Singular Value Fine-tuning for Few-Shot Class-Incremental Learning

• URL: http://arxiv.org/abs/2503.10214v1
• Date: Thu, 13 Mar 2025 09:57:28 GMT
• Title: Singular Value Fine-tuning for Few-Shot Class-Incremental Learning
• Authors: Zhiwu Wang, Yichen Wu, Renzhen Wang, Haokun Lin, Quanziang Wang, Qian Zhao, Deyu Meng,
• Abstract summary: Class-Incremental Learning (CIL) aims to prevent catastrophic forgetting of previously learned classes while incorporating new ones.<n>We propose the Singular Value Finetuning for FSCIL (SVFCL)<n>SVFCL applies singular value decomposition to the foundation model weights, keeping the singular vectors fixed while fine-tuning the singular values for each task, and then merging them.
• Score: 38.777602828340356
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Class-Incremental Learning (CIL) aims to prevent catastrophic forgetting of previously learned classes while sequentially incorporating new ones. The more challenging Few-shot CIL (FSCIL) setting further complicates this by providing only a limited number of samples for each new class, increasing the risk of overfitting in addition to standard CIL challenges. While catastrophic forgetting has been extensively studied, overfitting in FSCIL, especially with large foundation models, has received less attention. To fill this gap, we propose the Singular Value Fine-tuning for FSCIL (SVFCL) and compared it with existing approaches for adapting foundation models to FSCIL, which primarily build on Parameter Efficient Fine-Tuning (PEFT) methods like prompt tuning and Low-Rank Adaptation (LoRA). Specifically, SVFCL applies singular value decomposition to the foundation model weights, keeping the singular vectors fixed while fine-tuning the singular values for each task, and then merging them. This simple yet effective approach not only alleviates the forgetting problem but also mitigates overfitting more effectively while significantly reducing trainable parameters. Extensive experiments on four benchmark datasets, along with visualizations and ablation studies, validate the effectiveness of SVFCL. The code will be made available.

Related papers

• Adaptive Additive Parameter Updates of Vision Transformers for Few-Shot Continual Learning [0.0]
  Few-shot class incremental learning (FSCIL) addresses this by first training a model on a robust dataset of base classes and then incrementally adapting it in successive sessions. This approach is prone to overfitting on the limited new data, which can compromise overall performance and exacerbate forgetting. We propose a novel FSCIL framework that leverages a frozen Vision Transformer (ViT) backbone augmented with parameter-efficient additive updates.
  arXiv  Detail & Related papers  (2025-04-11T21:17:30Z)
• Unbiased Max-Min Embedding Classification for Transductive Few-Shot Learning: Clustering and Classification Are All You Need [83.10178754323955]
  Few-shot learning enables models to generalize from only a few labeled examples. We propose the Unbiased Max-Min Embedding Classification (UMMEC) Method, which addresses the key challenges in few-shot learning. Our method significantly improves classification performance with minimal labeled data, advancing the state-of-the-art in annotatedL.
  arXiv  Detail & Related papers  (2025-03-28T07:23:07Z)
• FeTT: Continual Class Incremental Learning via Feature Transformation Tuning [19.765229703131876]
  Continual learning (CL) aims to extend deep models from static and enclosed environments to dynamic and complex scenarios. Recent CL models have gradually shifted towards the utilization of pre-trained models with parameter-efficient fine-tuning strategies. This paper proposes feature transformation tuning (FeTT) model to non-parametrically fine-tune backbone features across all tasks.
  arXiv  Detail & Related papers  (2024-05-20T06:33:50Z)
• FeTrIL++: Feature Translation for Exemplar-Free Class-Incremental Learning with Hill-Climbing [3.533544633664583]
  Exemplar-free class-incremental learning (EFCIL) poses significant challenges, primarily due to catastrophic forgetting. Traditional EFCIL approaches typically skew towards either model plasticity through successive fine-tuning or stability. This paper builds upon the foundational FeTrIL framework to examine the efficacy of various oversampling techniques and dynamic optimization strategies.
  arXiv  Detail & Related papers  (2024-03-12T08:34:05Z)
• Bias Mitigating Few-Shot Class-Incremental Learning [17.185744533050116]
  Few-shot class-incremental learning aims at recognizing novel classes continually with limited novel class samples. Recent methods somewhat alleviate the accuracy imbalance between base and incremental classes by fine-tuning the feature extractor in the incremental sessions. We propose a novel method to mitigate model bias of the FSCIL problem during training and inference processes.
  arXiv  Detail & Related papers  (2024-02-01T10:37:41Z)
• Enhanced Few-Shot Class-Incremental Learning via Ensemble Models [34.84881941101568]
  Few-shot class-incremental learning aims to continually fit new classes with limited training data. The main challenges are overfitting the rare new training samples and forgetting old classes. We propose a new ensemble model framework cooperating with data augmentation to boost generalization.
  arXiv  Detail & Related papers  (2024-01-14T06:07:07Z)
• Sparse is Enough in Fine-tuning Pre-trained Large Language Models [98.46493578509039]
  We propose a gradient-based sparse fine-tuning algorithm, named Sparse Increment Fine-Tuning (SIFT) We validate its effectiveness on a range of tasks including the GLUE Benchmark and Instruction-tuning.
  arXiv  Detail & Related papers  (2023-12-19T06:06:30Z)
• To Repeat or Not To Repeat: Insights from Scaling LLM under Token-Crisis [50.31589712761807]
  Large language models (LLMs) are notoriously token-hungry during pre-training, and high-quality text data on the web is approaching its scaling limit for LLMs. We investigate the consequences of repeating pre-training data, revealing that the model is susceptible to overfitting. Second, we examine the key factors contributing to multi-epoch degradation, finding that significant factors include dataset size, model parameters, and training objectives.
  arXiv  Detail & Related papers  (2023-05-22T17:02:15Z)
• Strong Baselines for Parameter Efficient Few-Shot Fine-tuning [50.83426196335385]
  Few-shot classification (FSC) entails learning novel classes given only a few examples per class after a pre-training (or meta-training) phase. Recent works have shown that simply fine-tuning a pre-trained Vision Transformer (ViT) on new test classes is a strong approach for FSC. Fine-tuning ViTs, however, is expensive in time, compute and storage. This has motivated the design of parameter efficient fine-tuning (PEFT) methods which fine-tune only a fraction of the Transformer's parameters.
  arXiv  Detail & Related papers  (2023-04-04T16:14:39Z)
• Learning with Multiclass AUC: Theory and Algorithms [141.63211412386283]
  Area under the ROC curve (AUC) is a well-known ranking metric for problems such as imbalanced learning and recommender systems. In this paper, we start an early trial to consider the problem of learning multiclass scoring functions via optimizing multiclass AUC metrics.
  arXiv  Detail & Related papers  (2021-07-28T05:18:10Z)
• Exploring Complementary Strengths of Invariant and Equivariant Representations for Few-Shot Learning [96.75889543560497]
  In many real-world problems, collecting a large number of labeled samples is infeasible. Few-shot learning is the dominant approach to address this issue, where the objective is to quickly adapt to novel categories in presence of a limited number of samples. We propose a novel training mechanism that simultaneously enforces equivariance and invariance to a general set of geometric transformations.
  arXiv  Detail & Related papers  (2021-03-01T21:14:33Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.