Few-Shot Few-Shot Learning and the role of Spatial Attention
원문 초록
Few-shot learning is often motivated by the ability of humans to learn new tasks from few examples. However, standard few-shot classification benchmarks assume that the representation is learned on a limited amount of base class data, ignoring the amount of prior knowledge that a human may have accumulated before learning new tasks. At the same time, even if a powerful representation is available, it may happen in some domain that base class data are limited or non-existent. This motivates us to study a problem where the representation is obtained from a classifier pre-trained on a large-scale dataset of a different domain, assuming no access to its training process, while the base class data are limited to few examples per class and their role is to adapt the representation to the domain at hand rather than learn from scratch. We adapt the representation in two stages, namely on the few base class data if available and on the even fewer data of new tasks. In doing so, we obtain from the pre-trained classifier a spatial attention map that allows focusing on objects and suppressing background clutter. This is important in the new problem, because when base class data are few, the network cannot learn where to focus implicitly. We also show that a pre-trained network may be easily adapted to novel classes, without meta-learning.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
MISE: Meta-knowledge Inheritance for Social Media-Based Stressor Estimation
DRESS: Disentangled Representation-based Self-Supervised Meta-Learning for Diverse Tasks
FACE: Few-shot Adapter with Cross-view Fusion for Cross-subject EEG Emotion Recognition
Few-Shot Learning for Industrial Time Series: A Comparative Analysis Using the Example of Screw-Fastening Process Monitoring
Hyperbolic Dual Feature Augmentation for Open-Environment
Adaptive Clipping for Privacy-Preserving Few-Shot Learning: Enhancing Generalization with Limited Data
토론
이 논문과 연결된 포럼 글이 아직 없습니다.