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

May 31, 2022

Meta-ticket: Finding optimal subnetworks for few-shot learning within randomly initialized neural networks
Daiki Chijiwa, Shin'ya Yamaguchi, Atsutoshi Kumagai, Yasutoshi Ida
Neural Network Strong Generalization Shot Learning Sparse Neural Network Sparse Subnetworks Robust Ticket Novel Generalization

May 30, 2022

May 25, 2022

ToKen: Task Decomposition and Knowledge Infusion for Few-Shot Hate Speech Detection
Badr AlKhamissi, Faisal Ladhak, Srini Iyer, Ves Stoyanov, Zornitsa Kozareva, Xian Li, Pascale Fung, Lambert Mathias, Asli Celikyilmaz, Mona Diab
Shot Learning Hate Speech Detection Commonsense Reasoning K TOKEN Reasoning Datasets Online Hate Task Decomposition Knowledge Infusion

May 24, 2022

May 22, 2022

Self-mentoring: a new deep learning pipeline to train a self-supervised U-net for few-shot learning of bio-artificial capsule segmentation
Arnaud Deleruyelle, Cristian Versari, John Klein
Shot Learning Image Segmentation Accurate Segmentation Pipeline System 3D Capsule

May 21, 2022

Learning Meta Representations of One-shot Relations for Temporal Knowledge Graph Link Prediction
Zifeng Ding, Bailan He, Yunpu Ma, Zhen Han, Volker Tresp
Shot Learning Temporal Knowledge Graph Temporal Link Prediction Meta Representation

May 20, 2022

Mask-guided Vision Transformer (MG-ViT) for Few-Shot Learning
Yuzhong Chen, Zhenxiang Xiao, Lin Zhao, Lu Zhang, Haixing Dai, David Weizhong Liu, Zihao Wu, Changhe Li, Tuo Zhang, Changying Li, Dajiang Zhu, Tianming Liu, Xi Jiang
LeArning Abstract Vision Transformer Shot Learning Mask Transformer Shot Sample

May 17, 2022

Uncertainty-based Network for Few-shot Image Classification
Minglei Yuan, Qian Xu, Chunhao Cai, Yin-Dong Zheng, Tao Wang, Tong Lu
Shot Learning Mutual Information Uncertainty Aware Shot Image Classification Instance Query Transductive Inference

May 13, 2022

May 12, 2022

Using dependency parsing for few-shot learning in distributional semantics
Stefania Preda, Guy Emerson
Shot Learning Distributional Semantics Dependency Aware Incident Additive Intervention

May 10, 2022

Privacy Enhancement for Cloud-Based Few-Shot Learning
Archit Parnami, Muhammad Usama, Liyue Fan, Minwoo Lee
LeArning Abstract Shot Learning Privacy Preservation Privacy Preserving Image Visual Privacy Privacy Preserving Representation

May 8, 2022

PGADA: Perturbation-Guided Adversarial Alignment for Few-shot Learning Under the Support-Query Shift
Siyang Jiang, Wei Ding, Hsi-Wen Chen, Ming-Syan Chen
Shot Learning Optimal Transport Customer Service Adversarial Alignment Adversarial Style Augmentation

May 5, 2022

May 3, 2022

Kompetencer: Fine-grained Skill Classification in Danish Job Postings via Distant Supervision and Transfer Learning
Mike Zhang, Kristian Nørgaard Jensen, Barbara Plank
Fine Grained Transfer Learning Shot Learning Distant Supervision Job Market Skill Label

May 2, 2022

OPT: Open Pre-trained Transformer Language Models
Susan Zhang, Stephen Roller, Naman Goyal, Mikel Artetxe, Moya Chen, Shuohui Chen, Christopher Dewan, Mona Diab, Xian Li, Xi Victoria Lin, Todor Mihaylov, Myle Ott, Sam Shleifer, Kurt Shuster, Daniel Simig, Punit Singh Koura, Anjali Sridhar, Tianlu Wang, Luke Zettlemoyer
Large Language Model Shot Learning Model Weight Transformer Based Pre Trained Language

Shot Learning

Papers

Meta-ticket: Finding optimal subnetworks for few-shot learning within randomly initialized neural networks

Few-Shot Diffusion Models

Prompting ELECTRA: Few-Shot Learning with Discriminative Pre-Trained Models

Task-Prior Conditional Variational Auto-Encoder for Few-Shot Image Classification

ToKen: Task Decomposition and Knowledge Infusion for Few-Shot Hate Speech Detection

Large Language Models are Zero-Shot Reasoners

Adaptive Few-Shot Learning Algorithm for Rare Sound Event Detection

Self-mentoring: a new deep learning pipeline to train a self-supervised U-net for few-shot learning of bio-artificial capsule segmentation

Learning Meta Representations of One-shot Relations for Temporal Knowledge Graph Link Prediction

Mask-guided Vision Transformer (MG-ViT) for Few-Shot Learning

Uncertainty-based Network for Few-shot Image Classification

A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunities

How to Fine-tune Models with Few Samples: Update, Data Augmentation, and Test-time Augmentation

Using dependency parsing for few-shot learning in distributional semantics

Privacy Enhancement for Cloud-Based Few-Shot Learning

PGADA: Perturbation-Guided Adversarial Alignment for Few-shot Learning Under the Support-Query Shift

Generating Representative Samples for Few-Shot Classification

FAITH: Few-Shot Graph Classification with Hierarchical Task Graphs

Kompetencer: Fine-grained Skill Classification in Danish Job Postings via Distant Supervision and Transfer Learning

OPT: Open Pre-trained Transformer Language Models