Shot Learning

Few-shot learning (FSL) aims to train machine learning models that can effectively learn new concepts or tasks from only a small number of examples, addressing the limitations of traditional methods requiring massive datasets. Current research focuses on improving model robustness to noisy data and heterogeneous tasks, exploring architectures like prototypical networks and meta-learning algorithms, and leveraging large vision-language models and external memory for enhanced performance. This field is crucial for advancing AI in data-scarce domains like medical image analysis and personalized medicine, where acquiring large labeled datasets is often impractical or impossible. The development of efficient and reliable FSL methods has significant implications for various applications, including object detection, natural language processing, and other areas where labeled data is limited.

Papers

October 30, 2022

October 25, 2022

October 23, 2022

TAPE: Assessing Few-shot Russian Language Understanding
Ekaterina Taktasheva, Tatiana Shavrina, Alena Fenogenova, Denis Shevelev, Nadezhda Katricheva, Maria Tikhonova, Albina Akhmetgareeva, Oleg Zinkevich, Anastasiia Bashmakova, Svetlana Iordanskaia, Alena Spiridonova, Valentina Kurenshchikova, Ekaterina Artemova, Vladislav Mikhailov
Adversarial Attack Shot Learning NLP Task Level Perturbation Shot Natural Language Understanding Kinesiology Tape

October 21, 2022

Graph Few-shot Learning with Task-specific Structures
Song Wang, Chen Chen, Jundong Li
Graph Neural Network Shot Learning Graph Learning Task Task Specific Structure

October 19, 2022

Prompting through Prototype: A Prototype-based Prompt Learning on Pretrained Vision-Language Models
Yue Zhang, Hongliang Fei, Dingcheng Li, Tan Yu, Ping Li
Vision Language Model Pre Trained Shot Learning Visual Prototype Shot Recognition

October 18, 2022

Few-Shot Learning of Compact Models via Task-Specific Meta Distillation
Yong Wu, Shekhor Chanda, Mehrdad Hosseinzadeh, Zhi Liu, Yang Wang
LeArning Abstract Shot Learning Meta Training Shot Image Classification Compact Model Meta Distillation

October 17, 2022

HCL-TAT: A Hybrid Contrastive Learning Method for Few-shot Event Detection with Task-Adaptive Threshold
Ruihan Zhang, Wei Wei, Xian-Ling Mao, Rui Fang, Dangyang Chen
Contrastive Learning Shot Learning Efficient Hybrid Event Detection Discriminative Representation Threshold Optimization Shot Event Detection

October 14, 2022

Flame-state monitoring based on very low number of visible or infrared images via few-shot learning
Ruiyuan Kang, Panos Liatsis, Dimitrios C. Kyritsis
Shot Learning Richer RGB Infrared Feature Infrared Image Small Number

October 12, 2022

October 11, 2022

October 7, 2022

October 5, 2022

BaseTransformers: Attention over base data-points for One Shot Learning
Mayug Maniparambil, Kevin McGuinness, Noel O'Connor
Shot Learning Human Attention Feature Representation Instance Representation Standard Datasets Base Class Feature Space

October 1, 2022

Offline Handwritten Amharic Character Recognition Using Few-shot Learning
Mesay Samuel, Lars Schmidt-Thieme, DP Sharma, Abiot Sinamo, Abey Bruck
Machine Learning Image Classification Shot Learning Mini ImageNet Offline Handwritten Amharic Character Recognition

September 30, 2022

Contrastive Graph Few-Shot Learning
Chunhui Zhang, Hongfu Liu, Jundong Li, Yanfang Ye, Chuxu Zhang
LeArning Abstract Contrastive Learning Shot Learning Contrastive Graph Contrastive Distillation Shot Graph Deep Graph Model

September 28, 2022

Less is More: Rethinking Few-Shot Learning and Recurrent Neural Nets
Deborah Pereg, Martin Villiger, Brett Bouma, Polina Golland
LeArning Abstract Recurrent Neural Network Shot Learning Speckle Reduction

Shot Learning

Papers

Few-Shot Classification of Skin Lesions from Dermoscopic Images by Meta-Learning Representative Embeddings

Alleviating the Sample Selection Bias in Few-shot Learning by Removing Projection to the Centroid

Weakly Supervised Data Augmentation Through Prompting for Dialogue Understanding

Better Few-Shot Relation Extraction with Label Prompt Dropout

TAPE: Assessing Few-shot Russian Language Understanding

Graph Few-shot Learning with Task-specific Structures

Prompting through Prototype: A Prototype-based Prompt Learning on Pretrained Vision-Language Models

Few-Shot Learning of Compact Models via Task-Specific Meta Distillation

HCL-TAT: A Hybrid Contrastive Learning Method for Few-shot Event Detection with Task-Adaptive Threshold

Flame-state monitoring based on very low number of visible or infrared images via few-shot learning

A Unified Framework with Meta-dropout for Few-shot Learning

Semantic Cross Attention for Few-shot Learning

CLIP-Fields: Weakly Supervised Semantic Fields for Robotic Memory

ME-D2N: Multi-Expert Domain Decompositional Network for Cross-Domain Few-Shot Learning

Unsupervised Few-shot Learning via Deep Laplacian Eigenmaps

AI-Driven Road Maintenance Inspection v2: Reducing Data Dependency & Quantifying Road Damage

BaseTransformers: Attention over base data-points for One Shot Learning

Offline Handwritten Amharic Character Recognition Using Few-shot Learning

Contrastive Graph Few-Shot Learning

Less is More: Rethinking Few-Shot Learning and Recurrent Neural Nets