mlsanityData to 14 Oct 2026

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

arXiv 2411.05752 ↗First posted 8 Nov 2024cs.LG cs.CL cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

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 urlhttps://github.com/sgchr273/FisherMask.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 16 of its 24 references that are in the map. First posted on arXiv 8 Nov 2024.

Builds on

16 of 24 references.

References · 16

  1. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
  2. 2013Visualizing and Understanding Convolutional Networkscited by 2,290
  3. 2019Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Boundscited by 610
  4. 2021Training Neural Networks with Fixed Sparse Maskscited by 214
  5. 2019Deep Active Learning: Unified and Principled Method for Query and Trainingcited by 93
  6. 2019Diverse mini-batch Active Learningcited by 89
  7. 2021Gone Fishing: Neural Active Learning with Fisher Embeddingscited by 88
  8. 2022Unifying Approaches in Active Learning and Active Sampling via Fisher Information and Information-Theoretic Quantitiescited by 28
  9. 2015Convergence Rates of Active Learning for Maximum Likelihood Estimationcited by 25
  10. 2023Entropic Open-set Active Learningcited by 23
  11. 2021Active Learning for Deep Visual Trackingcited by 19
  12. 2016Asymptotic Analysis of Objectives based on Fisher Information in Active Learningcited by 14
4 more
  1. 2021Supervised Anomaly Detection via Conditional Generative Adversarial Network and Ensemble Active Learningcited by 11
  2. 2022Active Learning by Query by Committee with Robust Divergencescited by 9
  3. 2024Compute-Efficient Active Learningcited by 2
  4. 2023Ocean Data Quality Assessment through Outlier Detection-enhanced Active Learningcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 0; 2026: 2.

3 papers.

  1. 2024LPLgrad: Optimizing Active Learning Through Gradient Norm Sample Selection and Auxiliary Model Trainingcited by 2
  2. 2026Prototype Fusion: A Training-Free Multi-Layer Approach to OOD Detectioncited by 0
  3. 2026Learning What Can Be Picked: Active Reachability Estimation for Efficient Robotic Fruit Harvestingcited by 0