paper-with-me

Papers

Generalization Bounds for Few-Shot Transfer Learning with Pretrained Classifiers

2022-12-23 · Tomer Galanti, András György, Marcus Hutter

We study the ability of foundation models to learn representations for classification that are transferable to new, unseen classes. Recent results in the literature show that representations learned by a single classifier over many classes are competitive on few-shot learning problems with representations learned by special-purpose algorithms designed for such problems. We offer a theoretical explanation for this behavior based on the recently discovered phenomenon of class-feature-variability collapse, that is, that during the training of deep classification networks the feature embeddings of samples belonging to the same class tend to concentrate around their class means. More specifically, we show that the few-shot error of the learned feature map on new classes (defined as the classification error of the nearest class-center classifier using centers learned from a small number of random samples from each new class) is small in case of class-feature-variability collapse, under the assumption that the classes are selected independently from a fixed distribution. This suggests that foundation models can provide feature maps that are transferable to new downstream tasks, even with very few samples; to our knowledge, this is the first performance bound for transfer-learning that is non-vacuous in the few-shot setting.

📄 PDF Abstract BibTeX arXiv:2212.12532

Code (0)

등록된 구현이 없습니다.

Tasks

Few-Shot LearningGeneralization BoundsTransfer Learning

Methods 이 논문이 사용한 방법론

Test 설명 없음

Similar Papers 제목 키워드 기반

On the Role of Generalization in Transferability of Adversarial Examples

2022-06-18 · Yilin Wang, Farzan Farnia

Black-box adversarial attacks designing adversarial examples for unseen neural networks (NNs) have received great attention over the past years. While several successful black-box attack schemes have been proposed in the…

Generalization Bounds

Gentle robustness implies Generalization

2024-12-09 · Khoat Than, Dat Phan, Giang Vu

Robustness and generalization ability of machine learning models are of utmost importance in various application domains. There is a wide interest in efficient ways to analyze those properties. One important direction is…

Margin-Based Generalization Lower Bounds for Boosted Classifiers

2019-09-27 · NeurIPS 2019 12 · Allan Grønlund, Lior Kamma, Kasper Green Larsen, Alexander Mathiasen 외

Boosting is one of the most successful ideas in machine learning. The most well-accepted explanations for the low generalization error of boosting algorithms such as AdaBoost stem from margin theory. The study of margins…

Generalization Bounds

Zero-shot Cross-lingual Transfer is Under-specified Optimization

2022-07-12 · RepL4NLP (ACL) 2022 5 · Shijie Wu, Benjamin Van Durme, Mark Dredze

Pretrained multilingual encoders enable zero-shot cross-lingual transfer, but often produce unreliable models that exhibit high performance variance on the target language. We postulate that this high variance results fr…

Cross-Lingual TransferZero-Shot Cross-Lingual Transfer

Perch 2.0 transfers 'whale' to underwater tasks

2025-12-02 · Andrea Burns, Lauren Harrell, Bart van Merriënboer, Vincent Dumoulin 외 arxiv

Perch 2.0 is a supervised bioacoustics foundation model pretrained on 14,597 species, including birds, mammals, amphibians, and insects, and has state-of-the-art performance on multiple benchmarks. Given that Perch 2.0 i…

Transfer Learning