{"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/detnas-neural-architecture-search-on-object","title":"DetNAS: Backbone Search for Object Detection","arxiv_id":"1903.10979","date":"2019-03-26","proceeding":"NeurIPS 2019 12","authors":["Yukang Chen","Tong Yang","Xiangyu Zhang","Gaofeng Meng","Xinyu Xiao","Jian Sun"],"abstract":"Object detectors are usually equipped with backbone networks designed for image classification. It might be sub-optimal because of the gap between the tasks of image classification and object detection. In this work, we present DetNAS to use Neural Architecture Search (NAS) for the design of better backbones for object detection. It is non-trivial because detection training typically needs ImageNet pre-training while NAS systems require accuracies on the target detection task as supervisory signals. Based on the technique of one-shot supernet, which contains all possible networks in the search space, we propose a framework for backbone search on object detection. We train the supernet under the typical detector training schedule: ImageNet pre-training and detection fine-tuning. Then, the architecture search is performed on the trained supernet, using the detection task as the guidance. This framework makes NAS on backbones very efficient. In experiments, we show the effectiveness of DetNAS on various detectors, for instance, one-stage RetinaNet and the two-stage FPN. We empirically find that networks searched on object detection shows consistent superiority compared to those searched on ImageNet classification. The resulting architecture achieves superior performance than hand-crafted networks on COCO with much less FLOPs complexity.","url_abs":"https://arxiv.org/abs/1903.10979v4","url_pdf":"https://arxiv.org/pdf/1903.10979v4.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":"detnas-neural-architecture-search-on-object","repo_url":"https://github.com/megvii-model/DetNAS","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"detnas-neural-architecture-search-on-object","repo_url":"https://github.com/open-mmlab/mmrazor","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"architecture-search","task_name":"Neural Architecture Search"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"image-classification","task_name":"image-classification"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"channel-shuffle","method_name":"Channel Shuffle"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"depthwise-convolution","method_name":"Depthwise Convolution"},{"method_slug":"detnas","method_name":"DetNAS"},{"method_slug":"detnasnet","method_name":"DetNASNet"},{"method_slug":"fpn","method_name":"FPN"},{"method_slug":"focal-loss","method_name":"Focal Loss"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"retinanet","method_name":"RetinaNet"},{"method_slug":"sgd-with-momentum","method_name":"SGD with Momentum"},{"method_slug":"shufflenet-v2-block","method_name":"ShuffleNet V2 Block"},{"method_slug":"weight-decay","method_name":"Weight Decay"}],"datasets_introduced":[],"methods_introduced":[{"slug":"detnas","name":"DetNAS","full_name":"DetNAS"},{"slug":"detnasnet","name":"DetNASNet","full_name":"DetNASNet"}],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1903.10979","atlas_url":"https://app.syntology.ai/?focus=1903.10979","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1903.10979"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/open-mmlab/mmrazor","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/megvii-model/DetNAS","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":8},"by_repo_kind":{"official":{"samples":8,"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":"469bf48752905889","entry":"accuracy","repo":"megvii-model/DetNAS","repo_kind":"official","path":"Supernet-ImageNet/utils.py","file_url":"https://github.com/megvii-model/DetNAS/blob/HEAD/Supernet-ImageNet/utils.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":"469bf48752905889"}},{"code_sha256_prefix":"eaa44944ca357418","entry":"channel_shuffle","repo":"megvii-model/DetNAS","repo_kind":"official","path":"Supernet-ImageNet/flops.py","file_url":"https://github.com/megvii-model/DetNAS/blob/HEAD/Supernet-ImageNet/flops.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":"eaa44944ca357418"}},{"code_sha256_prefix":"4686ee462c7a3786","entry":"conv1x1_dwconv_conv1x1","repo":"megvii-model/DetNAS","repo_kind":"official","path":"Supernet-ImageNet/shuffle_blocks.py","file_url":"https://github.com/megvii-model/DetNAS/blob/HEAD/Supernet-ImageNet/shuffle_blocks.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":"4686ee462c7a3786"}},{"code_sha256_prefix":"a3b5e54e37ce61d4","entry":"create_spatial_conv2d_group_bn_relu","repo":"megvii-model/DetNAS","repo_kind":"official","path":"Supernet-ImageNet/shuffle_blocks.py","file_url":"https://github.com/megvii-model/DetNAS/blob/HEAD/Supernet-ImageNet/shuffle_blocks.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":"a3b5e54e37ce61d4"}},{"code_sha256_prefix":"06193fa1714ef6fd","entry":"get_flops","repo":"megvii-model/DetNAS","repo_kind":"official","path":"Supernet-ImageNet/flops.py","file_url":"https://github.com/megvii-model/DetNAS/blob/HEAD/Supernet-ImageNet/flops.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":"06193fa1714ef6fd"}},{"code_sha256_prefix":"9a700a3b149f4952","entry":"get_parameters","repo":"megvii-model/DetNAS","repo_kind":"official","path":"Supernet-ImageNet/utils.py","file_url":"https://github.com/megvii-model/DetNAS/blob/HEAD/Supernet-ImageNet/utils.py","link_basis":"plan_row","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":"9a700a3b149f4952"}},{"code_sha256_prefix":"2902bf4410253ff7","entry":"interpolate","repo":"megvii-model/DetNAS","repo_kind":"official","path":"maskrcnn_benchmark/layers/misc.py","file_url":"https://github.com/megvii-model/DetNAS/blob/HEAD/maskrcnn_benchmark/layers/misc.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":"2902bf4410253ff7"}},{"code_sha256_prefix":"5e4726ccff0e0daf","entry":"xception","repo":"megvii-model/DetNAS","repo_kind":"official","path":"Supernet-ImageNet/shuffle_blocks.py","file_url":"https://github.com/megvii-model/DetNAS/blob/HEAD/Supernet-ImageNet/shuffle_blocks.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":"5e4726ccff0e0daf"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}