{"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/learning-deep-representations-of-fine-grained","title":"Learning Deep Representations of Fine-grained Visual Descriptions","arxiv_id":"1605.05395","date":"2016-05-17","proceeding":"CVPR 2016 6","authors":["Scott Reed","Zeynep Akata","Bernt Schiele","Honglak Lee"],"abstract":"State-of-the-art methods for zero-shot visual recognition formulate learning\nas a joint embedding problem of images and side information. In these\nformulations the current best complement to visual features are attributes:\nmanually encoded vectors describing shared characteristics among categories.\nDespite good performance, attributes have limitations: (1) finer-grained\nrecognition requires commensurately more attributes, and (2) attributes do not\nprovide a natural language interface. We propose to overcome these limitations\nby training neural language models from scratch; i.e. without pre-training and\nonly consuming words and characters. Our proposed models train end-to-end to\nalign with the fine-grained and category-specific content of images. Natural\nlanguage provides a flexible and compact way of encoding only the salient\nvisual aspects for distinguishing categories. By training on raw text, our\nmodel can do inference on raw text as well, providing humans a familiar mode\nboth for annotation and retrieval. Our model achieves strong performance on\nzero-shot text-based image retrieval and significantly outperforms the\nattribute-based state-of-the-art for zero-shot classification on the Caltech\nUCSD Birds 200-2011 dataset.","url_abs":"http://arxiv.org/abs/1605.05395v1","url_pdf":"http://arxiv.org/pdf/1605.05395v1.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":"learning-deep-representations-of-fine-grained","repo_url":"https://github.com/Maymaher/StackGANv2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"learning-deep-representations-of-fine-grained","repo_url":"https://github.com/Vigneshthanga/stackGAN-v2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"learning-deep-representations-of-fine-grained","repo_url":"https://github.com/Vishal-V/StackGAN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"learning-deep-representations-of-fine-grained","repo_url":"https://github.com/hanzhanggit/StackGAN-inception-model","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"learning-deep-representations-of-fine-grained","repo_url":"https://github.com/hanzhanggit/StackGAN-v2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"learning-deep-representations-of-fine-grained","repo_url":"https://github.com/priscillalui/StackGAN-Stories","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"learning-deep-representations-of-fine-grained","repo_url":"https://github.com/rafiahmed40/stack-adverserial-network","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"learning-deep-representations-of-fine-grained","repo_url":"https://github.com/reedscot/cvpr2016","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"learning-deep-representations-of-fine-grained","repo_url":"https://github.com/rightlit/StackGAN-v2-rev","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"attribute","task_name":"Attribute"},{"task_slug":"image-retrieval","task_name":"Image Retrieval"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"zero-shot-learning","task_name":"Zero-Shot Learning"},{"task_slug":null,"task_name":"zero-shot-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/few-shot-image-classification-on-cub-200-50","task":"Few-Shot Image Classification","dataset":"CUB 200 50-way (0-shot)","model":"DA-SJE Reed et al. (2016)","rank_in_archive_order":2,"of":4,"metrics":{"Accuracy":"50.9"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-cub-200-50","task":"Few-Shot Image Classification","dataset":"CUB 200 50-way (0-shot)","model":"DS-SJE Reed et al. (2016)","rank_in_archive_order":3,"of":4,"metrics":{"Accuracy":"50.4"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-cub-200-2011-1","task":"Few-Shot Image Classification","dataset":"CUB-200-2011 - 0-Shot","model":"Word CNN-RNN (DS-SJE Embedding)","rank_in_archive_order":1,"of":5,"metrics":{"AP50":"48.7","Top-1 Accuracy":"56.8%"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-flowers-102-1","task":"Few-Shot Image Classification","dataset":"Flowers-102 - 0-Shot","model":"Word CNN-RNN (DS-SJE Embedding)","rank_in_archive_order":1,"of":1,"metrics":{"AP50":"59.6","Accuracy":"65.6%"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1605.05395","atlas_url":"https://app.syntology.ai/?focus=1605.05395","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":"1605.05395"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1605.05395\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1605.05395"},"call":"get_concepts_for_paper(arxiv_id=\"1605.05395\")"}],"by_repo":[{"repo":"Maymaher/StackGANv2","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"Vigneshthanga/stackGAN-v2","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"Vishal-V/StackGAN","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1612.03242"],"harvested_for_calls":[{"arxiv_id":"1612.03242","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1612.03242"},"call":"get_harvested_code_for_paper(arxiv_id=\"1612.03242\")"}]},{"repo":"hanzhanggit/StackGAN-inception-model","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1605.05396"],"harvested_for_calls":[{"arxiv_id":"1605.05396","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1605.05396"},"call":"get_harvested_code_for_paper(arxiv_id=\"1605.05396\")"}]},{"repo":"hanzhanggit/StackGAN-v2","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1710.10916"],"harvested_for_calls":[{"arxiv_id":"1710.10916","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1710.10916"},"call":"get_harvested_code_for_paper(arxiv_id=\"1710.10916\")"}]},{"repo":"priscillalui/StackGAN-Stories","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1605.05396"],"harvested_for_calls":[{"arxiv_id":"1605.05396","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1605.05396"},"call":"get_harvested_code_for_paper(arxiv_id=\"1605.05396\")"}]},{"repo":"rafiahmed40/stack-adverserial-network","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1612.03242"],"harvested_for_calls":[{"arxiv_id":"1612.03242","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1612.03242"},"call":"get_harvested_code_for_paper(arxiv_id=\"1612.03242\")"}]},{"repo":"reedscot/cvpr2016","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"rightlit/StackGAN-v2-rev","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1710.10916"],"harvested_for_calls":[{"arxiv_id":"1710.10916","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1710.10916"},"call":"get_harvested_code_for_paper(arxiv_id=\"1710.10916\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","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":"15395502e54ffe9ee9f61180d11f4cf96807fe9912a99619a3adf100f9f32b5d","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}