2021 IEEE International Conference on Image Processing

19-22 September 2021 • Anchorage, Alaska, USA

Imaging Without Borders

2021 IEEE International Conference on Image Processing

19-22 September 2021 • Anchorage, Alaska, USA

Login Paper Search My Schedule Paper Index Help

My ICIP 2021 Schedule

Note: Your custom schedule will not be saved unless you create a new account or login to an existing account.
  1. Create a login based on your email (takes less than one minute)
  2. Perform 'Paper Search'
  3. Select papers that you desire to save in your personalized schedule
  4. Click on 'My Schedule' to see the current list of selected papers
  5. Click on 'Printable Version' to create a separate window suitable for printing (the header and menu will appear, but will not actually print)

Paper Detail

Paper IDSS-EDNN.4
Paper Title Class Specific Interpretability in CNN Using Causal Analysis
Authors Ankit Yadu, Suhas P K, Samsung Research Institute India, Bangalore, India; Neelam Sinha, International Institute of Information Technology, Bangalore, India
SessionSS-EDNN: Special Session: Explainable Deep Neural Networks for Image/Video Processing
LocationArea B
Session Time:Wednesday, 22 September, 14:30 - 16:00
Presentation Time:Wednesday, 22 September, 14:30 - 16:00
Presentation Poster
Topic Special Sessions: Explainable Deep Neural Networks for Image/Video Processing
IEEE Xplore Open Preview  Click here to view in IEEE Xplore
Abstract A singular problem that mars the wide applicability of machine learning (ML) models is the lack of generalizability and interpretability. The ML community is increasingly working on bridging this gap. Prominent among them are methods that study causal significance of features, with techniques such as Average Causal Effect (ACE). In this paper, our objective is to utilize the causal analysis framework to measure the significance level of the features in binary classification task. Towards this, we propose a novel ACE-based metric called "Absolute area under ACE (A-ACE)" which computes the area of the absolute value of the ACE across different permissible levels of intervention. The performance of the proposed metric is illustrated on MNIST data set (~42000 images) by considering pair-wise binary classification problem. The computed metric values are found to be higher (peak performance of 50% higher than others) at precisely those locations that human intuition would mark as distinguishing regions. The method helps to capture the quantifiable metric which represents the distinction between the classes learnt by the model. This metric aids in visual explanation of the model's prediction and thus, makes the model more trustworthy.