Shot Scenario

Few-shot learning aims to train machine learning models effectively using only a limited number of labeled examples, addressing the challenge of data scarcity in various domains. Current research focuses on improving the performance and robustness of few-shot learning across diverse tasks, including image classification, object detection, natural language processing (e.g., named entity recognition, text generation), and graph anomaly detection, often employing techniques like meta-learning, prototype networks, and contrastive learning within transformer and other neural network architectures. This research is significant because it enables the development of adaptable and efficient AI systems capable of handling new tasks and domains with minimal training data, impacting fields ranging from robotics and medical image analysis to natural language understanding and cybersecurity.

Papers

October 21, 2024

Few-shot target-driven instance detection based on open-vocabulary object detection models
Ben Crulis, Barthelemy Serres, Cyril De Runz, Gilles Venturini
Object Detection Model Shot Object Detection Large Vision Model Shot Scenario Zero Shot Detection

October 20, 2024

Open-vocabulary vs. Closed-set: Best Practice for Few-shot Object Detection Considering Text Describability
Yusuke Hosoya, Masanori Suganuma, Takayuki Okatani
Data Detection Object Detection Open Vocabulary Open Vocabulary Object Detection Shot Object Detection Shot Scenario

October 15, 2024

In-Context Learning for Long-Context Sentiment Analysis on Infrastructure Project Opinions
Alireza Shamshiri, Kyeong Rok Ryu, June Young Park
Large Language Model Context Learning GPT 4 Long Context Sentiment Polarity Shot Scenario

October 2, 2024

Mitigating Copy Bias in In-Context Learning through Neuron Pruning
Ameen Ali, Lior Wolf, Ivan Titov
Large Language Model Context Learning Mitigating Bias Shot Scenario Synthetic Task Task Vector Neuron Pruning

September 3, 2024

Multi-Modal Adapter for Vision-Language Models
Dominykas Seputis, Serghei Mihailov, Soham Chatterjee, Zehao Xiao
Vision Language Model Pre Trained Vision Language Model Multi Head Attention CLIP Model Shot Scenario Modal Adapter Modal Adaptation

August 11, 2024

An analysis of HOI: using a training-free method with multimodal visual foundation models when only the test set is available, without the training set
Chaoyi Ai
General Analysis Human Object Interaction Training Free Shot Scenario Training Set Multimodal Foundation

August 9, 2024

FewShotNeRF: Meta-Learning-based Novel View Synthesis for Rapid Scene-Specific Adaptation
Piraveen Sivakumar, Paul Janson, Jathushan Rajasegaran, Thanuja Ambegoda
Neural Radiance Field Novel View Synthesis Multi View Image 3D Datasets Shot Scenario Real World Object Robust 3D

July 24, 2024

Selective Vision-Language Subspace Projection for Few-shot CLIP
Xingyu Zhu, Beier Zhu, Yi Tan, Shuo Wang, Yanbin Hao, Hanwang Zhang
Vision Language Model Vision Language Image Text Pair Image Text Alignment Shot Scenario

June 25, 2024

TALEC: Teach Your LLM to Evaluate in Specific Domain with In-house Criteria by Criteria Division and Zero-shot Plus Few-shot
Kaiqi Zhang, Shuai Yuan, Honghan Zhao
Large Language Model Global Evaluation Open Domain Text Generation Task Shot Scenario Likely Criterion Model Based Evaluation

May 20, 2024

Learning Spatial Similarity Distribution for Few-shot Object Counting
Yuanwu Xu, Feifan Song, Haofeng Zhang
Feature Pyramid Network Shot Scenario Similarity Matrix Shot Object Counting Deep Similarity

May 19, 2024

DaVinci at SemEval-2024 Task 9: Few-shot prompting GPT-3.5 for Unconventional Reasoning
Suyash Vardhan Mathur, Akshett Rai Jindal, Manish Shrivastava
SemEval 2022 Task Shot Scenario Lateral Thinking Rational Reasoning

March 26, 2024

Continual Few-shot Event Detection via Hierarchical Augmentation Networks
Chenlong Zhang, Pengfei Cao, Yubo Chen, Kang Liu, Zhiqiang Zhang, Mengshu Sun, Jun Zhao
Event Detection Shot Scenario Shot Event Detection Hierarchical Augmentation

