{"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/deep-metric-learning-via-lifted-structured","title":"Deep Metric Learning via Lifted Structured Feature Embedding","arxiv_id":"1511.06452","date":"2015-11-19","proceeding":"CVPR 2016 6","authors":["Hyun Oh Song","Yu Xiang","Stefanie Jegelka","Silvio Savarese"],"abstract":"Learning the distance metric between pairs of examples is of great importance\nfor learning and visual recognition. With the remarkable success from the state\nof the art convolutional neural networks, recent works have shown promising\nresults on discriminatively training the networks to learn semantic feature\nembeddings where similar examples are mapped close to each other and dissimilar\nexamples are mapped farther apart. In this paper, we describe an algorithm for\ntaking full advantage of the training batches in the neural network training by\nlifting the vector of pairwise distances within the batch to the matrix of\npairwise distances. This step enables the algorithm to learn the state of the\nart feature embedding by optimizing a novel structured prediction objective on\nthe lifted problem. Additionally, we collected Online Products dataset: 120k\nimages of 23k classes of online products for metric learning. Our experiments\non the CUB-200-2011, CARS196, and Online Products datasets demonstrate\nsignificant improvement over existing deep feature embedding methods on all\nexperimented embedding sizes with the GoogLeNet network.","url_abs":"http://arxiv.org/abs/1511.06452v1","url_pdf":"http://arxiv.org/pdf/1511.06452v1.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":"deep-metric-learning-via-lifted-structured","repo_url":"https://github.com/rksltnl/Deep-Metric-Learning-CVPR16","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"deep-metric-learning-via-lifted-structured","repo_url":"https://github.com/Cadene/recipe1m.bootstrap.pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"deep-metric-learning-via-lifted-structured","repo_url":"https://github.com/layumi/Person_reID_baseline_pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"metric-learning","task_name":"Metric Learning"},{"task_slug":"structured-prediction","task_name":"Structured Prediction"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"auxiliary-classifier","method_name":"Auxiliary Classifier"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"googlenet","method_name":"GoogLeNet"},{"method_slug":"inception-module","method_name":"Inception Module"},{"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":"softmax","method_name":"Softmax"}],"datasets_introduced":[{"slug":"stanford-online-products","name":"Stanford Online Products","full_name":"Stanford Online Products"}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1511.06452","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}