Locally Testing Model Detections for Semantic Global Concepts
Ensuring the quality of black-box Deep Neural Networks (DNNs) has become ever more significant, especially in safety-critical domains such as automated driving. While global concept encodings generally enable a user to test a model for a specific concept, linking global concept encodings to the local processing of single network inputs reveals their strengths and limitations. Our proposed framework global-to-local Concept Attribution (glCA) uses approaches from local (why a specific prediction originates) and global (how a model works generally) eXplainable Artificial Intelligence (xAI) to test DNNs for a predefined semantical concept locally. The approach allows for conditioning local, post-hoc explanations on predefined semantic concepts encoded as linear directions in the model's latent space. Pixel-exact scoring concerning the global concept usage assists the tester in further understanding the model processing of single data points for the selected concept. Our approach has the advantage of fully covering the model-internal encoding of the semantic concept and allowing the localization of relevant concept-related information. The results show major differences in the local perception and usage of individual global concept encodings and demand for further investigations regarding obtaining thorough semantic concept encodings.
Code (0)
등록된 구현이 없습니다.
Tasks
Explainable artificial intelligenceExplainable Artificial Intelligence (XAI)modelSimilar Papers 제목 키워드 기반
Real-Time Multi-View 3D Human Pose Estimation using Semantic Feedback to Smart Edge Sensors
We present a novel method for estimation of 3D human poses from a multi-camera setup, employing distributed smart edge sensors coupled with a backend through a semantic feedback loop. 2D joint detection for each camera v…
3D Human Pose Estimation3D Multi-Person Pose EstimationMulti-view 3D Human Pose EstimationPose EstimationI Bet You Did Not Mean That: Testing Semantic Importance via Betting
Recent works have extended notions of feature importance to semantic concepts that are inherently interpretable to the users interacting with a black-box predictive model. Yet, precise statistical guarantees, such as fal…
Feature Importanceimage-classificationImage ClassificationSemantics for Global and Local Interpretation of Deep Neural Networks
Deep neural networks (DNNs) with high expressiveness have achieved state-of-the-art performance in many tasks. However, their distributed feature representations are difficult to interpret semantically. In this work, hum…
Online Object-Level Semantic Mapping for Quadrupeds in Real-World Environments
We present an online semantic object mapping system for a quadruped robot operating in real indoor environments, turning sensor detections into named objects in a global map. During a run, the mapper integrates range geo…
Assignment-Space-Based Multi-Object Tracking and Segmentation
Multi-object tracking and segmentation (MOTS) is important for understanding dynamic scenes in video data. Existing methods perform well on multi-object detection and segmentation for independent video frames, but tr…
Multi-Object TrackingMulti-Object Tracking and SegmentationObjectobject-detection+3