March 6, 2024

X-Shot: A Unified System to Handle Frequent, Few-shot and Zero-shot Learning Simultaneously in Classification
Hanzi Xu, Muhao Chen, Lifu Huang, Slobodan Vucetic, Wenpeng Yin
Classification Code Shot Learning Zero Shot Learning Shot Scenario Textual Label Open Domain Generalization

January 20, 2024

Stability Plasticity Decoupled Fine-tuning For Few-shot end-to-end Object Detection
Yuantao Yin, Ping Yin
Fine Tuning Object Detector Plasticity Rule Shot Scenario Stability Plasticity Sparse R CNN

November 17, 2023

Few-shot Message-Enhanced Contrastive Learning for Graph Anomaly Detection
Fan Xu, Nan Wang, Xuezhi Wen, Meiqi Gao, Chaoqun Guo, Xibin Zhao
Contrastive Learning Graph Anomaly Detection Shot Anomaly Detection Domain Discrepancy Shot Scenario Shot Data

September 23, 2023

Defending Pre-trained Language Models as Few-shot Learners against Backdoor Attacks
Zhaohan Xi, Tianyu Du, Changjiang Li, Ren Pang, Shouling Ji, Jinghui Chen, Fenglong Ma, Ting Wang
Language Model Pre Trained Language Model Backdoor Attack Shot Scenario Shot Learner Shot Data

September 22, 2023

Detect Everything with Few Examples
Xinyu Zhang, Yuhan Liu, Yuting Wang, Abdeslam Boularias
Shot Object Detection One Shot Shot Scenario Mask Propagation

September 21, 2023

HANS, are you clever? Clever Hans Effect Analysis of Neural Systems
Leonardo Ranaldi, Fabio Massimo Zanzotto
Adversarial Example Reasoning Ability Shot Scenario Neural System Clever Han

September 3, 2023

Chinese Text Recognition with A Pre-Trained CLIP-Like Model Through Image-IDS Aligning
Haiyang Yu, Xiaocong Wang, Bin Li, Xiangyang Xue
Shot Scenario Chinese Text Recognition

August 7, 2023

Improving Few-shot and Zero-shot Entity Linking with Coarse-to-Fine Lexicon-based Retriever
Shijue Huang, Bingbing Wang, Libo Qin, Qin Zhao, Ruifeng Xu
Entity Mention Coarse to Fine Shot Scenario Entity Description Hybrid Retriever Lexicon Based Retrieval Zero Shot Entity Linking

Shot Scenario

Papers

Few-shot target-driven instance detection based on open-vocabulary object detection models

Open-vocabulary vs. Closed-set: Best Practice for Few-shot Object Detection Considering Text Describability

In-Context Learning for Long-Context Sentiment Analysis on Infrastructure Project Opinions

Mitigating Copy Bias in In-Context Learning through Neuron Pruning

Multi-Modal Adapter for Vision-Language Models

An analysis of HOI: using a training-free method with multimodal visual foundation models when only the test set is available, without the training set

FewShotNeRF: Meta-Learning-based Novel View Synthesis for Rapid Scene-Specific Adaptation

Selective Vision-Language Subspace Projection for Few-shot CLIP

TALEC: Teach Your LLM to Evaluate in Specific Domain with In-house Criteria by Criteria Division and Zero-shot Plus Few-shot

Learning Spatial Similarity Distribution for Few-shot Object Counting

DaVinci at SemEval-2024 Task 9: Few-shot prompting GPT-3.5 for Unconventional Reasoning

Continual Few-shot Event Detection via Hierarchical Augmentation Networks

X-Shot: A Unified System to Handle Frequent, Few-shot and Zero-shot Learning Simultaneously in Classification

Stability Plasticity Decoupled Fine-tuning For Few-shot end-to-end Object Detection

Few-shot Message-Enhanced Contrastive Learning for Graph Anomaly Detection

Defending Pre-trained Language Models as Few-shot Learners against Backdoor Attacks

Detect Everything with Few Examples

HANS, are you clever? Clever Hans Effect Analysis of Neural Systems

Chinese Text Recognition with A Pre-Trained CLIP-Like Model Through Image-IDS Aligning

Improving Few-shot and Zero-shot Entity Linking with Coarse-to-Fine Lexicon-based Retriever