FisherMask: Enhancing Neural Network Labeling Efficiency in Image Classification Using Fisher Information

TL;DR

FisherMask introduces a Fisher information-based active learning method that efficiently identifies key model parameters to reduce labeling efforts in image classification tasks, outperforming existing approaches especially with imbalanced data.

Contribution

The paper presents FisherMask, a novel Fisher information-based active learning approach that improves sample selection and model understanding in image classification.

Findings

Outperforms state-of-the-art methods on CIFAR-10 and FashionMNIST.

Significantly improves labeling efficiency, especially in imbalanced datasets.

Provides insights into model behavior through Fisher information analysis.

Abstract

Deep learning (DL) models are popular across various domains due to their remarkable performance and efficiency. However, their effectiveness relies heavily on large amounts of labeled data, which are often time-consuming and labor-intensive to generate manually. To overcome this challenge, it is essential to develop strategies that reduce reliance on extensive labeled data while preserving model performance. In this paper, we propose FisherMask, a Fisher information-based active learning (AL) approach that identifies key network parameters by masking them based on their Fisher information values. FisherMask enhances batch AL by using Fisher information to select the most critical parameters, allowing the identification of the most impactful samples during AL training. Moreover, Fisher information possesses favorable statistical properties, offering valuable insights into model behavior and providing a better understanding of the performance characteristics within the AL pipeline. Our extensive experiments demonstrate that FisherMask significantly outperforms state-of-the-art methods on diverse datasets, including CIFAR-10 and FashionMNIST, especially under imbalanced settings. These improvements lead to substantial gains in labeling efficiency. Hence serving as an effective tool to measure the sensitivity of model parameters to data samples. Our code is available on \url{https://github.com/sgchr273/FisherMask}.