A Programmatic and Semantic Approach to Explaining and DebuggingNeural Network Based Object Detectors
Even as deep neural networks have become very effective for tasks in vision and perception, it remains difficult to explain and debug their behavior. In this paper, we present a programmatic and semantic approach to explaining, understanding, and debugging the correct and incorrect behaviors of a neural network-based perception system. Our approach is semantic in that it employs a high-level representation of the distribution of environment scenarios that the detector is intended to work on. It is programmatic in that scenario representation is a program in a domain-specific probabilistic programming language which can be used to generate synthetic data to test a given perception module. Our framework assesses the performance of a perception module to identify correct and incorrect detections, extracts rules from those results that semantically characterizes the correct and incorrect scenarios, and then specializes the probabilistic program with those rules in order to more precisely characterize the scenarios in which the perception module operates correctly or not. We demonstrate our results using the SCENIC probabilistic programming language and a neural network-based object detector. Our experiments show that it is possible to automatically generate compact rules that significantly increase the correct detection rate (or conversely the incorrect detection rate) of the network and can thus help with understanding and debugging its behavior.
Code (0)
등록된 구현이 없습니다.
Tasks
Probabilistic ProgrammingMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
A Programmatic and Semantic Approach to Explaining and Debugging Neural Network Based Object Detectors
Even as deep neural networks have become very effective for tasks in vision and perception, it remains difficult to explain and debug their behavior. In this paper, we present a programmatic and semantic approach to expl…
Probabilistic ProgrammingLearning from Multiple Noisy Partial Labelers
Programmatic weak supervision creates models without hand-labeled training data by combining the outputs of heuristic labelers. Existing frameworks make the restrictive assumption that labelers output a single class labe…
AttributeClassificationtext-classificationText Classification+1Scene-level Pose Estimation for Multiple Instances of Densely Packed Objects
This paper introduces key machine learning operations that allow the realization of robust, joint 6D pose estimation of multiple instances of objects either densely packed or in unstructured piles from RGB-D data. The fi…
6D Pose EstimationPose EstimationWhat Do Deepfake Speech Detectors Actually Hear?
Deepfake speech detectors often output a single score without explaining why an audio sample is flagged, where in the signal the evidence lies, or what cues drive the decision. We propose an audio-native explainability p…
Marvolo: Programmatic Data Augmentation for Practical ML-Driven Malware Detection
Data augmentation has been rare in the cyber security domain due to technical difficulties in altering data in a manner that is semantically consistent with the original data. This shortfall is particularly onerous given…
Data AugmentationMalware Detection