{"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/dynamic-resolution-network","title":"Dynamic Resolution Network","arxiv_id":"2106.02898","date":"2021-06-05","proceeding":"NeurIPS 2021 12","authors":["Mingjian Zhu","Kai Han","Enhua Wu","Qiulin Zhang","Ying Nie","Zhenzhong Lan","Yunhe Wang"],"abstract":"Deep convolutional neural networks (CNNs) are often of sophisticated design with numerous learnable parameters for the accuracy reason. To alleviate the expensive costs of deploying them on mobile devices, recent works have made huge efforts for excavating redundancy in pre-defined architectures. Nevertheless, the redundancy on the input resolution of modern CNNs has not been fully investigated, i.e., the resolution of input image is fixed. In this paper, we observe that the smallest resolution for accurately predicting the given image is different using the same neural network. To this end, we propose a novel dynamic-resolution network (DRNet) in which the input resolution is determined dynamically based on each input sample. Wherein, a resolution predictor with negligible computational costs is explored and optimized jointly with the desired network. Specifically, the predictor learns the smallest resolution that can retain and even exceed the original recognition accuracy for each image. During the inference, each input image will be resized to its predicted resolution for minimizing the overall computation burden. We then conduct extensive experiments on several benchmark networks and datasets. The results show that our DRNet can be embedded in any off-the-shelf network architecture to obtain a considerable reduction in computational complexity. For instance, DR-ResNet-50 achieves similar performance with an about 34% computation reduction, while gaining 1.4% accuracy increase with 10% computation reduction compared to the original ResNet-50 on ImageNet.","url_abs":"https://arxiv.org/abs/2106.02898v3","url_pdf":"https://arxiv.org/pdf/2106.02898v3.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":"dynamic-resolution-network","repo_url":"https://github.com/LKLQQ/DRNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"mindspore","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"dynamic-resolution-network","repo_url":"https://github.com/robin-ex/DRNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"mindspore","reach":{"status":"ok"}},{"paper_slug":"dynamic-resolution-network","repo_url":"https://github.com/mindspore-ai/models/tree/master/research/cv/DDRNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2106.02898","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.02898"}},"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/robin-ex/DRNet","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mindspore-ai/models/tree/master/research/cv/DDRNet","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/LKLQQ/DRNet","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_draft_wrong":1,"unverified":4},"by_repo_kind":{"listed":{"samples":5,"ran":1,"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":"b9e24c3e3e0e88a7","entry":"merge","repo":"LKLQQ/DRNet","repo_kind":"listed","path":"src/model_utils/config.py","file_url":"https://github.com/LKLQQ/DRNet/blob/HEAD/src/model_utils/config.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":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b9e24c3e3e0e88a7"}},{"code_sha256_prefix":"82c48515ddda4614","entry":"calculate_gain","repo":"LKLQQ/DRNet","repo_kind":"listed","path":"src/classifier.py","file_url":"https://github.com/LKLQQ/DRNet/blob/HEAD/src/classifier.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"82c48515ddda4614"}},{"code_sha256_prefix":"f0a6216664197738","entry":"kaiming_normal","repo":"LKLQQ/DRNet","repo_kind":"listed","path":"src/classifier.py","file_url":"https://github.com/LKLQQ/DRNet/blob/HEAD/src/classifier.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f0a6216664197738"}},{"code_sha256_prefix":"f0b391cf1db2ea47","entry":"parse_cli_to_yaml","repo":"LKLQQ/DRNet","repo_kind":"listed","path":"src/model_utils/config.py","file_url":"https://github.com/LKLQQ/DRNet/blob/HEAD/src/model_utils/config.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f0b391cf1db2ea47"}},{"code_sha256_prefix":"aacd1cc8cc1ff2e4","entry":"parse_yaml","repo":"LKLQQ/DRNet","repo_kind":"listed","path":"src/model_utils/config.py","file_url":"https://github.com/LKLQQ/DRNet/blob/HEAD/src/model_utils/config.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"aacd1cc8cc1ff2e4"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}