{"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/spatially-adaptive-computation-time-for","title":"Spatially Adaptive Computation Time for Residual Networks","arxiv_id":"1612.02297","date":"2016-12-07","proceeding":"CVPR 2017 7","authors":["Michael Figurnov","Maxwell D. Collins","Yukun Zhu","Li Zhang","Jonathan Huang","Dmitry Vetrov","Ruslan Salakhutdinov"],"abstract":"This paper proposes a deep learning architecture based on Residual Network\nthat dynamically adjusts the number of executed layers for the regions of the\nimage. This architecture is end-to-end trainable, deterministic and\nproblem-agnostic. It is therefore applicable without any modifications to a\nwide range of computer vision problems such as image classification, object\ndetection and image segmentation. We present experimental results showing that\nthis model improves the computational efficiency of Residual Networks on the\nchallenging ImageNet classification and COCO object detection datasets.\nAdditionally, we evaluate the computation time maps on the visual saliency\ndataset cat2000 and find that they correlate surprisingly well with human eye\nfixation positions.","url_abs":"http://arxiv.org/abs/1612.02297v2","url_pdf":"http://arxiv.org/pdf/1612.02297v2.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":"spatially-adaptive-computation-time-for","repo_url":"https://github.com/mfigurnov/sact","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"computational-efficiency","task_name":"Computational Efficiency"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-segmentation","task_name":"Image Segmentation"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"image-classification","task_name":"image-classification"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1612.02297","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1612.02297"}},"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/mfigurnov/sact","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":6},"by_repo_kind":{"official":{"samples":6,"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":6,"samples":[{"code_sha256_prefix":"6dcedbfb658b2fb1","entry":"adaptive_computation_time","repo":"mfigurnov/sact","repo_kind":"official","path":"act.py","file_url":"https://github.com/mfigurnov/sact/blob/HEAD/act.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"6dcedbfb658b2fb1"}},{"code_sha256_prefix":"1d39565ada613292","entry":"adaptive_computation_time_wrapper","repo":"mfigurnov/sact","repo_kind":"official","path":"act.py","file_url":"https://github.com/mfigurnov/sact/blob/HEAD/act.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"1d39565ada613292"}},{"code_sha256_prefix":"4b998dd1f53d28b4","entry":"lrelu","repo":"mfigurnov/sact","repo_kind":"official","path":"cifar_model.py","file_url":"https://github.com/mfigurnov/sact/blob/HEAD/cifar_model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"4b998dd1f53d28b4"}},{"code_sha256_prefix":"4219e649c9a3608a","entry":"preprocessing","repo":"mfigurnov/sact","repo_kind":"official","path":"imagenet_ponder_map.py","file_url":"https://github.com/mfigurnov/sact/blob/HEAD/imagenet_ponder_map.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"4219e649c9a3608a"}},{"code_sha256_prefix":"cf4244e5237e63d9","entry":"reverse_preprocessing","repo":"mfigurnov/sact","repo_kind":"official","path":"imagenet_ponder_map.py","file_url":"https://github.com/mfigurnov/sact/blob/HEAD/imagenet_ponder_map.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"cf4244e5237e63d9"}},{"code_sha256_prefix":"29d5200ad23e574a","entry":"run_units","repo":"mfigurnov/sact","repo_kind":"official","path":"act.py","file_url":"https://github.com/mfigurnov/sact/blob/HEAD/act.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"29d5200ad23e574a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}