Adaptive Prototypical Networks

2022-11-22 · Manas Gogoi, Sambhavi Tiwari, Shekhar Verma

Prototypical network for Few shot learning tries to learn an embedding function in the encoder that embeds images with similar features close to one another in the embedding space. However, in this process, the support set samples for a task are embedded independently of one other, and hence, the inter-class closeness is not taken into account. Thus, in the presence of similar-looking classes in a task, the embeddings will tend to be close to each other in the embedding space and even possibly overlap in some regions, which is not desirable for classification. In this paper, we propose an approach that intuitively pushes the embeddings of each of the classes away from the others in the meta-testing phase, thereby grouping them closely based on the distinct class labels rather than only the similarity of spatial features. This is achieved by training the encoder network for classification using the support set samples and labels of the new task. Extensive experiments conducted on benchmark data sets show improvements in meta-testing accuracy when compared with Prototypical Networks and also other standard few-shot learning models.

📄 PDF Abstract BibTeX arXiv:2211.12479

Code (1)

manasgg44/improved_proto 공식 구현 pytorch

Tasks

Few-Shot Learning

APP: Adaptive Prototypical Pseudo-Labeling for Few-shot OOD Detection

2023-10-20 · Pei Wang, Keqing He, Yutao Mou, Xiaoshuai Song 외

Detecting out-of-domain (OOD) intents from user queries is essential for a task-oriented dialogue system. Previous OOD detection studies generally work on the assumption that plenty of labeled IND intents exist. In this …

Infinite Mixture Prototypes for Few-Shot Learning

2019-02-12 · Kelsey R. Allen, Evan Shelhamer, Hanul Shin, Joshua B. Tenenbaum

We propose infinite mixture prototypes to adaptively represent both simple and complex data distributions for few-shot learning. Our infinite mixture prototypes represent each class by a set of clusters, unlike existing …

Clustering Few-Shot Learning

Prototypical Calibration for Few-shot Learning of Language Models

2022-05-20 · Zhixiong Han, Yaru Hao, Li Dong, Yutao Sun 외

In-context learning of GPT-like models has been recognized as fragile across different hand-crafted templates, and demonstration permutations. In this work, we propose prototypical calibration to adaptively learn a more …

Few-Shot Learning In-Context Learning