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

September 28, 2022

September 24, 2022

Graph Neural Network Expressivity and Meta-Learning for Molecular Property Regression
Haitz Sáez de Ocáriz Borde, Federico Barbero
Shot Learning Meta Learning Regression Task GNN Model Molecular Property Expressive Graph Neural Network

September 21, 2022

A Few Shot Multi-Representation Approach for N-gram Spotting in Historical Manuscripts
Giuseppe De Gregorio, Sanket Biswas, Mohamed Ali Souibgui, Asma Bensalah, Josep Lladós, Alicia Fornés, Angelo Marcelli
Shot Learning Keyword Spotting Text Recognition N Gram Handwritten Text Recognition Handwritten Text Image Historical Manuscript

September 17, 2022

Few-Shot Classification with Contrastive Learning
Zhanyuan Yang, Jinghua Wang, Yingying Zhu
Contrastive Learning Classification Code Shot Learning Contrastive Learning Framework Two Stage Training Supervised Contrastive Loss

September 12, 2022

Prototypical few-shot segmentation for cross-institution male pelvic structures with spatial registration
Yiwen Li, Yunguan Fu, Iani Gayo, Qianye Yang, Zhe Min, Shaheer Saeed, Wen Yan, Yipei Wang, J. Alison Noble, Mark Emberton, Matthew J. Clarkson, Henkjan Huisman, Dean Barratt, Victor Adrian Prisacariu, Yipeng Hu
Shot Learning Shot Segmentation Shot 3D Spatial Alignment Segmentation Head Temporal Registration

September 2, 2022

Learn to Adapt to New Environment from Past Experience and Few Pilot
Ouya Wang, Jiabao Gao, Geoffrey Ye Li
Deep Learning Shot Learning eXperience Report New Environment Deep Learning Based Channel Estimation

August 29, 2022

Prompt Tuning with Soft Context Sharing for Vision-Language Models
Kun Ding, Ying Wang, Pengzhang Liu, Qiang Yu, Haojian Zhang, Shiming Xiang, Chunhong Pan
Vision Language Model Multi Task Learning Shot Learning Prompt Tuning Pre Trained Vision Language Model Vision Language Prompt

August 26, 2022

August 23, 2022

August 22, 2022

Transductive Decoupled Variational Inference for Few-Shot Classification
Anuj Singh, Hadi Jamali-Rad
Classification Code Shot Learning Variational Inference Shot Classification Shot Task TinyImagenet Benchmark

August 20, 2022

Learning Primitive-aware Discriminative Representations for Few-shot Learning
Jianpeng Yang, Yuhang Niu, Xuemei Xie, Guangming Shi
Shot Learning Primitive Based Adversarial Training

August 17, 2022

August 12, 2022

Domain-invariant Prototypes for Semantic Segmentation
Zhengeng Yang, Hongshan Yu, Wei Sun, Li-Cheng, Ajmal Mian
Semantic Segmentation Domain Adaptation Shot Learning

August 11, 2022

FIGO: Enhanced Fingerprint Identification Approach Using GAN and One Shot Learning Techniques
Ibrahim Yilmaz, Mahmoud Abouyoussef
Shot Learning GAN Model Fingerprint Biometrics Fingerprint Enhancement

August 9, 2022

Few-shot Bioacoustic Event Detection with Machine Learning Methods
Leah Chowenhill, Gaurav Satyanath, Shubhranshu Singh, Madhav Mahendra Wagh
Deep Learning Machine Learning Shot Learning Meta Learning Ultrasonic Vocalization

Shot Learning

Papers

Revisiting Few-Shot Learning from a Causal Perspective

An Embarrassingly Simple Approach to Semi-Supervised Few-Shot Learning

Graph Neural Network Expressivity and Meta-Learning for Molecular Property Regression

A Few Shot Multi-Representation Approach for N-gram Spotting in Historical Manuscripts

Few-Shot Classification with Contrastive Learning

Prototypical few-shot segmentation for cross-institution male pelvic structures with spatial registration

Learn to Adapt to New Environment from Past Experience and Few Pilot

Prompt Tuning with Soft Context Sharing for Vision-Language Models

Disentangle and Remerge: Interventional Knowledge Distillation for Few-Shot Object Detection from A Conditional Causal Perspective

Expanding continual few-shot learning benchmarks to include recognition of specific instances

Few-Shot Learning Meets Transformer: Unified Query-Support Transformers for Few-Shot Classification

Adversarial Feature Augmentation for Cross-domain Few-shot Classification

Transfer Learning Application of Self-supervised Learning in ARPES

Transductive Decoupled Variational Inference for Few-Shot Classification

Learning Primitive-aware Discriminative Representations for Few-shot Learning

Gradient-Based Meta-Learning Using Uncertainty to Weigh Loss for Few-Shot Learning

Constrained Few-Shot Learning: Human-Like Low Sample Complexity Learning and Non-Episodic Text Classification

Domain-invariant Prototypes for Semantic Segmentation

FIGO: Enhanced Fingerprint Identification Approach Using GAN and One Shot Learning Techniques

Few-shot Bioacoustic Event Detection with Machine Learning Methods