{"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/deeper-and-wider-siamese-networks-for-real","title":"Deeper and Wider Siamese Networks for Real-Time Visual Tracking","arxiv_id":"1901.01660","date":"2019-01-07","proceeding":"CVPR 2019 6","authors":["Zhipeng Zhang","Houwen Peng"],"abstract":"Siamese networks have drawn great attention in visual tracking because of\ntheir balanced accuracy and speed. However, the backbone networks used in\nSiamese trackers are relatively shallow, such as AlexNet [18], which does not\nfully take advantage of the capability of modern deep neural networks. In this\npaper, we investigate how to leverage deeper and wider convolutional neural\nnetworks to enhance tracking robustness and accuracy. We observe that direct\nreplacement of backbones with existing powerful architectures, such as ResNet\n[14] and Inception [33], does not bring improvements. The main reasons are that\n1)large increases in the receptive field of neurons lead to reduced feature\ndiscriminability and localization precision; and 2) the network padding for\nconvolutions induces a positional bias in learning. To address these issues, we\npropose new residual modules to eliminate the negative impact of padding, and\nfurther design new architectures using these modules with controlled receptive\nfield size and network stride. The designed architectures are lightweight and\nguarantee real-time tracking speed when applied to SiamFC [2] and SiamRPN [20].\nExperiments show that solely due to the proposed network architectures, our\nSiamFC+ and SiamRPN+ obtain up to 9.8%/5.7% (AUC), 23.3%/8.8% (EAO) and\n24.4%/25.0% (EAO) relative improvements over the original versions [2, 20] on\nthe OTB-15, VOT-16 and VOT-17 datasets, respectively.","url_abs":"http://arxiv.org/abs/1901.01660v3","url_pdf":"http://arxiv.org/pdf/1901.01660v3.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":"deeper-and-wider-siamese-networks-for-real","repo_url":"https://github.com/researchmm/SiamDW","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"deeper-and-wider-siamese-networks-for-real","repo_url":"https://github.com/logiklesuraj/SiamFC","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"deeper-and-wider-siamese-networks-for-real","repo_url":"https://github.com/logiklesuraj/siamfcex","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"deeper-and-wider-siamese-networks-for-real","repo_url":"https://github.com/wangxiao5791509/SiamDW_tracker_revised","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"deeper-and-wider-siamese-networks-for-real","repo_url":"https://github.com/zllrunning/SiameseX.PyTorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"real-time-visual-tracking","task_name":"Real-Time Visual Tracking"},{"task_slug":"video-object-tracking","task_name":"Video Object Tracking"},{"task_slug":"visual-object-tracking","task_name":"Visual Object Tracking"},{"task_slug":"visual-tracking","task_name":"Visual Tracking"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"grouped-convolution","method_name":"Grouped Convolution"},{"method_slug":"local-response-normalization","method_name":"Local Response Normalization"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"speed","method_name":"SPEED"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/video-object-tracking-on-nv-vot211","task":"Video Object Tracking","dataset":"NT-VOT211","model":"SiamDW","rank_in_archive_order":21,"of":43,"metrics":{"AUC":"35.18","Precision":"46.18"},"uses_additional_data":false},{"leaderboard":"/sota/visual-object-tracking-on-vot2016","task":"Visual Object Tracking","dataset":"VOT2016","model":"SiamRPN+","rank_in_archive_order":3,"of":6,"metrics":{"Expected Average Overlap (EAO)":"0.37"},"uses_additional_data":false},{"leaderboard":"/sota/visual-object-tracking-on-vot2017","task":"Visual Object Tracking","dataset":"VOT2017","model":"SiamRPN+","rank_in_archive_order":2,"of":6,"metrics":{"Expected Average Overlap (EAO)":"0.30"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1901.01660","atlas_url":"https://app.syntology.ai/?focus=1901.01660","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.01660"}},"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/wangxiao5791509/SiamDW_tracker_revised","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/zllrunning/SiameseX.PyTorch","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/logiklesuraj/SiamFC","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/researchmm/SiamDW","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/logiklesuraj/siamfcex","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":3},"by_repo_kind":{"official":{"samples":3,"ran":3,"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":"c8ac63d1d0b8d1d6","entry":"check_trainable","repo":"researchmm/SiamDW","repo_kind":"official","path":"siamese_tracking/train_siamfc.py","file_url":"https://github.com/researchmm/SiamDW/blob/HEAD/siamese_tracking/train_siamfc.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c8ac63d1d0b8d1d6"}},{"code_sha256_prefix":"24b18da9072cadee","entry":"get_optimizer","repo":"researchmm/SiamDW","repo_kind":"official","path":"siamese_tracking/train_siamfc.py","file_url":"https://github.com/researchmm/SiamDW/blob/HEAD/siamese_tracking/train_siamfc.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"24b18da9072cadee"}},{"code_sha256_prefix":"05eeb398e5bfdf18","entry":"lr_decay","repo":"researchmm/SiamDW","repo_kind":"official","path":"siamese_tracking/train_siamfc.py","file_url":"https://github.com/researchmm/SiamDW/blob/HEAD/siamese_tracking/train_siamfc.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"05eeb398e5bfdf18"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}