Content area

Abstract

Explanation methods are being used to understand model reasoning and decision-making. In this work, we introduce a novel point of view for these methods. We first apply Grad-CAM, initially proposed to explain image classification models, to a segmentation network. Then, we show that small negative gradients can be used to enhance model predictions in the case of under-pixel prediction without retraining. Instead of discarding negative gradients with ReLU as Grad-CAM does, we propose Drift-Grad-CAM with two heuristics methods of thresholding as a novel approach that leverages the informative potential hidden within negative gradients. Drift-Grad-CAM method applied to U-Net and DeepLabV3 model with a ResNet-50 backbone and on two datasets, results in an improvement of performance metrics, Dice and IoU scores, by up to 46% without retraining the model. It demonstrates that some small negative gradients are underestimated but valuable source of information for pixel prediction, and they should be considered as meaningful as positive gradients in future works.

Details

Title
Drift-grad-cam method for enhanced segmentation predictions without model retraining
Publication title
Volume
37
Issue
3
Pages
1375-1388
Publication year
2025
Publication date
Jan 2025
Publisher
Springer Nature B.V.
Place of publication
Heidelberg
Country of publication
Netherlands
ISSN
09410643
e-ISSN
14333058
Source type
Scholarly Journal
Language of publication
English
Document type
Journal Article
Publication history
 
 
Online publication date
2024-11-20
Milestone dates
2024-10-05 (Registration); 2024-04-29 (Received); 2024-10-01 (Accepted)
Publication history
 
 
   First posting date
20 Nov 2024
ProQuest document ID
3159549842
Document URL
https://www.proquest.com/scholarly-journals/drift-grad-cam-method-enhanced-segmentation/docview/3159549842/se-2?accountid=208611
Copyright
Copyright Springer Nature B.V. Jan 2025
Last updated
2025-02-03
Database
ProQuest One Academic