Mamba-FSCIL: Dynamic Adaptation with Selective State Space Model for Few-Shot Class-Incremental Learning

• URL: http://arxiv.org/abs/2407.06136v2
• Date: Wed, 21 Aug 2024 15:32:26 GMT
• Title: Mamba-FSCIL: Dynamic Adaptation with Selective State Space Model for Few-Shot Class-Incremental Learning
• Authors: Xiaojie Li, Yibo Yang, Jianlong Wu, Bernard Ghanem, Liqiang Nie, Min Zhang,
• Abstract summary: Few-shot class-incremental learning (FSCIL) confronts the challenge of integrating new classes into a model with minimal training samples. Traditional methods widely adopt static adaptation relying on a fixed parameter space to learn from data that arrive sequentially. We propose a dual selective SSM projector that dynamically adjusts the projection parameters based on the intermediate features for dynamic adaptation.
• Score: 113.89327264634984
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Few-shot class-incremental learning (FSCIL) confronts the challenge of integrating new classes into a model with minimal training samples while preserving the knowledge of previously learned classes. Traditional methods widely adopt static adaptation relying on a fixed parameter space to learn from data that arrive sequentially, prone to overfitting to the current session. Existing dynamic strategies require the expansion of the parameter space continually, leading to increased complexity. In this study, we explore the potential of Selective State Space Models (SSMs) for FSCIL, leveraging its dynamic weights and strong ability in sequence modeling to address these challenges. Concretely, we propose a dual selective SSM projector that dynamically adjusts the projection parameters based on the intermediate features for dynamic adaptation. The dual design enables the model to maintain the robust features of base classes, while adaptively learning distinctive feature shifts for novel classes. Additionally, we develop a class-sensitive selective scan mechanism to guide dynamic adaptation. It minimizes the disruption to base-class representations caused by training on novel data, and meanwhile, forces the selective scan to perform in distinct patterns between base and novel classes. Experiments on miniImageNet, CUB-200, and CIFAR-100 demonstrate that our framework outperforms the existing state-of-the-art methods. The code is available at \url{https://github.com/xiaojieli0903/Mamba-FSCIL}.

Related papers

• Collaborative Static-Dynamic Teaching: A Semi-Supervised Framework for Stripe-Like Space Target Detection [2.9133687889451023]
  Stripe-like space target detection is crucial for space situational awareness. Traditional unsupervised methods often fail in low signal-to-noise ratio and variable stripe-like space targets scenarios. We introduce an innovative Collaborative Static-Dynamic Teacher (CSDT) SSL framework, which includes static and dynamic teacher models as well as a student model. We also present MSSA-Net, a novel SSTD network featuring a multi-scale dual-path convolution (MDPC) block and a feature map weighted attention (FMWA) block.
  arXiv  Detail & Related papers  (2024-08-09T12:33:27Z)
• Dynamic Feature Learning and Matching for Class-Incremental Learning [20.432575325147894]
  Class-incremental learning (CIL) has emerged as a means to learn new classes without catastrophic forgetting of previous classes. We propose the Dynamic Feature Learning and Matching (DFLM) model in this paper. Our proposed model achieves significant performance improvements over existing methods.
  arXiv  Detail & Related papers  (2024-05-14T12:17:19Z)
• Expandable Subspace Ensemble for Pre-Trained Model-Based Class-Incremental Learning [65.57123249246358]
  We propose ExpAndable Subspace Ensemble (EASE) for PTM-based CIL. We train a distinct lightweight adapter module for each new task, aiming to create task-specific subspaces. Our prototype complement strategy synthesizes old classes' new features without using any old class instance.
  arXiv  Detail & Related papers  (2024-03-18T17:58:13Z)
• Online Calibration of Deep Learning Sub-Models for Hybrid Numerical Modeling Systems [34.50407690251862]
  We present an efficient and practical online learning approach for hybrid systems. We demonstrate that the method, called EGA for Euler Gradient Approximation, converges to the exact gradients in the limit of infinitely small time steps. Results show significant improvements over offline learning, highlighting the potential of end-to-end online learning for hybrid modeling.
  arXiv  Detail & Related papers  (2023-11-17T17:36:26Z)
• Sparse Modular Activation for Efficient Sequence Modeling [94.11125833685583]
  Recent models combining Linear State Space Models with self-attention mechanisms have demonstrated impressive results across a range of sequence modeling tasks. Current approaches apply attention modules statically and uniformly to all elements in the input sequences, leading to sub-optimal quality-efficiency trade-offs. We introduce Sparse Modular Activation (SMA), a general mechanism enabling neural networks to sparsely activate sub-modules for sequence elements in a differentiable manner.
  arXiv  Detail & Related papers  (2023-06-19T23:10:02Z)
• Switchable Representation Learning Framework with Self-compatibility [50.48336074436792]
  We propose a Switchable representation learning Framework with Self-Compatibility (SFSC) SFSC generates a series of compatible sub-models with different capacities through one training process. SFSC achieves state-of-the-art performance on the evaluated datasets.
  arXiv  Detail & Related papers  (2022-06-16T16:46:32Z)
• FOSTER: Feature Boosting and Compression for Class-Incremental Learning [52.603520403933985]
  Deep neural networks suffer from catastrophic forgetting when learning new categories. We propose a novel two-stage learning paradigm FOSTER, empowering the model to learn new categories adaptively.
  arXiv  Detail & Related papers  (2022-04-10T11:38:33Z)
• Incremental Few-Shot Learning via Implanting and Compressing [13.122771115838523]
  Incremental Few-Shot Learning requires a model to continually learn novel classes from only a few examples. We propose a two-step learning strategy referred to as textbfImplanting and textbfCompressing. Specifically, in the textbfImplanting step, we propose to mimic the data distribution of novel classes with the assistance of data-abundant base set. In the textbf step, we adapt the feature extractor to precisely represent each novel class for enhancing intra-class compactness.
  arXiv  Detail & Related papers  (2022-03-19T11:04:43Z)
• Trajectory-wise Multiple Choice Learning for Dynamics Generalization in Reinforcement Learning [137.39196753245105]
  We present a new model-based reinforcement learning algorithm that learns a multi-headed dynamics model for dynamics generalization. We incorporate context learning, which encodes dynamics-specific information from past experiences into the context latent vector. Our method exhibits superior zero-shot generalization performance across a variety of control tasks, compared to state-of-the-art RL methods.
  arXiv  Detail & Related papers  (2020-10-26T03:20:42Z)

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.