Shot Classification Benchmark

Shot classification benchmarks evaluate the performance of machine learning models in classifying images with limited training data (few-shot learning). Current research focuses on improving model generalization by leveraging techniques like incorporating semantic information from large language models, employing attention mechanisms within vision transformers, and utilizing ensemble learning strategies with diverse feature extraction methods. These advancements aim to bridge the gap between human-like visual learning and the capabilities of artificial neural networks, impacting fields such as image recognition and object detection where labeled data is scarce.

Papers

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

August 22, 2024

Envisioning Class Entity Reasoning by Large Language Models for Few-shot Learning
Mushui Liu, Fangtai Wu, Bozheng Li, Ziqian Lu, Yunlong Yu, Xi Li
Shot Learning Generalization Capability Visual Pattern Shot Classification Benchmark

May 6, 2024

Intra-task Mutual Attention based Vision Transformer for Few-Shot Learning
Weihao Jiang, Chang Liu, Kun He
LeArning Abstract Vision Transformer Shot Learning Pre Trained Vision Transformer Intra Class Shot Classification Benchmark Mutual Attention

April 30, 2023

Few-shot Classification via Ensemble Learning with Multi-Order Statistics
Sai Yang, Fan Liu, Delong Chen, Jun Zhou
Transfer Learning Ensemble Learning Shot Classification Shot Classification Benchmark Order Statistic

April 27, 2023

Generating images of rare concepts using pre-trained diffusion models
Dvir Samuel, Rami Ben-Ari, Simon Raviv, Nir Darshan, Gal Chechik
Image Generation Text to Image Diffusion Model Text to Image Model Pre Trained Diffusion Model Underrepresented Group Novel Concept Shot Classification Benchmark Imbalanced Training

November 29, 2022

Exploiting Category Names for Few-Shot Classification with Vision-Language Models
Taihong Xiao, Zirui Wang, Liangliang Cao, Jiahui Yu, Shengyang Dai, Ming-Hsuan Yang
Vision Language Model Classification Code Large Vision Language Model Shot Classification Vision Language Foundation Model Category Shift Shot Classification Benchmark

June 15, 2022

Rethinking Generalization in Few-Shot Classification
Markus Hiller, Rongkai Ma, Mehrtash Harandi, Tom Drummond
Classification Code Systematic Generalization Image Level Annotation Shot Classification Benchmark

December 7, 2021

Learning Instance and Task-Aware Dynamic Kernels for Few Shot Learning
Rongkai Ma, Pengfei Fang, Gil Avraham, Yan Zuo, Tianyu Zhu, Tom Drummond, Mehrtash Harandi
Deep Convolutional Neural Network Shot Classification Shot Detection Shot Classification Benchmark

December 6, 2021

Label Hallucination for Few-Shot Classification
Yiren Jian, Lorenzo Torresani
Classification Code Shot Learning Content Hallucination Shot Classification Unseen Class Shot Classification Benchmark

December 3, 2021

Adaptive Poincar\'e Point to Set Distance for Few-Shot Classification
Rongkai Ma, Pengfei Fang, Tom Drummond, Mehrtash Harandi
Classification Code Shot Learning Adaptive Importance Exceptional Point Shot Classification Benchmark Hyperbolic Metric Learning X Ray Style Distance