Few-Shot Image Classification

200 papers with code • 88 benchmarks • 23 datasets

Few-Shot Image Classification is a computer vision task that involves training machine learning models to classify images into predefined categories using only a few labeled examples of each category (typically < 6 examples). The goal is to enable models to recognize and classify new images with minimal supervision and limited data, without having to train on large datasets. (typically < 6 examples)

( Image credit: Learning Embedding Adaptation for Few-Shot Learning )

Libraries

Use these libraries to find Few-Shot Image Classification models and implementations

Latest papers with no code

Frozen Feature Augmentation for Few-Shot Image Classification

no code yet • 15 Mar 2024

Training a linear classifier or lightweight model on top of pretrained vision model outputs, so-called 'frozen features', leads to impressive performance on a number of downstream few-shot tasks.

Few-Shot Image Classification and Segmentation as Visual Question Answering Using Vision-Language Models

no code yet • 15 Mar 2024

By enabling a VLM to interact with off-the-shelf vision models as tools, the proposed method is capable of classifying and segmenting target objects using only image-level labels.

Few and Fewer: Learning Better from Few Examples Using Fewer Base Classes

no code yet • 29 Jan 2024

Fine-tuning is ineffective for few-shot learning, since the target dataset contains only a handful of examples.

LDCA: Local Descriptors with Contextual Augmentation for Few-Shot Learning

no code yet • 24 Jan 2024

Few-shot image classification has emerged as a key challenge in the field of computer vision, highlighting the capability to rapidly adapt to new tasks with minimal labeled data.

TALDS-Net: Task-Aware Adaptive Local Descriptors Selection for Few-shot Image Classification

no code yet • 9 Dec 2023

Few-shot image classification aims to classify images from unseen novel classes with few samples.

Large Language Models are Good Prompt Learners for Low-Shot Image Classification

no code yet • 7 Dec 2023

Thus, we propose LLaMP, Large Language Models as Prompt learners, that produces adaptive prompts for the CLIP text encoder, establishing it as the connecting bridge.

Few-Shot Classification & Segmentation Using Large Language Models Agent

no code yet • 19 Nov 2023

The task of few-shot image classification and segmentation (FS-CS) requires the classification and segmentation of target objects in a query image, given only a few examples of the target classes.

PrototypeFormer: Learning to Explore Prototype Relationships for Few-shot Image Classification

no code yet • 5 Oct 2023

In particular, our method achieves 97. 07% and 90. 88% on 5-way 5-shot and 5-way 1-shot tasks of miniImageNet, which surpasses the state-of-the-art results with accuracy of 7. 27% and 8. 72%, respectively.

MVP: Meta Visual Prompt Tuning for Few-Shot Remote Sensing Image Scene Classification

no code yet • 17 Sep 2023

In order to tackle these issues, we turn to the recently proposed parameter-efficient tuning methods, such as VPT, which updates only the newly added prompt parameters while keeping the pre-trained backbone frozen.

Knowledge-Aware Prompt Tuning for Generalizable Vision-Language Models

no code yet • ICCV 2023

Pre-trained vision-language models, e. g., CLIP, working with manually designed prompts have demonstrated great capacity of transfer learning.