{"work":{"id":"e4785f6f-2131-4f8e-bb53-1137ea630ec1","openalex_id":null,"doi":null,"arxiv_id":"1711.11279","raw_key":null,"title":"Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)","authors":null,"authors_text":"Been Kim, Martin Wattenberg, Justin Gilmer, Carrie Cai, James Wexler, Fernanda Viegas, and Rory Sayres","year":2017,"venue":"stat.ML","abstract":"The interpretation of deep learning models is a challenge due to their size, complexity, and often opaque internal state. In addition, many systems, such as image classifiers, operate on low-level features rather than high-level concepts. To address these challenges, we introduce Concept Activation Vectors (CAVs), which provide an interpretation of a neural net's internal state in terms of human-friendly concepts. The key idea is to view the high-dimensional internal state of a neural net as an aid, not an obstacle. We show how to use CAVs as part of a technique, Testing with CAVs (TCAV), that uses directional derivatives to quantify the degree to which a user-defined concept is important to a classification result--for example, how sensitive a prediction of \"zebra\" is to the presence of stripes. Using the domain of image classification as a testing ground, we describe how CAVs may be used to explore hypotheses and generate insights for a standard image classification network as well as a medical application.","external_url":"https://arxiv.org/abs/1711.11279","cited_by_count":null,"metadata_source":"pith","metadata_fetched_at":"2026-05-25T19:06:09.221823+00:00","pith_arxiv_id":"1711.11279","created_at":"2026-05-09T21:53:45.575214+00:00","updated_at":"2026-06-05T21:23:00.469572+00:00","title_quality_ok":true,"display_title":"Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)","render_title":"Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)"},"hub":{"state":{"work_id":"e4785f6f-2131-4f8e-bb53-1137ea630ec1","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":11,"external_cited_by_count":null,"distinct_field_count":6,"first_pith_cited_at":"2019-06-20T21:19:31+00:00","last_pith_cited_at":"2026-05-19T13:42:38+00:00","author_build_status":"not_needed","summary_status":"needed","contexts_status":"needed","graph_status":"needed","ask_index_status":"not_needed","reader_status":"not_needed","recognition_status":"not_needed","updated_at":"2026-06-08T21:24:10.143095+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":1}],"polarity_counts":[{"context_polarity":"background","n":1}],"runs":{},"summary":{},"graph":{},"authors":[]}}