Selective Backpropagation for Efficient Few-Shot Class-Incremental Learning

cs.LG, cs.AI, cs.CV

Submitted: 2026-10-02

Updated: 2026-10-02

Code: https://github.com/PaInt-Lab/sbp-main-public

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Sources

• A Closer Look at Few-shot Classification
• Anatomy of Catastrophic Forgetting: Hidden Representations and Task Semantics
• Progressive Neural Networks
• Compositional Few-Shot Class-Incremental Learning

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks