Documents
Poster
Poster
Poster for IMAGE ATTRIBUTION BY GENERATING IMAGES
- DOI:
- 10.60864/ewss-7962
- Citation Author(s):
- Submitted by:
- aniket singh
- Last updated:
- 6 June 2024 - 10:27am
- Document Type:
- Poster
- Document Year:
- 2024
- Event:
- Presenters:
- aniket singh
- Paper Code:
- 4010
- Categories:
- Log in to post comments
We introduce GPNN-CAM, a novel method for CNN explanation, that bridges two distinct areas of computer vision:
Image Attribution, which aims to explain a predictor by highlighting image regions it finds important, and Single
Image Generation (SIG), that focuses on learning how to generate variations of a single sample. GPNN-CAM leverages samples generated by Generative
Patch Nearest Neighbors (GPNN) into a Class Activation Map (CAM) flavored attribution scheme. Our findings reveal that the incorporation of these samples yields remarkably effective results, enabling GPNN-CAM to demonstrate superior performance across multiple classifier architectures, and datasets.