Identifying Interpretable Action Concepts in Deep Networks

Abstract

A number of recent methods to understand neural networks have focused on quantifying the role of individual features. One such method, NetDissect identifies interpretable features of a model using the Broden dataset of visual semantic labels (colors, materials, textures, objects and scenes). Given the recent rise of a number of action recognition datasets, we propose extending the Broden dataset to include actions to better analyze learned action models. We describe the annotation process and results from interpreting action recognition models on the extended Broden dataset.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jun 16, 2019
Accession Number
AD1154451

Entities

People

  • Alex Lascelles
  • Aude Oliva
  • Barry A. Mcnamara
  • Dan Gutfreund
  • Kandan Ramakrishnan
  • Mathew Monfort
  • Rogerio Feris

Organizations

  • IBM Research
  • Massachusetts Institute of Technology

Tags

DTIC Thesaurus Topics

  • Artificial Intelligence
  • Artificial Intelligence Computing
  • Artificial Intelligence Software
  • Computer Vision
  • Computers
  • Convolutional Neural Networks
  • Detection
  • Detectors
  • Graphics
  • Image Recognition
  • Image Segmentation
  • Information Science
  • Learning
  • Materials
  • Neural Networks
  • Pattern Recognition
  • Recognition
  • Statistics
  • Visualizations

Fields of Study

  • Computer science

Readers

  • Computer Vision.
  • Neural Network Machine Learning.

Technology Areas

  • AI & ML
  • AI & ML - Neural Networks