{"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/aligning-pretraining-for-detection-via-object","title":"Aligning Pretraining for Detection via Object-Level Contrastive Learning","arxiv_id":"2106.02637","date":"2021-06-04","proceeding":"NeurIPS 2021 12","authors":["Fangyun Wei","Yue Gao","Zhirong Wu","Han Hu","Stephen Lin"],"abstract":"Image-level contrastive representation learning has proven to be highly effective as a generic model for transfer learning. Such generality for transfer learning, however, sacrifices specificity if we are interested in a certain downstream task. We argue that this could be sub-optimal and thus advocate a design principle which encourages alignment between the self-supervised pretext task and the downstream task. In this paper, we follow this principle with a pretraining method specifically designed for the task of object detection. We attain alignment in the following three aspects: 1) object-level representations are introduced via selective search bounding boxes as object proposals; 2) the pretraining network architecture incorporates the same dedicated modules used in the detection pipeline (e.g. FPN); 3) the pretraining is equipped with object detection properties such as object-level translation invariance and scale invariance. Our method, called Selective Object COntrastive learning (SoCo), achieves state-of-the-art results for transfer performance on COCO detection using a Mask R-CNN framework. Code is available at https://github.com/hologerry/SoCo.","url_abs":"https://arxiv.org/abs/2106.02637v2","url_pdf":"https://arxiv.org/pdf/2106.02637v2.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":"aligning-pretraining-for-detection-via-object","repo_url":"https://github.com/hologerry/SoCo","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"aligning-pretraining-for-detection-via-object","repo_url":"https://github.com/zhaojingjing713/hpr","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"specificity","task_name":"Specificity"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"},{"task_slug":"translation","task_name":"Translation"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"mask-r-cnn","method_name":"Mask R-CNN"},{"method_slug":"rpn","method_name":"RPN"},{"method_slug":"roi-align","method_name":"RoIAlign"},{"method_slug":"selective-search","method_name":"Selective Search"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2106.02637","atlas_url":"https://app.syntology.ai/?focus=2106.02637","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.02637"}},"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":"deterministic:regex_extraction","url":"https://github.com/hologerry/SoCo","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/zhaojingjing713/hpr","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":3,"ran_draft_wrong":1,"unverified":2},"by_repo_kind":{"official":{"samples":6,"ran":4,"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":3,"samples":[{"code_sha256_prefix":"b82884ce6a92a54c","entry":"add_weight_decay","repo":"hologerry/SoCo","repo_kind":"official","path":"contrast/lars.py","file_url":"https://github.com/hologerry/SoCo/blob/HEAD/contrast/lars.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b82884ce6a92a54c"}},{"code_sha256_prefix":"fac5364e2f53c6db","entry":"conv3x3","repo":"hologerry/SoCo","repo_kind":"official","path":"contrast/resnet.py","file_url":"https://github.com/hologerry/SoCo/blob/HEAD/contrast/resnet.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":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"fac5364e2f53c6db"}},{"code_sha256_prefix":"f4128de2d8a26538","entry":"conv3x3_bn_relu","repo":"hologerry/SoCo","repo_kind":"official","path":"contrast/resnet.py","file_url":"https://github.com/hologerry/SoCo/blob/HEAD/contrast/resnet.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f4128de2d8a26538"}},{"code_sha256_prefix":"0ab9a9693c33888a","entry":"setup_logger","repo":"hologerry/SoCo","repo_kind":"official","path":"contrast/logger.py","file_url":"https://github.com/hologerry/SoCo/blob/HEAD/contrast/logger.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0ab9a9693c33888a"}},{"code_sha256_prefix":"831fbed7ca8ad42c","entry":"append_batch_index_to_bboxs_and_scale","repo":"hologerry/SoCo","repo_kind":"official","path":"contrast/models/box_util.py","file_url":"https://github.com/hologerry/SoCo/blob/HEAD/contrast/models/box_util.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":false,"mcp_get_code":{"code_sha256":"831fbed7ca8ad42c"}},{"code_sha256_prefix":"719e3e747eea5104","entry":"get_scheduler","repo":"hologerry/SoCo","repo_kind":"official","path":"contrast/lr_scheduler.py","file_url":"https://github.com/hologerry/SoCo/blob/HEAD/contrast/lr_scheduler.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":false,"mcp_get_code":{"code_sha256":"719e3e747eea5104"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}