{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/virtual-class-enhanced-discriminative","title":"Virtual Class Enhanced Discriminative Embedding Learning","arxiv_id":"1811.12611","date":"2018-11-30","proceeding":"NeurIPS 2018 12","authors":["Binghui Chen","Weihong Deng","Haifeng Shen"],"abstract":"Recently, learning discriminative features to improve the recognition\nperformances gradually becomes the primary goal of deep learning, and numerous\nremarkable works have emerged. In this paper, we propose a novel yet extremely\nsimple method \\textbf{Virtual Softmax} to enhance the discriminative property\nof learned features by injecting a dynamic virtual negative class into the\noriginal softmax. Injecting virtual class aims to enlarge inter-class margin\nand compress intra-class distribution by strengthening the decision boundary\nconstraint. Although it seems weird to optimize with this additional virtual\nclass, we show that our method derives from an intuitive and clear motivation,\nand it indeed encourages the features to be more compact and separable. This\npaper empirically and experimentally demonstrates the superiority of Virtual\nSoftmax, improving the performances on a variety of object classification and\nface verification tasks.","url_abs":"http://arxiv.org/abs/1811.12611v1","url_pdf":"http://arxiv.org/pdf/1811.12611v1.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":"virtual-class-enhanced-discriminative","repo_url":"https://github.com/sungwool/virtual_softmax","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"virtual-class-enhanced-discriminative","repo_url":"https://github.com/taekwan-lee/Virtual-Softmax-TF","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"face-verification","task_name":"Face Verification"},{"task_slug":"classification","task_name":"General Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1811.12611","atlas_url":"https://app.syntology.ai/?focus=1811.12611","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1811.12611"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1811.12611\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1811.12611"},"call":"get_concepts_for_paper(arxiv_id=\"1811.12611\")"}],"by_repo":[{"repo":"sungwool/virtual_softmax","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"taekwan-lee/Virtual-Softmax-TF","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"51b8e43d21f4c77f4618afeac715f4e04c8bf5e11fd9efe05785b83e1db941c8","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}