mlsanityData to 7 Oct 2026

A novel spatial-frequency domain network for zero-shot incremental learning

arXiv 2402.07216 ↗First posted 11 Feb 2024cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Zero-shot incremental learning aims to enable the model to generalize to new classes without forgetting previously learned classes. However, the semantic gap between old and new sample classes can lead to catastrophic forgetting. Additionally, existing algorithms lack capturing significant information from each sample image domain, impairing models' classification performance. Therefore, this paper proposes a novel Spatial-Frequency Domain Network (SFDNet) which contains a Spatial-Frequency Feature Extraction (SFFE) module and Attention Feature Alignment (AFA) module to improve the Zero-Shot Translation for Class Incremental algorithm. Firstly, SFFE module is designed which contains a dual attention mechanism for obtaining salient spatial-frequency feature information. Secondly, a novel feature fusion module is conducted for obtaining fused spatial-frequency domain features. Thirdly, the Nearest Class Mean classifier is utilized to select the most suitable category. Finally, iteration between tasks is performed using the Zero-Shot Translation model. The proposed SFDNet has the ability to effectively extract spatial-frequency feature representation from input images, improve the accuracy of image classification, and fundamentally alleviate catastrophic forgetting. Extensive experiments on the CUB 200-2011 and CIFAR100 datasets demonstrate that our proposed algorithm outperforms state-of-the-art incremental learning algorithms.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 24 of its 50 references that are in the map. First posted on arXiv 11 Feb 2024.

Builds on

24 of 50 references.

References · 24

  1. 2017Squeeze-and-Excitation Networkscited by 4,763
  2. 2016Overcoming catastrophic forgetting in neural networkscited by 4,718
  3. 2013Auto-Encoding Variational Bayescited by 3,980
  4. 2016Learning without Forgettingcited by 2,465
  5. 2017Gradient Episodic Memory for Continual Learningcited by 1,871
  6. 2016Progressive Neural Networkscited by 1,332
  7. 2017Continual Learning with Deep Generative Replaycited by 1,152
  8. 2017Memory Aware Synapses: Learning what (not) to forgetcited by 1,094
  9. 2019Decoupling Representation and Classifier for Long-Tailed Recognitioncited by 806
  10. 2018Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigencecited by 734
  11. 2018Overcoming catastrophic forgetting with hard attention to the taskcited by 672
  12. 2016Expert Gate: Lifelong Learning with a Network of Expertscited by 369
12 more
  1. 2014Recurrent Models of Visual Attentioncited by 344
  2. 2018Learning without Memorizingcited by 249
  3. 2017Overcoming Catastrophic Forgetting by Incremental Moment Matchingcited by 243
  4. 2020Semantic Drift Compensation for Class-Incremental Learningcited by 241
  5. 2018Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoderscited by 206
  6. 2020FcaNet: Frequency Channel Attention Networkscited by 177
  7. 2019Class-incremental Learning via Deep Model Consolidationcited by 172
  8. 2019A continual learning survey: Defying forgetting in classification taskscited by 118
  9. 2017Incremental Learning Through Deep Adaptationcited by 108
  10. 2016Less-forgetting Learning in Deep Neural Networkscited by 97
  11. 2021NDPNet: A novel non-linear data projection network for few-shot fine-grained image classificationcited by 13
  12. 2020Incremental Embedding Learning via Zero-Shot Translationcited by 11

Built on by

Not cited yet.