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 implementationsDatasets
Subtasks
Latest papers
Logarithm-transform aided Gaussian Sampling for Few-Shot Learning
These methods rely on transforming the distributions of experimental data to approximate Gaussian distributions for their functioning.
PRE: Vision-Language Prompt Learning with Reparameterization Encoder
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.
Language Models as Black-Box Optimizers for Vision-Language Models
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.
Cross-Image Context Matters for Bongard Problems
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.
DiffKendall: A Novel Approach for Few-Shot Learning with Differentiable Kendall's Rank Correlation
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.
Distilling Large Vision-Language Model with Out-of-Distribution Generalizability
Model distillation, the process of creating smaller, faster models that maintain the performance of larger models, is a promising direction towards the solution.
Proto-CLIP: Vision-Language Prototypical Network for Few-Shot Learning
The two encoders are used to compute prototypes of image classes for classification.
Comparing the Efficacy of Fine-Tuning and Meta-Learning for Few-Shot Policy Imitation
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.
Multistage Relation Network With Dual-Metric for Few-Shot Hyperspectral Image Classification
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.
ESPT: A Self-Supervised Episodic Spatial Pretext Task for Improving Few-Shot Learning
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.