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 with no code
Feature Activation Map: Visual Explanation of Deep Learning Models for Image Classification
However, all the CAM-based methods (e. g., CAM, Grad-CAM, and Relevance-CAM) can only be used for interpreting CNN models with fully-connected (FC) layers as a classifier.
FILM: How can Few-Shot Image Classification Benefit from Pre-Trained Language Models?
Few-shot learning aims to train models that can be generalized to novel classes with only a few samples.
Distilling Self-Supervised Vision Transformers for Weakly-Supervised Few-Shot Classification & Segmentation
For this mixed setup, we propose to improve the pseudo-labels using a pseudo-label enhancer that was trained using the available ground-truth pixel-level labels.
SuSana Distancia is all you need: Enforcing class separability in metric learning via two novel distance-based loss functions for few-shot image classification
Few-shot learning is a challenging area of research that aims to learn new concepts with only a few labeled samples of data.
Strong Baselines for Parameter Efficient Few-Shot Fine-tuning
Through our controlled empirical study, we have two main findings: (i) Fine-tuning just the LayerNorm parameters (which we call LN-Tune) during few-shot adaptation is an extremely strong baseline across ViTs pre-trained with both self-supervised and supervised objectives, (ii) For self-supervised ViTs, we find that simply learning a set of scaling parameters for each attention matrix (which we call AttnScale) along with a domain-residual adapter (DRA) module leads to state-of-the-art performance (while being $\sim\!$ 9$\times$ more parameter-efficient) on MD.
Boosting Few-Shot Text Classification via Distribution Estimation
Distribution estimation has been demonstrated as one of the most effective approaches in dealing with few-shot image classification, as the low-level patterns and underlying representations can be easily transferred across different tasks in computer vision domain.
RotoGBML: Towards Out-of-Distribution Generalization for Gradient-Based Meta-Learning
OOD exacerbates inconsistencies in magnitudes and directions of task gradients, which brings challenges for GBML to optimize the meta-knowledge by minimizing the sum of task gradients in each minibatch.
Understanding and Constructing Latent Modality Structures in Multi-modal Representation Learning
Hence we advocate that the key of better performance lies in meaningful latent modality structures instead of perfect modality alignment.
CovidExpert: A Triplet Siamese Neural Network framework for the detection of COVID-19
Patients with the COVID-19 infection may have pneumonia-like symptoms as well as respiratory problems which may harm the lungs.
Explore the Power of Dropout on Few-shot Learning
The generalization power of the pre-trained model is the key for few-shot deep learning.