{"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/training-time-friendly-network-for-real-time","title":"Training-Time-Friendly Network for Real-Time Object Detection","arxiv_id":"1909.00700","date":"2019-09-02","proceeding":null,"authors":["Zili Liu","Tu Zheng","Guodong Xu","Zheng Yang","Haifeng Liu","Deng Cai"],"abstract":"Modern object detectors can rarely achieve short training time, fast inference speed, and high accuracy at the same time. To strike a balance among them, we propose the Training-Time-Friendly Network (TTFNet). In this work, we start with light-head, single-stage, and anchor-free designs, which enable fast inference speed. Then, we focus on shortening training time. We notice that encoding more training samples from annotated boxes plays a similar role as increasing batch size, which helps enlarge the learning rate and accelerate the training process. To this end, we introduce a novel approach using Gaussian kernels to encode training samples. Besides, we design the initiative sample weights for better information utilization. Experiments on MS COCO show that our TTFNet has great advantages in balancing training time, inference speed, and accuracy. It has reduced training time by more than seven times compared to previous real-time detectors while maintaining state-of-the-art performances. In addition, our super-fast version of TTFNet-18 and TTFNet-53 can outperform SSD300 and YOLOv3 by less than one-tenth of their training time, respectively. The code has been made available at \\url{https://github.com/ZJULearning/ttfnet}.","url_abs":"https://arxiv.org/abs/1909.00700v3","url_pdf":"https://arxiv.org/pdf/1909.00700v3.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":"training-time-friendly-network-for-real-time","repo_url":"https://github.com/ZJULearning/ttfnet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"training-time-friendly-network-for-real-time","repo_url":"https://github.com/593903762/ttf","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"training-time-friendly-network-for-real-time","repo_url":"https://github.com/XinYangDong/ttfnet-master2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"training-time-friendly-network-for-real-time","repo_url":"https://github.com/oulin1031esti/detect","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"training-time-friendly-network-for-real-time","repo_url":"https://github.com/ximilar-com/xcenternet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"training-time-friendly-network-for-real-time","repo_url":"https://github.com/PaddlePaddle/PaddleDetection","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"paddle","reach":null}],"tasks":[{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"real-time-object-detection","task_name":"Real-Time Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"logistic-regression","method_name":"Logistic Regression"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"yolov3","method_name":"YOLOv3"},{"method_slug":"k-means-clustering","method_name":"k-Means Clustering"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1909.00700","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.00700"}},"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/oulin1031esti/detect","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ZJULearning/ttfnet","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/PaddlePaddle/PaddleDetection","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/593903762/ttf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/XinYangDong/ttfnet-master2","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ximilar-com/xcenternet","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":1,"unverified":7},"by_repo_kind":{"listed":{"samples":8,"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":"f2a33236566ea043","entry":"gaussian_radius","repo":"ximilar-com/xcenternet","repo_kind":"listed","path":"xcenternet/model/encoder.py","file_url":"https://github.com/ximilar-com/xcenternet/blob/HEAD/xcenternet/model/encoder.py","link_basis":"harvester_set","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":"f2a33236566ea043"}},{"code_sha256_prefix":"97ec0f498e1be4e1","entry":"draw_umich_gaussian","repo":"ximilar-com/xcenternet","repo_kind":"listed","path":"xcenternet/model/encoder.py","file_url":"https://github.com/ximilar-com/xcenternet/blob/HEAD/xcenternet/model/encoder.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":"97ec0f498e1be4e1"}},{"code_sha256_prefix":"c171c4b57b660e23","entry":"gaussian2D","repo":"ximilar-com/xcenternet","repo_kind":"listed","path":"xcenternet/model/encoder.py","file_url":"https://github.com/ximilar-com/xcenternet/blob/HEAD/xcenternet/model/encoder.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":"c171c4b57b660e23"}},{"code_sha256_prefix":"d81ea661f423acca","entry":"heatmap_focal_loss","repo":"ximilar-com/xcenternet","repo_kind":"listed","path":"xcenternet/model/loss.py","file_url":"https://github.com/ximilar-com/xcenternet/blob/HEAD/xcenternet/model/loss.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":"d81ea661f423acca"}},{"code_sha256_prefix":"bebeea9a1d22ce22","entry":"nms","repo":"ximilar-com/xcenternet","repo_kind":"listed","path":"xcenternet/model/decoder.py","file_url":"https://github.com/ximilar-com/xcenternet/blob/HEAD/xcenternet/model/decoder.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":"bebeea9a1d22ce22"}},{"code_sha256_prefix":"e14793d929c62e92","entry":"offset_l1_loss","repo":"ximilar-com/xcenternet","repo_kind":"listed","path":"xcenternet/model/loss.py","file_url":"https://github.com/ximilar-com/xcenternet/blob/HEAD/xcenternet/model/loss.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":"e14793d929c62e92"}},{"code_sha256_prefix":"6f7345c38f60f030","entry":"size_l1_loss","repo":"ximilar-com/xcenternet","repo_kind":"listed","path":"xcenternet/model/loss.py","file_url":"https://github.com/ximilar-com/xcenternet/blob/HEAD/xcenternet/model/loss.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":"6f7345c38f60f030"}},{"code_sha256_prefix":"116fc2a94a061185","entry":"topk","repo":"ximilar-com/xcenternet","repo_kind":"listed","path":"xcenternet/model/decoder.py","file_url":"https://github.com/ximilar-com/xcenternet/blob/HEAD/xcenternet/model/decoder.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":"116fc2a94a061185"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}