paper-with-me

홈 › Papers

TapNet: Neural Network Augmented with Task-Adaptive Projection for Few-Shot Learning

2019-05-16 · Sung Whan Yoon, Jun Seo, Jaekyun Moon

Handling previously unseen tasks after given only a few training examples continues to be a tough challenge in machine learning. We propose TapNets, neural networks augmented with task-adaptive projection for improved few-shot learning. Here, employing a meta-learning strategy with episode-based training, a network and a set of per-class reference vectors are learned across widely varying tasks. At the same time, for every episode, features in the embedding space are linearly projected into a new space as a form of quick task-specific conditioning. The training loss is obtained based on a distance metric between the query and the reference vectors in the projection space. Excellent generalization results in this way. When tested on the Omniglot, miniImageNet and tieredImageNet datasets, we obtain state of the art classification accuracies under various few-shot scenarios.

📄 PDF Abstract BibTeX arXiv:1905.06549

Code (1)

istarjun/TapNet 공식 구현

Tasks

Few-Shot LearningMeta-Learning

Similar Papers 제목 키워드 기반

Few-shot Slot Tagging with Collapsed Dependency Transfer and Label-enhanced Task-adaptive Projection Network

2020-06-10 · ACL 2020 6 · Yutai Hou, Wanxiang Che, Yongkui Lai, Zhihan Zhou 외

In this paper, we explore the slot tagging with only a few labeled support sentences (a.k.a. few-shot). Few-shot slot tagging faces a unique challenge compared to the other few-shot classification problems as it calls fo…

Few-Shot LearningGeneral Classification

TapNet: The Design, Training, Implementation, and Applications of a Multi-Task Learning CNN for Off-Screen Mobile Input

2021-02-18 · Michael Xuelin Huang, Yang Li, Nazneen Nazneen, Alexander Chao 외

To make off-screen interaction without specialized hardware practical, we investigate using deep learning methods to process the common built-in IMU sensor (accelerometers and gyroscopes) on mobile phones into a useful s…

Transformer-Based Dual-Optical Attention Fusion Crowd Head Point Counting and Localization Network

2025-05-11 · Fei Zhou, Yi Li, Mingqing Zhu

In this paper, the dual-optical attention fusion crowd head point counting model (TAPNet) is proposed to address the problem of the difficulty of accurate counting in complex scenes such as crowd dense occlusion and low …

Crowd CountingData Augmentation

OmniAI: A Surface-Adaptive Aerial Projection Interface for Human--Drone Interaction

2026-08-01 · Nikita Kuzmin, Yuhua Jin, Georgii Demianchuk, Mariya Lezina 외 arxiv

Drones in human environments often lack spatially grounded in- terfaces for situated communication. We present OmniAI, an em- bodied aerial agent that supports surface-adaptive interaction by switching projection between…

Vector Projection Network for Few-shot Slot Tagging in Natural Language Understanding

2020-09-21 · Su Zhu, Ruisheng Cao, Lu Chen, Kai Yu

Few-shot slot tagging becomes appealing for rapid domain transfer and adaptation, motivated by the tremendous development of conversational dialogue systems. In this paper, we propose a vector projection network for few-…

Few-Shot LearningNatural Language UnderstandingNERWord Embeddings