paper-with-me

홈 › Papers

One-shot Learning with Absolute Generalization

2021-05-28 · Hao Su

One-shot learning is proposed to make a pretrained classifier workable on a new dataset based on one labeled samples from each pattern. However, few of researchers consider whether the dataset itself supports one-shot learning. In this paper, we propose a set of definitions to explain what kind of datasets can support one-shot learning and propose the concept "absolute generalization". Based on these definitions, we proposed a method to build an absolutely generalizable classifier. The proposed method concatenates two samples as a new single sample, and converts a classification problem to an identity identification problem or a similarity metric problem. Experiments demonstrate that the proposed method is superior to baseline on one-shot learning datasets and artificial datasets.

📄 PDF Abstract BibTeX arXiv:2105.13559

Code (1)

qqsuhao/One-shot-Learning-with-Absolute-Genelization 공식 구현 pytorch

Tasks

One-Shot Learning

Similar Papers 제목 키워드 기반

Zero-shot Text-to-SQL Learning with Auxiliary Task

2019-08-29 · Shuaichen Chang, PengFei Liu, Yun Tang, Jing Huang 외

Recent years have seen great success in the use of neural seq2seq models on the text-to-SQL task. However, little work has paid attention to how these models generalize to realistic unseen data, which naturally raises a …

Text to SQLText-To-SQL

PromptStereo: Zero-Shot Stereo Matching via Structure and Motion Prompts

2026-03-02 · Xianqi Wang, Hao Yang, Hangtian Wang, Junda Cheng 외 arxiv

Modern stereo matching methods have leveraged monocular depth foundation models to achieve superior zero-shot generalization performance. However, most existing methods primarily focus on extracting robust features for c…

Zero-shot Generalization

Pruning as Regularization: Sensitivity-Aware One-Shot Pruning in ASR

2025-11-11 · Julian Irigoyen, Arthur Söhler, Andreas Søeborg Kirkedal arxiv

We challenge the conventional view of neural network pruning as solely a compression technique, demonstrating that one-shot magnitude pruning serves as a powerful implicit regularizer for ASR. Using Whisper-small, we com…

Network Pruning

Verbalized Representation Learning for Interpretable Few-Shot Generalization

2024-11-27 · Cheng-Fu Yang, Da Yin, WenBo Hu, Nanyun Peng 외

Humans recognize objects after observing only a few examples, a remarkable capability enabled by their inherent language understanding of the real-world environment. Developing verbalized and interpretable representation…

Language ModelingLanguage ModellingObject RecognitionRepresentation Learning

Zero-Shot Learning from scratch (ZFS): leveraging local compositional representations

2020-10-22 · Tristan Sylvain, Linda Petrini, R Devon Hjelm

Zero-shot classification is a generalization task where no instance from the target classes is seen during training. To allow for test-time transfer, each class is annotated with semantic information, commonly in the for…

General ClassificationRepresentation Learningzero-shot-classificationZero-Shot Learning