SMOOT: Saliency Guided Mask Optimized Online Training

TL;DR

SMOOT introduces a saliency-guided mask optimization technique that dynamically determines the optimal masking level during training, enhancing model accuracy and interpretability in deep neural networks.

Contribution

The paper presents a novel method to adaptively select the number of masked inputs based on training metrics, improving saliency relevance and model performance.

Findings

Improved model accuracy with saliency-guided masking.

Enhanced interpretability of neural networks through better saliency maps.

Demonstrated effectiveness on image classification tasks.

Abstract

Deep Neural Networks are powerful tools for understanding complex patterns and making decisions. However, their black-box nature impedes a complete understanding of their inner workings. Saliency-Guided Training (SGT) methods try to highlight the prominent features in the model's training based on the output to alleviate this problem. These methods use back-propagation and modified gradients to guide the model toward the most relevant features while keeping the impact on the prediction accuracy negligible. SGT makes the model's final result more interpretable by masking input partially. In this way, considering the model's output, we can infer how each segment of the input affects the output. In the particular case of image as the input, masking is applied to the input pixels. However, the masking strategy and number of pixels which we mask, are considered as a hyperparameter. Appropriate setting of masking strategy can directly affect the model's training. In this paper, we focus on this issue and present our contribution. We propose a novel method to determine the optimal number of masked images based on input, accuracy, and model loss during the training. The strategy prevents information loss which leads to better accuracy values. Also, by integrating the model's performance in the strategy formula, we show that our model represents the salient features more meaningful. Our experimental results demonstrate a substantial improvement in both model accuracy and the prominence of saliency, thereby affirming the effectiveness of our proposed solution.