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

August 28, 2023

August 24, 2023

Less is More: Towards Efficient Few-shot 3D Semantic Segmentation via Training-free Networks
Xiangyang Zhu, Renrui Zhang, Bowei He, Ziyu Guo, Jiaming Liu, Hao Dong, Peng Gao
Shot Learning Training Free 3D Segmentation Shot 3D

August 21, 2023

COCA: Classifier-Oriented Calibration via Textual Prototype for Source-Free Universal Domain Adaptation
Xinghong Liu, Yi Zhou, Tao Zhou, Chun-Mei Feng, Ling Shao
Shot Learning Calibration Performance Universal Domain Adaptation Classifier Calibration

August 19, 2023

UniAP: Towards Universal Animal Perception in Vision via Few-shot Learning
Meiqi Sun, Zhonghan Zhao, Wenhao Chai, Hanjun Luo, Shidong Cao, Yanting Zhang, Jenq-Neng Hwang, Gaoang Wang
Shot Learning Vision Paper Visual Perception Deep Learning Based Perception Universal Visual Perception

August 14, 2023

Approximating Human-Like Few-shot Learning with GPT-based Compression
Cynthia Huang, Yuqing Xie, Zhiying Jiang, Jimmy Lin, Ming Li
Shot Learning Generative Pre Trained Transformer Data Compression Pre Trained Generative Model Lossless Compression Generative Compression Information Maximization

August 10, 2023

Cross-heterogeneity Graph Few-shot Learning
Pengfei Ding, Yan Wang, Guanfeng Liu
Shot Learning Heterogeneous Graph

August 4, 2023

Self-Normalizing Neural Network, Enabling One Shot Transfer Learning for Modeling EDFA Wavelength Dependent Gain
Agastya Raj, Zehao Wang, Frank Slyne, Tingjun Chen, Dan Kilper, Marco Ruffini
Transfer Learning Shot Learning Adaptive Normalization Light Source EDA Developer

July 31, 2023

MetaDiff: Meta-Learning with Conditional Diffusion for Few-Shot Learning
Baoquan Zhang, Chuyao Luo, Demin Yu, Huiwei Lin, Xutao Li, Yunming Ye, Bowen Zhang
LeArning Abstract Shot Learning Meta Learning Deep Model Conditional Diffusion Gradient Based Meta Learning

July 28, 2023

July 27, 2023

July 20, 2023

Optimizing PatchCore for Few/many-shot Anomaly Detection
João Santos, Triet Tran, Oliver Rippel
Shot Learning Shot Anomaly Detection Anomaly Segmentation

July 9, 2023

FILM: How can Few-Shot Image Classification Benefit from Pre-Trained Language Models?
Zihao Jiang, Yunkai Dang, Dong Pang, Huishuai Zhang, Weiran Huang
Contrastive Learning Pre Trained Language Model Shot Learning Movie Review

July 6, 2023

Proto-CLIP: Vision-Language Prototypical Network for Few-Shot Learning
Jishnu Jaykumar P, Kamalesh Palanisamy, Yu-Wei Chao, Xinya Du, Yu Xiang
LeArning Abstract Shot Learning Shot Classification Shot Example Unimodal Representation

July 5, 2023

Task-Specific Alignment and Multiple Level Transformer for Few-Shot Action Recognition
Fei Guo, Li Zhu, YiWang Wang, Jing Sun
Shot Learning Action Recognition Temporal Alignment Layer Transformer Task Alignment Action Duration

July 4, 2023

June 19, 2023

Adversarial Robustness of Prompt-based Few-Shot Learning for Natural Language Understanding
Venkata Prabhakara Sarath Nookala, Gaurav Verma, Subhabrata Mukherjee, Srijan Kumar
LeArning Abstract Adversarial Robustness Shot Learning Adversarial Perturbation Language Understanding Shot Example

Shot Learning

Papers

VesselShot: Few-shot learning for cerebral blood vessel segmentation

Fair Few-shot Learning with Auxiliary Sets

Less is More: Towards Efficient Few-shot 3D Semantic Segmentation via Training-free Networks

COCA: Classifier-Oriented Calibration via Textual Prototype for Source-Free Universal Domain Adaptation

UniAP: Towards Universal Animal Perception in Vision via Few-shot Learning

Approximating Human-Like Few-shot Learning with GPT-based Compression

Cross-heterogeneity Graph Few-shot Learning

Self-Normalizing Neural Network, Enabling One Shot Transfer Learning for Modeling EDFA Wavelength Dependent Gain

MetaDiff: Meta-Learning with Conditional Diffusion for Few-Shot Learning

Cross-Modal Concept Learning and Inference for Vision-Language Models

DiffKendall: A Novel Approach for Few-Shot Learning with Differentiable Kendall's Rank Correlation

Med-Flamingo: a Multimodal Medical Few-shot Learner

GenCo: An Auxiliary Generator from Contrastive Learning for Enhanced Few-Shot Learning in Remote Sensing

Optimizing PatchCore for Few/many-shot Anomaly Detection

FILM: How can Few-Shot Image Classification Benefit from Pre-Trained Language Models?

Proto-CLIP: Vision-Language Prototypical Network for Few-Shot Learning

Task-Specific Alignment and Multiple Level Transformer for Few-Shot Action Recognition

Diverse Retrieval-Augmented In-Context Learning for Dialogue State Tracking

TablEye: Seeing small Tables through the Lens of Images

Adversarial Robustness of Prompt-based Few-Shot Learning for Natural Language Understanding