Generalization Bounds for Few-Shot Transfer Learning with Pretrained Classifiers
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Few-Shot LearningGeneralization BoundsTransfer LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
On the Role of Generalization in Transferability of Adversarial Examples
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 BoundsGentle robustness implies Generalization
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
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 BoundsZero-shot Cross-lingual Transfer is Under-specified Optimization
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 TransferPerch 2.0 transfers 'whale' to underwater tasks
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