{"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/visual-interpretability-for-deep-learning-a","title":"Visual Interpretability for Deep Learning: a Survey","arxiv_id":"1802.00614","date":"2018-02-02","proceeding":null,"authors":["Quanshi Zhang","Song-Chun Zhu"],"abstract":"This paper reviews recent studies in understanding neural-network\nrepresentations and learning neural networks with interpretable/disentangled\nmiddle-layer representations. Although deep neural networks have exhibited\nsuperior performance in various tasks, the interpretability is always the\nAchilles' heel of deep neural networks. At present, deep neural networks obtain\nhigh discrimination power at the cost of low interpretability of their\nblack-box representations. We believe that high model interpretability may help\npeople to break several bottlenecks of deep learning, e.g., learning from very\nfew annotations, learning via human-computer communications at the semantic\nlevel, and semantically debugging network representations. We focus on\nconvolutional neural networks (CNNs), and we revisit the visualization of CNN\nrepresentations, methods of diagnosing representations of pre-trained CNNs,\napproaches for disentangling pre-trained CNN representations, learning of CNNs\nwith disentangled representations, and middle-to-end learning based on model\ninterpretability. Finally, we discuss prospective trends in explainable\nartificial intelligence.","url_abs":"http://arxiv.org/abs/1802.00614v2","url_pdf":"http://arxiv.org/pdf/1802.00614v2.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":"visual-interpretability-for-deep-learning-a","repo_url":"https://github.com/JepsonWong/CNN_Visualization","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"deep-learning","task_name":"Deep Learning"},{"task_slug":"explainable-artificial-intelligence","task_name":"Explainable artificial intelligence"},{"task_slug":"survey","task_name":"Survey"}],"methods":[{"method_slug":"interpretability","method_name":"Interpretability"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1802.00614","atlas_url":"https://app.syntology.ai/?focus=1802.00614","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":"1802.00614"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1802.00614\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1802.00614"},"call":"get_concepts_for_paper(arxiv_id=\"1802.00614\")"}],"by_repo":[{"repo":"JepsonWong/CNN_Visualization","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":"299570cb08e3416067bb46b6e9afdcda5ab2622a1e815c9dbf5c567c8cb3ef92","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}