Explainability Requires Interactivity
When explaining the decisions of deep neural networks, simple stories are tempting but dangerous. Especially in computer vision, the most popular explanation approaches give a false sense of comprehension to its users and provide an overly simplistic picture. We introduce an interactive framework to understand the highly complex decision boundaries of modern vision models. It allows the user to exhaustively inspect, probe, and test a network's decisions. Across a range of case studies, we compare the power of our interactive approach to static explanation methods, showing how these can lead a user astray, with potentially severe consequences.
Code (2)
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Interactivity x Explainability: Toward Understanding How Interactivity Can Improve Computer Vision Explanations
Explanations for computer vision models are important tools for interpreting how the underlying models work. However, they are often presented in static formats, which pose challenges for users, including information ove…
ChatDiet: Empowering Personalized Nutrition-Oriented Food Recommender Chatbots through an LLM-Augmented Framework
The profound impact of food on health necessitates advanced nutrition-oriented food recommendation services. Conventional methods often lack the crucial elements of personalization, explainability, and interactivity. Whi…
Causal DiscoveryFood recommendationNutritionPreliminary Quantitative Study on Explainability and Trust in AI Systems
Large-scale AI models such as GPT-4 have accelerated the deployment of artificial intelligence across critical domains including law, healthcare, and finance, raising urgent questions about trust and transparency. This s…
Feature ImportanceThe Role of Interactivity in Structured Estimation
We study high-dimensional sparse estimation under three natural constraints: communication constraints, local privacy constraints, and linear measurements (compressive sensing). Without sparsity assumptions, it has been …
Compressive SensingInteractive Autonomous Navigation with Internal State Inference and Interactivity Estimation
Deep reinforcement learning (DRL) provides a promising way for intelligent agents (e.g., autonomous vehicles) to learn to navigate complex scenarios. However, DRL with neural networks as function approximators is typical…
Autonomous NavigationAutonomous VehiclescounterfactualCounterfactual Reasoning+5