Computer Vision
 
Edit

Few-Shot Image Classification

202 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

Datasets

Subtasks

Logarithm-transform aided Gaussian Sampling for Few-Shot Learning

ganatra-v/gaussian-sampling-fsl • • 28 Sep 2023

These methods rely on transforming the distributions of experimental data to approximate Gaussian distributions for their functioning.

0
28 Sep 2023
Paper
Code

PRE: Vision-Language Prompt Learning with Reparameterization Encoder

minhanh151/respro • • 14 Sep 2023

In this work, we present Prompt Learning with Reparameterization Encoder (PRE) - a simple and efficient method that enhances the generalization ability of the learnable prompt to unseen classes while maintaining the capacity to learn Base classes.

4
14 Sep 2023
Paper
Code

Language Models as Black-Box Optimizers for Vision-Language Models

shihongl1998/llm-as-a-blackbox-optimizer • 12 Sep 2023

We highlight the advantage of conversational feedback that incorporates both positive and negative prompts, suggesting that LLMs can utilize the implicit gradient direction in textual feedback for a more efficient search.

8
12 Sep 2023
Paper
Code

Cross-Image Context Matters for Bongard Problems

nraghuraman/bongard-context • • 7 Sep 2023

Current machine learning methods struggle to solve Bongard problems, which are a type of IQ test that requires deriving an abstract "concept" from a set of positive and negative "support" images, and then classifying whether or not a new query image depicts the key concept.

1
07 Sep 2023
Paper
Code

DiffKendall: A Novel Approach for Few-Shot Learning with Differentiable Kendall's Rank Correlation

kaipengm2/DiffKendall • • NeurIPS 2023

By replacing geometric similarity with differentiable Kendall's rank correlation, our method can integrate with numerous existing few-shot approaches and is ready for integrating with future state-of-the-art methods that rely on geometric similarity metrics.

1
28 Jul 2023
Paper
Code

Distilling Large Vision-Language Model with Out-of-Distribution Generalizability

xuanlinli17/large_vlm_distillation_ood • • ICCV 2023

Model distillation, the process of creating smaller, faster models that maintain the performance of larger models, is a promising direction towards the solution.

42
06 Jul 2023
Paper
Code

Proto-CLIP: Vision-Language Prototypical Network for Few-Shot Learning

IRVLUTD/Proto-CLIP • • 6 Jul 2023

The two encoders are used to compute prototypes of image classes for classification.

32
06 Jul 2023
Paper
Code

Comparing the Efficacy of Fine-Tuning and Meta-Learning for Few-Shot Policy Imitation

mpatacchiola/imujoco • • 23 Jun 2023

Despite its simplicity this baseline is competitive with meta-learning methods on a variety of conditions and is able to imitate target policies trained on unseen variations of the original environment.

4
23 Jun 2023
Paper
Code

Multistage Relation Network With Dual-Metric for Few-Shot Hyperspectral Image Classification

ZhaohuiXue/DM-MRN • • IEEE Transactions on Geoscience and Remote Sensing 2023

In addition, an adaptive weighting strategy is designed to fuse the obtained relation scores, and classification can be achieved by assigning each query sample to the class with the highest value of the fused relation score.

11
28 Apr 2023
Paper
Code

ESPT: A Self-Supervised Episodic Spatial Pretext Task for Improving Few-Shot Learning

whut-yirong/espt • • 26 Apr 2023

With this definition, the ESPT-augmented FSL objective promotes learning more transferable feature representations that capture the local spatial features of different images and their inter-relational structural information in each input episode, thus enabling the model to generalize better to new categories with only a few samples.

19
26 Apr 2023
Paper
Code
Contact us on: hello@paperswithcode.com . Papers With Code is a free resource with all data licensed under CC-BY-SA.
Terms Data policy Cookies policy