Explain to Fix: A Framework to Interpret and Correct DNN Object Detector Predictions

11/19/2018
by   Denis Gudovskiy, et al.
0

Explaining predictions of deep neural networks (DNNs) is an important and nontrivial task. In this paper, we propose a practical approach to interpret decisions made by a DNN object detector that has fidelity comparable to state-of-the-art methods and sufficient computational efficiency to process large datasets. Our method relies on recent theory and approximates Shapley feature importance values. We qualitatively and quantitatively show that the proposed explanation method can be used to find image features which cause failures in DNN object detection. The developed software tool combined into the "Explain to Fix" (E2X) framework has a factor of 10 higher computational efficiency than prior methods and can be used for cluster processing using graphics processing units (GPUs). Lastly, we propose a potential extension of the E2X framework where the discovered missing features can be added into training dataset to overcome failures after model retraining.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/05/2023

Towards Better Explanations for Object Detection

Recent advances in Artificial Intelligence (AI) technology have promoted...
research
05/20/2020

An Adversarial Approach for Explaining the Predictions of Deep Neural Networks

Machine learning models have been successfully applied to a wide range o...
research
11/28/2018

Strike (with) a Pose: Neural Networks Are Easily Fooled by Strange Poses of Familiar Objects

Despite excellent performance on stationary test sets, deep neural netwo...
research
03/03/2021

Self-Checking Deep Neural Networks in Deployment

The widespread adoption of Deep Neural Networks (DNNs) in important doma...
research
05/17/2023

Explain Any Concept: Segment Anything Meets Concept-Based Explanation

EXplainable AI (XAI) is an essential topic to improve human understandin...
research
06/19/2021

Low-Power Multi-Camera Object Re-Identification using Hierarchical Neural Networks

Low-power computer vision on embedded devices has many applications. Thi...
research
09/05/2019

Detecting Deep Neural Network Defects with Data Flow Analysis

Deep neural networks (DNNs) are shown to be promising solutions in many ...

Please sign up or login with your details

Forgot password? Click here to reset