Shot Transfer Learning

Few-shot transfer learning aims to adapt pre-trained models to new tasks with limited labeled data, leveraging knowledge from a source domain to improve performance and efficiency in the target domain. Current research focuses on developing novel architectures and algorithms, including those based on prototype networks, hypernetworks, and graph neural networks, to enhance sample efficiency and robustness across diverse applications. This approach is particularly significant for resource-constrained scenarios and personalized applications, offering substantial improvements in areas like natural language processing, computer vision, and reinforcement learning by reducing the need for extensive data annotation and training. The resulting models are more adaptable and efficient, leading to advancements in various fields.

Papers

December 24, 2024

Text-Aware Adapter for Few-Shot Keyword Spotting
Youngmoon Jung, Jinyoung Lee, Seungjin Lee, Myunghun Jung, Yong-Hyeok Lee, Hoon-Young Cho
Keyword Spotting Textual Feature Pre Trained Text Shot Transfer Learning

July 21, 2024

Few-Shot Transfer Learning for Individualized Braking Intent Detection on Neuromorphic Hardware
Nathan Lutes, Venkata Sriram Siddhardh Nadendla, K. Krishnamurthy
Transfer Learning Neuromorphic Hardware Convolutional Spiking Neural Network Shot Transfer Learning

June 20, 2024

Robust Few-shot Transfer Learning for Knowledge Base Question Answering with Unanswerable Questions
Riya Sawhney, Indrajit Bhattacharya, Mausam
Unanswerable Question Shot Transfer Learning KBQA Model Shot Transfer

November 15, 2023

Few-shot Transfer Learning for Knowledge Base Question Answering: Fusing Supervised Models with In-Context Learning
Mayur Patidar, Riya Sawhney, Avinash Singh, Biswajit Chatterjee, Mausam, Indrajit Bhattacharya
Context Learning Supervised Learning Knowledge Retrieval Shot in Context Learning Knowledge Base Question Answering Shot Transfer Learning

October 18, 2023

Prototype-based HyperAdapter for Sample-Efficient Multi-task Tuning
Hao Zhao, Jie Fu, Zhaofeng He
Pre Trained Language Model Parameter Efficient Fine Tuning Dense Retriever Prototype Adaptation Shot Transfer Learning

June 12, 2023

Online Prototype Alignment for Few-shot Policy Transfer
Qi Yi, Rui Zhang, Shaohui Peng, Jiaming Guo, Yunkai Gao, Kaizhao Yuan, Ruizhi Chen, Siming Lan, Xing Hu, Zidong Du, Xishan Zhang, Qi Guo, Yunji Chen
Reinforcement Learning Domain Adaptation Mapping Function Prototype Alignment Shot Transfer Learning

October 19, 2022

CPL: Counterfactual Prompt Learning for Vision and Language Models
Xuehai He, Diji Yang, Weixi Feng, Tsu-Jui Fu, Arjun Akula, Varun Jampani, Pradyumna Narayana, Sugato Basu, William Yang Wang, Xin Eric Wang
Language Model Contrastive Learning Vision Paper Prompt Based Learning Learnable Prompt Shot Transfer Learning Prompt Representation

June 17, 2022

FiT: Parameter Efficient Few-shot Transfer Learning for Personalized and Federated Image Classification
Aliaksandra Shysheya, John Bronskill, Massimiliano Patacchiola, Sebastian Nowozin, Richard E Turner
Transfer Learning Parameter Efficient Personalized Subject Federated Image Classification Modern Deep Learning Better FiT Shot Transfer Learning

March 9, 2022

Rethinking Task Sampling for Few-shot Vision-Language Transfer Learning
Zhenhailong Wang, Hang Yu, Manling Li, Han Zhao, Heng Ji
Shot Learning Shot Transfer Learning Task Sampling Shot Vision Language

January 29, 2022

Few-Shot Transfer Learning for Device-Free Fingerprinting Indoor Localization
Bing-Jia Chen, Ronald Y. Chang
Convolutional Neural Network Transfer Learning Shot Transfer Learning Device Free

January 27, 2022

Few-shot Transfer Learning for Holographic Image Reconstruction using a Recurrent Neural Network
Luzhe Huang, Xilin Yang, Tairan Liu, Aydogan Ozcan
Recurrent Neural Network Digital Holography Shot Transfer Learning

December 30, 2021

THE Benchmark: Transferable Representation Learning for Monocular Height Estimation
Zhitong Xiong, Wei Huang, Jingtao Hu, Xiao Xiang Zhu
New Benchmark Large Scale Synthetic Dataset Height Estimation Transferable Visual Shot Transfer Learning

December 12, 2021

Few-Shot Out-of-Domain Transfer Learning of Natural Language Explanations in a Label-Abundant Setup
Yordan Yordanov, Vid Kocijan, Thomas Lukasiewicz, Oana-Maria Camburu
Transfer Learning Natural Language Explanation Shot Transfer Learning Shot Out of Distribution Detection Higher NLE Quality

Shot Transfer Learning

Papers

Text-Aware Adapter for Few-Shot Keyword Spotting

Few-Shot Transfer Learning for Individualized Braking Intent Detection on Neuromorphic Hardware

Robust Few-shot Transfer Learning for Knowledge Base Question Answering with Unanswerable Questions

Few-shot Transfer Learning for Knowledge Base Question Answering: Fusing Supervised Models with In-Context Learning

Prototype-based HyperAdapter for Sample-Efficient Multi-task Tuning

Online Prototype Alignment for Few-shot Policy Transfer

CPL: Counterfactual Prompt Learning for Vision and Language Models

FiT: Parameter Efficient Few-shot Transfer Learning for Personalized and Federated Image Classification

Rethinking Task Sampling for Few-shot Vision-Language Transfer Learning

Few-Shot Transfer Learning for Device-Free Fingerprinting Indoor Localization

Few-shot Transfer Learning for Holographic Image Reconstruction using a Recurrent Neural Network

THE Benchmark: Transferable Representation Learning for Monocular Height Estimation

Few-Shot Out-of-Domain Transfer Learning of Natural Language Explanations in a Label-Abundant Setup