Can I read Automatic Concept Extraction for Concept Bottleneck-based Video Classification on EtoBox?

Automatic Concept Extraction for Concept Bottleneck-based Video Classification by Jeyakumar, Jeya Vikranth; Dickens, Luke; Garcia, Luis; Cheng, Yu-Hsi; Echavarria, Diego Ramirez; Noor, Joseph; Russo, Alessandra; Kaplan, Lance; Blasch, Erik; Srivastava, Mani is a scholarly article available to read on EtoBox.

What is Automatic Concept Extraction for Concept Bottleneck-based Video Classification about?

Recent efforts in interpretable deep learning models have shown that concept-based explanation methods achieve competitive accuracy with standard end-to-end models and enable reasoning and intervention about extracted high-level visual concepts from images, e.g., identifying the wing color and beak length for bird-species classification. However, these concept bottleneck models rely on a necessary and sufficient set of predefined concepts-which is intractable for complex tasks such as video classification. For complex tasks, the labels and the relationship between visual elements span many frames, e.g., identifying a bird flying or catching prey-necessitating concepts with various levels of abstraction. To this end, we present CoDEx, an automatic Concept Discovery and Extraction module that rigorously composes a necessary and sufficient set of concept abstractions for concept-based video classification. CoDEx identifies a rich set of complex concept abstractions from natural language explanations of videos-obviating the need to predefine the amorphous set of concepts. To demonstrate our method's viability, we construct two new public datasets that combine existing complex video cla

Author

Jeyakumar, Jeya Vikranth; Dickens, Luke; Garcia, Luis; Cheng, Yu-Hsi; Echavarria, Diego Ramirez; Noor, Joseph; Russo, Alessandra; Kaplan, Lance; Blasch, Erik; Srivastava, Mani

Published

2022

Language

EN