DeepAI AI Chat
Log In Sign Up

Diagnosing and Remedying Shot Sensitivity with Cosine Few-Shot Learners

by   Davis Wertheimer, et al.
cornell university

Few-shot recognition involves training an image classifier to distinguish novel concepts at test time using few examples (shot). Existing approaches generally assume that the shot number at test time is known in advance. This is not realistic, and the performance of a popular and foundational method has been shown to suffer when train and test shots do not match. We conduct a systematic empirical study of this phenomenon. In line with prior work, we find that shot sensitivity is broadly present across metric-based few-shot learners, but in contrast to prior work, larger neural architectures provide a degree of built-in robustness to varying test shot. More importantly, a simple, previously known but greatly overlooked class of approaches based on cosine distance consistently and greatly improves robustness to shot variation, by removing sensitivity to sample noise. We derive cosine alternatives to popular and recent few-shot classifiers, broadening their applicability to realistic settings. These cosine models consistently improve shot-robustness, outperform prior shot-robust state of the art, and provide competitive accuracy on a range of benchmarks and architectures, including notable gains in the very-low-shot regime.


page 17

page 18

page 19

page 20

page 21

page 23

page 24

page 27


On the Importance of Firth Bias Reduction in Few-Shot Classification

Learning accurate classifiers for novel categories from very few example...

Finding Task-Relevant Features for Few-Shot Learning by Category Traversal

Few-shot learning is an important area of research. Conceptually, humans...

Incremental Few-Shot Instance Segmentation

Few-shot instance segmentation methods are promising when labeled traini...

On the Relation between Sensitivity and Accuracy in In-context Learning

In-context learning (ICL) suffers from oversensitivity to the prompt, wh...

Dynamic Few-Shot Visual Learning without Forgetting

The human visual system has the remarkably ability to be able to effortl...

A Maximum Log-Likelihood Method for Imbalanced Few-Shot Learning Tasks

Few-shot learning is a rapidly evolving area of research in machine lear...

True Few-Shot Learning with Language Models

Pretrained language models (LMs) perform well on many tasks even when le...