{"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/heated-up-softmax-embedding","title":"Heated-Up Softmax Embedding","arxiv_id":"1809.04157","date":"2018-09-11","proceeding":"ICLR 2019 5","authors":["Xu Zhang","Felix Xinnan Yu","Svebor Karaman","Wei zhang","Shih-Fu Chang"],"abstract":"Metric learning aims at learning a distance which is consistent with the\nsemantic meaning of the samples. The problem is generally solved by learning an\nembedding for each sample such that the embeddings of samples of the same\ncategory are compact while the embeddings of samples of different categories\nare spread-out in the feature space. We study the features extracted from the\nsecond last layer of a deep neural network based classifier trained with the\ncross entropy loss on top of the softmax layer. We show that training\nclassifiers with different temperature values of softmax function leads to\nfeatures with different levels of compactness. Leveraging these insights, we\npropose a \"heating-up\" strategy to train a classifier with increasing\ntemperatures, leading the corresponding embeddings to achieve state-of-the-art\nperformance on a variety of metric learning benchmarks.","url_abs":"http://arxiv.org/abs/1809.04157v1","url_pdf":"http://arxiv.org/pdf/1809.04157v1.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":"heated-up-softmax-embedding","repo_url":"https://github.com/ColumbiaDVMM/Heated_Up_Softmax_Embedding","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"BSD-2-Clause"}}],"tasks":[{"task_slug":"metric-learning","task_name":"Metric Learning"}],"methods":[{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1809.04157","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1809.04157"}},"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/ColumbiaDVMM/Heated_Up_Softmax_Embedding","reach":{"status":"ok","spdx":"BSD-2-Clause"}}],"summary":{"unverified":10},"by_repo_kind":{"official":{"samples":10,"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":"b083ebe764bd88c8","entry":"GeMPooling","repo":"ColumbiaDVMM/Heated_Up_Softmax_Embedding","repo_kind":"official","path":"tensorflow/nets/inception_v1.py","file_url":"https://github.com/ColumbiaDVMM/Heated_Up_Softmax_Embedding/blob/HEAD/tensorflow/nets/inception_v1.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"b083ebe764bd88c8"}},{"code_sha256_prefix":"6a10e91275b9fa20","entry":"crc32c","repo":"ColumbiaDVMM/Heated_Up_Softmax_Embedding","repo_kind":"official","path":"tensorflow/crc32c.py","file_url":"https://github.com/ColumbiaDVMM/Heated_Up_Softmax_Embedding/blob/HEAD/tensorflow/crc32c.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"6a10e91275b9fa20"}},{"code_sha256_prefix":"aefa7f66567ae42a","entry":"crc_finalize","repo":"ColumbiaDVMM/Heated_Up_Softmax_Embedding","repo_kind":"official","path":"tensorflow/crc32c.py","file_url":"https://github.com/ColumbiaDVMM/Heated_Up_Softmax_Embedding/blob/HEAD/tensorflow/crc32c.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"aefa7f66567ae42a"}},{"code_sha256_prefix":"bd3941c9231fdeb6","entry":"crc_update","repo":"ColumbiaDVMM/Heated_Up_Softmax_Embedding","repo_kind":"official","path":"tensorflow/crc32c.py","file_url":"https://github.com/ColumbiaDVMM/Heated_Up_Softmax_Embedding/blob/HEAD/tensorflow/crc32c.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"bd3941c9231fdeb6"}},{"code_sha256_prefix":"cd2dd7d4d3a3dff6","entry":"dense_to_one_hot","repo":"ColumbiaDVMM/Heated_Up_Softmax_Embedding","repo_kind":"official","path":"tensorflow/mnist.py","file_url":"https://github.com/ColumbiaDVMM/Heated_Up_Softmax_Embedding/blob/HEAD/tensorflow/mnist.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"cd2dd7d4d3a3dff6"}},{"code_sha256_prefix":"24b10f0c7a83f999","entry":"extract_images","repo":"ColumbiaDVMM/Heated_Up_Softmax_Embedding","repo_kind":"official","path":"tensorflow/mnist.py","file_url":"https://github.com/ColumbiaDVMM/Heated_Up_Softmax_Embedding/blob/HEAD/tensorflow/mnist.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"24b10f0c7a83f999"}},{"code_sha256_prefix":"1318c92a86283291","entry":"extract_labels","repo":"ColumbiaDVMM/Heated_Up_Softmax_Embedding","repo_kind":"official","path":"tensorflow/mnist.py","file_url":"https://github.com/ColumbiaDVMM/Heated_Up_Softmax_Embedding/blob/HEAD/tensorflow/mnist.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"1318c92a86283291"}},{"code_sha256_prefix":"1df18732e8c6b704","entry":"nca_loss","repo":"ColumbiaDVMM/Heated_Up_Softmax_Embedding","repo_kind":"official","path":"tensorflow/layers.py","file_url":"https://github.com/ColumbiaDVMM/Heated_Up_Softmax_Embedding/blob/HEAD/tensorflow/layers.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"1df18732e8c6b704"}},{"code_sha256_prefix":"dc83b74103e1aaff","entry":"pad","repo":"ColumbiaDVMM/Heated_Up_Softmax_Embedding","repo_kind":"official","path":"dataset/bird200.py","file_url":"https://github.com/ColumbiaDVMM/Heated_Up_Softmax_Embedding/blob/HEAD/dataset/bird200.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"dc83b74103e1aaff"}},{"code_sha256_prefix":"56d62fbe02062398","entry":"trim","repo":"ColumbiaDVMM/Heated_Up_Softmax_Embedding","repo_kind":"official","path":"dataset/bird200.py","file_url":"https://github.com/ColumbiaDVMM/Heated_Up_Softmax_Embedding/blob/HEAD/dataset/bird200.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"56d62fbe02062398"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}