# Big-model Driven Few-shot Continual Learning

arXiv: https://arxiv.org/abs/2309.00862 · HTML: https://mlsanity.com/paper/2309.00862/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 27 of its 40 references that are in the map.
- First posted on arXiv 2 Sep 2023.

## Builds on (most cited first, 27 of 27)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [iCaRL: Incremental Classifier and Representation Learning](https://mlsanity.com/paper/1611.07725/) (2016)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [CLIP-Adapter: Better Vision-Language Models with Feature Adapters](https://mlsanity.com/paper/2110.04544/) (2021)
- [End-to-End Incremental Learning](https://mlsanity.com/paper/1807.09536/) (2018)
- [Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2004.10956/) (2020)
- [Meta-Learning Representations for Continual Learning](https://mlsanity.com/paper/1905.12588/) (2019)
- [Few-Shot Incremental Learning with Continually Evolved Classifiers](https://mlsanity.com/paper/2104.03047/) (2021)
- [Negative Margin Matters: Understanding Margin in Few-shot Classification](https://mlsanity.com/paper/2003.12060/) (2020)
- [Forward Compatible Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2203.06953/) (2022)
- [Neural Collapse Inspired Feature-Classifier Alignment for Few-Shot Class Incremental Learning](https://mlsanity.com/paper/2302.03004/) (2023)
- [Semantic-aware Knowledge Distillation for Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2103.04059/) (2021)
- [Preventing Zero-Shot Transfer Degradation in Continual Learning of Vision-Language Models](https://mlsanity.com/paper/2303.06628/) (2023)
- [Self-Promoted Prototype Refinement for Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2107.08918/) (2021)
- [Constrained Few-shot Class-incremental Learning](https://mlsanity.com/paper/2203.16588/) (2022)
- [Few-Shot Class-Incremental Learning from an Open-Set Perspective](https://mlsanity.com/paper/2208.00147/) (2022)
- [CLIP model is an Efficient Continual Learner](https://mlsanity.com/paper/2210.03114/) (2022)
- [Don't Stop Learning: Towards Continual Learning for the CLIP Model](https://mlsanity.com/paper/2207.09248/) (2022)
- [Few-Shot Lifelong Learning](https://mlsanity.com/paper/2103.00991/) (2021)
- [CLIP-guided Prototype Modulating for Few-shot Action Recognition](https://mlsanity.com/paper/2303.02982/) (2023)
- [S3C: Self-Supervised Stochastic Classifiers for Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2307.02246/) (2023)

## Abstract (arXiv)

Few-shot continual learning (FSCL) has attracted intensive attention and achieved some advances in recent years, but now it is difficult to again make a big stride in accuracy due to the limitation of only few-shot incremental samples. Inspired by distinctive human cognition ability in life learning, in this work, we propose a novel Big-model driven Few-shot Continual Learning (B-FSCL) framework to gradually evolve the model under the traction of the world's big-models (like human accumulative knowledge). Specifically, we perform the big-model driven transfer learning to leverage the powerful encoding capability of these existing big-models, which can adapt the continual model to a few of newly added samples while avoiding the over-fitting problem. Considering that the big-model and the continual model may have different perceived results for the identical images, we introduce an instance-level adaptive decision mechanism to provide the high-level flexibility cognitive support adjusted to varying samples. In turn, the adaptive decision can be further adopted to optimize the parameters of the continual model, performing the adaptive distillation of big-model's knowledge information. Experimental results of our proposed B-FSCL on three popular datasets (including CIFAR100, minilmageNet and CUB200) completely surpass all state-of-the-art FSCL methods.