Rethinking gradient weights' influence over saliency map estimation

07/12/2022
by   Masud An Nur Islam Fahim, et al.
0

Class activation map (CAM) helps to formulate saliency maps that aid in interpreting the deep neural network's prediction. Gradient-based methods are generally faster than other branches of vision interpretability and independent of human guidance. The performance of CAM-like studies depends on the governing model's layer response, and the influences of the gradients. Typical gradient-oriented CAM studies rely on weighted aggregation for saliency map estimation by projecting the gradient maps into single weight values, which may lead to over generalized saliency map. To address this issue, we use a global guidance map to rectify the weighted aggregation operation during saliency estimation, where resultant interpretations are comparatively clean er and instance-specific. We obtain the global guidance map by performing elementwise multiplication between the feature maps and their corresponding gradient maps. To validate our study, we compare the proposed study with eight different saliency visualizers. In addition, we use seven commonly used evaluation metrics for quantitative comparison. The proposed scheme achieves significant improvement over the test images from the ImageNet, MS-COCO 14, and PASCAL VOC 2012 datasets.

READ FULL TEXT

page 2

page 5

page 6

research
01/17/2023

Opti-CAM: Optimizing saliency maps for interpretability

Methods based on class activation maps (CAM) provide a simple mechanism ...
research
02/13/2019

Why are Saliency Maps Noisy? Cause of and Solution to Noisy Saliency Maps

Saliency Map, the gradient of the score function with respect to the inp...
research
12/01/2020

Rethinking Positive Aggregation and Propagation of Gradients in Gradient-based Saliency Methods

Saliency methods interpret the prediction of a neural network by showing...
research
05/04/2022

Domino Saliency Metrics: Improving Existing Channel Saliency Metrics with Structural Information

Channel pruning is used to reduce the number of weights in a Convolution...
research
01/21/2022

Conceptor Learning for Class Activation Mapping

Class Activation Mapping (CAM) has been widely adopted to generate salie...
research
09/28/2022

Recipro-CAM: Gradient-free reciprocal class activation map

Convolutional neural network (CNN) becomes one of the most popular and p...
research
04/12/2021

Evaluating Saliency Methods for Neural Language Models

Saliency methods are widely used to interpret neural network predictions...

Please sign up or login with your details

Forgot password? Click here to reset