Concept-based Explanations for Out-Of-Distribution Detectors
Out-of-distribution (OOD) detection plays a crucial role in ensuring the safe deployment of deep neural network (DNN) classifiers. While a myriad of methods have focused on improving the performance of OOD detectors, a critical gap remains in interpreting their decisions. We help bridge this gap by providing explanations for OOD detectors based on learned high-level concepts. We first propose two new metrics for assessing the effectiveness of a particular set of concepts for explaining OOD detectors: 1) detection completeness, which quantifies the sufficiency of concepts for explaining an OOD-detector's decisions, and 2) concept separability, which captures the distributional separation between in-distribution and OOD data in the concept space. Based on these metrics, we propose an unsupervised framework for learning a set of concepts that satisfy the desired properties of high detection completeness and concept separability, and demonstrate its effectiveness in providing concept-based explanations for diverse off-the-shelf OOD detectors. We also show how to identify prominent concepts contributing to the detection results, and provide further reasoning about their decisions.
Code (1)
Tasks
Out of Distribution (OOD) DetectionSimilar Papers 제목 키워드 기반
Explaining Object Detectors via Collective Contribution of Pixels
Visual explanations for object detectors are crucial for enhancing their reliability. Since object detectors identify and localize instances by assessing multiple features collectively, generating explanations that captu…
ObjectWhy Fake ? Unveiling the Semantic Vocabulary of Deepfake Detectors
Deepfake (DF) technology poses a significant threat to information integrity, driving the need for robust detection methods. Most DF detectors only consider predicting a binary label for whether the input is real or fake…
FFAM: Feature Factorization Activation Map for Explanation of 3D Detectors
LiDAR-based 3D object detection has made impressive progress recently, yet most existing models are black-box, lacking interpretability. Previous explanation approaches primarily focus on analyzing image-based models and…
3D Object DetectionObjectobject-detectionObject DetectionReal-Time Incremental Explanations for Object Detectors
Existing black box explainability tools for object detectors rely on multiple calls to the model, which prevents them from computing explanations in real time. In this paper we introduce IncX, an algorithm for real-time …
ObjectAre Concept Drift Detectors Reliable Alarming Systems? -- A Comparative Study
As machine learning models increasingly replace traditional business logic in the production system, their lifecycle management is becoming a significant concern. Once deployed into production, the machine learning model…
Drift DetectionManagement