paper-with-me

홈 › Papers

Task Adaptive Feature Transformation for One-Shot Learning

2023-04-13 · Imtiaz Masud Ziko, Freddy Lecue, Ismail Ben Ayed

We introduce a simple non-linear embedding adaptation layer, which is fine-tuned on top of fixed pre-trained features for one-shot tasks, improving significantly transductive entropy-based inference for low-shot regimes. Our norm-induced transformation could be understood as a re-parametrization of the feature space to disentangle the representations of different classes in a task specific manner. It focuses on the relevant feature dimensions while hindering the effects of non-relevant dimensions that may cause overfitting in a one-shot setting. We also provide an interpretation of our proposed feature transformation in the basic case of few-shot inference with K-means clustering. Furthermore, we give an interesting bound-optimization link between K-means and entropy minimization. This emphasizes why our feature transformation is useful in the context of entropy minimization. We report comprehensive experiments, which show consistent improvements over a variety of one-shot benchmarks, outperforming recent state-of-the-art methods.

📄 PDF Abstract BibTeX arXiv:2304.06832

Code (0)

등록된 구현이 없습니다.

Tasks

One-Shot Learning

Similar Papers 제목 키워드 기반

Task-Adaptive Feature Transformer for Few-Shot Segmentation

2020-10-22 · Jun Seo, Young-Hyun Park, Sung-Whan Yoon, Jaekyun Moon

Few-shot learning allows machines to classify novel classes using only a few labeled samples. Recently, few-shot segmentation aiming at semantic segmentation on low sample data has also seen great interest. In this paper…

Few-Shot LearningSegmentationSemantic Segmentation

Task-Adaptive Feature Transformer with Semantic Enrichment for Few-Shot Segmentation

2022-02-14 · Jun Seo, Young-Hyun Park, Sung Whan Yoon, Jaekyun Moon

Few-shot learning allows machines to classify novel classes using only a few labeled samples. Recently, few-shot segmentation aiming at semantic segmentation on low sample data has also seen great interest. In this paper…

Few-Shot LearningSegmentationSemantic Segmentation

Meta-OLE: Meta-learned Orthogonal Low-Rank Embedding

2021-09-29 · Ze Wang, Yue Lu, Qiang Qiu

We introduce Meta-OLE, a new geometry-regularized method for fast adaptation to novel tasks in few-shot image classification. The proposed method learns to adapt for each few-shot classification task a feature space with…

ClassificationFew-Shot Image Classificationimage-classificationImage Classification+1

TART: Improved Few-shot Text Classification Using Task-Adaptive Reference Transformation

2023-06-03 · Shuo Lei, Xuchao Zhang, Jianfeng He, Fanglan Chen 외

Meta-learning has emerged as a trending technique to tackle few-shot text classification and achieve state-of-the-art performance. However, the performance of existing approaches heavily depends on the inter-class varian…

Few-Shot Text ClassificationMeta-Learningtext-classificationText Classification

Fast Task Adaptation for Few-Shot Learning

2019-09-25 · Yingying Zhang, Qiaoyong Zhong, Di Xie, ShiLiang Pu

Few-shot classification is a challenging task due to the scarcity of training examples for each class. The key lies in generalization of prior knowledge learned from large-scale base classes and fast adaptation of the cl…

Few-Shot Learning