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

June 18, 2023

June 17, 2023

Federated Few-shot Learning
Song Wang, Xingbo Fu, Kaize Ding, Chen Chen, Huiyuan Chen, Jundong Li
Shot Learning Shot Approach One Shot Federated Learning Shot Sample

June 15, 2023

June 13, 2023

June 8, 2023

EMO: Episodic Memory Optimization for Few-Shot Meta-Learning
Yingjun Du, Jiayi Shen, Xiantong Zhen, Cees G. M. Snoek
Shot Learning Meta Learning Episodic Memory BLSP Emo Shot Meta Learning Optimization Based Meta Learning

June 6, 2023

GSHOT: Few-shot Generative Modeling of Labeled Graphs
Sahil Manchanda, Shubham Gupta, Sayan Ranu, Srikanta Bedathur
Shot Learning Generative Modeling Deep Generative Unseen Graph Unlabeled Graph

June 5, 2023

Few Shot Rationale Generation using Self-Training with Dual Teachers
Aditya Srikanth Veerubhotla, Lahari Poddar, Jun Yin, György Szarvas, Sharanya Eswaran
Multi Task Learning Shot Learning Self Training Dual Teacher Self Rationalization Free Text Explanation Based Regularization

June 3, 2023

Few-Shot Open-Set Learning for On-Device Customization of KeyWord Spotting Systems
Manuele Rusci, Tinne Tuytelaars
Shot Learning Open Set Keyword Spotting Google Speech Command Open Vocabulary Keyword Spotting

June 1, 2023

Consistency-guided Prompt Learning for Vision-Language Models
Shuvendu Roy, Ali Etemad
Zero Shot Vision Language Model Shot Learning Prompt Learning

May 30, 2023

May 29, 2023

May 27, 2023

May 23, 2023

Shot Learning

Papers

Dual Adaptive Representation Alignment for Cross-domain Few-shot Learning

Channel-Spatial-Based Few-Shot Bird Sound Event Detection

Federated Few-shot Learning

Sample-Efficient Learning of Novel Visual Concepts

Few-shot bioacoustic event detection at the DCASE 2023 challenge

FLamE: Few-shot Learning from Natural Language Explanations

One-for-All: Generalized LoRA for Parameter-Efficient Fine-tuning

EMO: Episodic Memory Optimization for Few-Shot Meta-Learning

GSHOT: Few-shot Generative Modeling of Labeled Graphs

Few Shot Rationale Generation using Self-Training with Dual Teachers

Few-Shot Open-Set Learning for On-Device Customization of KeyWord Spotting Systems

Consistency-guided Prompt Learning for Vision-Language Models

SENet: A Spectral Filtering Approach to Represent Exemplars for Few-shot Learning

Task-Equivariant Graph Few-shot Learning

MT-SLVR: Multi-Task Self-Supervised Learning for Transformation In(Variant) Representations

The Rise of AI Language Pathologists: Exploring Two-level Prompt Learning for Few-shot Weakly-supervised Whole Slide Image Classification

Toward Understanding Generative Data Augmentation

Instance-based Max-margin for Practical Few-shot Recognition

Active Learning Principles for In-Context Learning with Large Language Models

Skill-Based Few-Shot Selection for In-Context Learning