LAP: An Attention-Based Module for Concept Based Self-Interpretation and Knowledge Injection in Convolutional Neural Networks

no code implementations • 27 Jan 2022 • Rassa Ghavami Modegh, Ahmad Salimi, Alireza Dizaji, Hamid R. Rabiee

Despite the state-of-the-art performance of deep convolutional neural networks, they are susceptible to bias and malfunction in unseen situations.

Decision Making valid