홈 › Papers

Incremental Few-Shot Meta-Learning via Indirect Discriminant Alignment

2020-08-01 · ECCV 2020 8 · Qing Liu, Orchid Majumder, Alessandro Achille, Avinash Ravichandran, Rahul Bhotika, Stefano Soatto

We propose a method to train a model so it can learn new classification tasks while improving with each task solved. This amounts to combining meta-learning with incremental learning. Different tasks can have disjoint classes, so one cannot directly align different classifiers as done in model distillation. On the other hand, simply aligning features shared by all classes does not allow the base model sufficient flexibility to evolve to solve new tasks. We therefore indirectly align features relative to a minimal set of anchor classes. Such indirect discriminant alignment (IDA) adapts a new model to old classes without the need to re-process old data, while leaving maximum flexibility for the model to adapt to new tasks. This process enables incrementally improving the model by processing multiple learning episodes, each representing a different learning task, even with few training examples. Experiments on few-shot learning benchmarks show that this incremental approach performs favorably compared to training the model with the entire dataset at once.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Few-Shot Learning Incremental Learning Meta-Learning

Incremental Meta-Learning via Indirect Discriminant Alignment

2020-02-11 · Qing Liu, Orchid Majumder, Alessandro Achille, Avinash Ravichandran 외

Majority of the modern meta-learning methods for few-shot classification tasks operate in two phases: a meta-training phase where the meta-learner learns a generic representation by solving multiple few-shot tasks sample…

Incremental Learning Meta-Learning

Neural Collapse Inspired Feature-Classifier Alignment for Few-Shot Class-Incremental Learning

2023-02-02 · ICLR 2023 2 · Yibo Yang, Haobo Yuan, Xiangtai Li, Zhouchen Lin 외

Few-shot class-incremental learning (FSCIL) has been a challenging problem as only a few training samples are accessible for each novel class in the new sessions. Finetuning the backbone or adjusting the classifier proto…

class-incremental learning Class Incremental Learning Few-Shot Class-Incremental Learning Incremental Learning

Unlocking Zero-Shot Geospatial Reasoning via Indirect Rewards

2025-09-29 · Chenhui Xu, Fuxun Yu, Michael J. Bianco, Jacob Kovarskiy 외 arxiv

Training robust reasoning vision-language models (VLMs) in rare domains (such as geospatial) is fundamentally constrained by supervision scarcity. While raw geospatial imagery is abundant, the amount of task-direct super…

Reinforcement Learning

Neural Collapse Inspired Feature-Classifier Alignment for Few-Shot Class Incremental Learning

2023-02-06 · Yibo Yang, Haobo Yuan, Xiangtai Li, Zhouchen Lin 외

class-incremental learning Class Incremental Learning Few-Shot Class-Incremental Learning Incremental Learning

MetaFSCIL: A Meta-Learning Approach for Few-Shot Class Incremental Learning

2022-01-01 · CVPR 2022 1 · Zhixiang Chi, Li Gu, Huan Liu, Yang Wang 외

In this paper, we tackle the problem of few-shot class incremental learning (FSCIL). FSCIL aims to incrementally learn new classes with only a few samples in each class. Most existing methods only consider the increm…

class-incremental learning Class Incremental Learning Few-Shot Class-Incremental Learning Incremental Learning+1