{"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/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":{"atlas_url":"https://app.syntology.ai/?focus=1802.00614","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}