Shot Classification

Shot classification, particularly few-shot classification, focuses on training classifiers with limited labeled data, aiming to improve generalization to unseen classes. Current research emphasizes adapting pre-trained models like CLIP, employing meta-learning algorithms, and exploring techniques such as prompt engineering and hyperdimensional computing to enhance efficiency and accuracy. This field is crucial for addressing data scarcity issues in various domains, including medical imaging and natural language processing, enabling the development of more robust and adaptable AI systems.

Papers

October 24, 2024

Tailored-LLaMA: Optimizing Few-Shot Learning in Pruned LLaMA Models with Task-Specific Prompts
Danyal Aftab, Steven Davy
Large Language Model LeArning Abstract Shot Learning Task Specific Shot Classification LLaMA Model Fine Tuned Llama

October 11, 2024

Cross-Domain Evaluation of Few-Shot Classification Models: Natural Images vs. Histopathological Images
Ardhendu Sekhar, Aditya Bhattacharya, Vinayak Goyal, Vrinda Goel, Aditya Bhangale, Ravi Kant Gupta, Amit Sethi
Cross Domain Histopathological Image Shot Classification Image Domain Histopathology Datasets

October 8, 2024

Efficient Few-shot Learning for Multi-label Classification of Scientific Documents with Many Classes
Tim Schopf, Alexander Blatzheim, Nektarios Machner, Florian Matthes
High Efficiency Multi Label Classification Shot Classification Class Specific Scientific Document Scientific Document Representation Text Fusion

October 7, 2024

Fine-Tuning CLIP's Last Visual Projector: A Few-Shot Cornucopia
Mohammad Fahes, Tuan-Hung Vu, Andrei Bursuc, Patrick Pérez, Raoul de Charette
Vision Language Model Shot Classification Camera Projector Shot Class CLIP Adaptation Shot Classification Benchmark

October 3, 2024

Unsupervised Meta-Learning via Dynamic Head and Heterogeneous Task Construction for Few-Shot Classification
Yunchuan Guan, Yu Liu, Ketong Liu, Ke Zhou, Zhiqi Shen
Shot Learning Meta Learning Shot Classification Heterogeneous Task

September 28, 2024

Learning to Obstruct Few-Shot Image Classification over Restricted Classes
Amber Yijia Zheng, Chiao-An Yang, Raymond A. Yeh
LeArning Abstract Pre Trained Model Image Classification Supervised ImageNet Shot Classification Class Specific Pre Trained Backbone

September 17, 2024

September 15, 2024

COSCO: A Sharpness-Aware Training Framework for Few-shot Multivariate Time Series Classification
Jesus Barreda, Ashley Gomez, Ruben Puga, Kaixiong Zhou, Li Zhang
Loss Function Time Series Classification Shot Classification Multivariate Time Series Classification

September 12, 2024

Enhancing Few-Shot Image Classification through Learnable Multi-Scale Embedding and Attention Mechanisms
Fatemeh Askari, Amirreza Fateh, Mohammad Reza Mohammadi
Image Classification Attention Mechanism Multi Scale Shot Classification Feature Space Feature Vector Diverse Feature

September 3, 2024

Political DEBATE: Efficient Zero-shot and Few-shot Classifiers for Political Text
Michael Burnham, Kayla Kahn, Ryan Yank Wang, Rachel X. Peng
Large Language Model Language Model Zero Shot Zero Shot Learning Textual Entailment Shot Classification Political Discourse Political Content

August 26, 2024

Feature Aligning Few shot Learning Method Using Local Descriptors Weighted Rules
Bingchen Yan
Shot Classification Feature Alignment Shot Image Classification Local Descriptor Learning Method

August 25, 2024

Few-Shot Histopathology Image Classification: Evaluating State-of-the-Art Methods and Unveiling Performance Insights
Ardhendu Sekhar, Ravi Kant Gupta, Amit Sethi
Image Classification Shot Learning State of the Art Shot Classification Histopathology Image Histopathology Datasets

August 21, 2024

Making Large Vision Language Models to be Good Few-shot Learners
Fan Liu, Wenwen Cai, Jian Huo, Chuanyi Zhang, Delong Chen, Jun Zhou
Shot Learning Large Vision Language Model Shot Classification Shot Learner

August 6, 2024

LAMPO: Large Language Models as Preference Machines for Few-shot Ordinal Classification
Zhen Qin, Junru Wu, Jiaming Shen, Tianqi Liu, Xuanhui Wang
Shot Learning Shot Classification Speech Detection Latent Action Point Prediction

July 2, 2024

Unleash the Power of Local Representations for Few-Shot Classification
Shi Tang, Guiming Luo, Xinchen Ye, Zhiyi Xia
Classification Code Real Power Shot Classification Local Feature Local Representation Class Diversity Novel Class Generalization

June 14, 2024

Self-Supervised and Few-Shot Learning for Robust Bioaerosol Monitoring
Adrian Willi, Pascal Baumann, Sophie Erb, Fabian Gröger, Yanick Zeder, Simone Lionetti
LeArning Abstract Self Supervised Learning Self Supervised Shot Learning Shot Classification Data Collection Aerosol Particle

May 29, 2024

May 25, 2024

Enhancing Near OOD Detection in Prompt Learning: Maximum Gains, Minimal Costs
Myong Chol Jung, He Zhao, Joanna Dipnall, Belinda Gabbe, Lan Du
Distribution Detection Prompt Learning Shot Classification Intrinsic Out of Distribution Detection Minimal Cost

Shot Classification

Papers

Tailored-LLaMA: Optimizing Few-Shot Learning in Pruned LLaMA Models with Task-Specific Prompts

Cross-Domain Evaluation of Few-Shot Classification Models: Natural Images vs. Histopathological Images

Efficient Few-shot Learning for Multi-label Classification of Scientific Documents with Many Classes

Fine-Tuning CLIP's Last Visual Projector: A Few-Shot Cornucopia

Unsupervised Meta-Learning via Dynamic Head and Heterogeneous Task Construction for Few-Shot Classification

Learning to Obstruct Few-Shot Image Classification over Restricted Classes

CLIP Adaptation by Intra-modal Overlap Reduction

FSL-HDnn: A 5.7 TOPS/W End-to-end Few-shot Learning Classifier Accelerator with Feature Extraction and Hyperdimensional Computing

COSCO: A Sharpness-Aware Training Framework for Few-shot Multivariate Time Series Classification

Enhancing Few-Shot Image Classification through Learnable Multi-Scale Embedding and Attention Mechanisms

Political DEBATE: Efficient Zero-shot and Few-shot Classifiers for Political Text

Feature Aligning Few shot Learning Method Using Local Descriptors Weighted Rules

Few-Shot Histopathology Image Classification: Evaluating State-of-the-Art Methods and Unveiling Performance Insights

Making Large Vision Language Models to be Good Few-shot Learners

LAMPO: Large Language Models as Preference Machines for Few-shot Ordinal Classification

Unleash the Power of Local Representations for Few-Shot Classification

Self-Supervised and Few-Shot Learning for Robust Bioaerosol Monitoring

MOKD: Cross-domain Finetuning for Few-shot Classification via Maximizing Optimized Kernel Dependence

On the Limits of Multi-modal Meta-Learning with Auxiliary Task Modulation Using Conditional Batch Normalization

Enhancing Near OOD Detection in Prompt Learning: Maximum Gains, Minimal Costs