FisherMask: Enhancing Neural Network Labeling Efficiency in Image Classification Using Fisher Information
This work addresses the labeling efficiency problem for deep learning practitioners by offering an incremental improvement in active learning methods.
The paper tackles the problem of reducing reliance on large labeled datasets in deep learning by proposing FisherMask, a Fisher information-based active learning method that identifies critical network parameters to select impactful samples, achieving significant performance gains on datasets like CIFAR-10 and FashionMNIST, especially in imbalanced settings.
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}.