"official","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":"a1e71e2d334828a87337884e2871099db9bd635b95f4bc3b198125340f534df2","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}