Few Shot Image Classification On Mini 2

Metrics

Accuracy

Results

Performance results of various models on this benchmark

Model Name	Accuracy	Paper Title	Repository
UniSiam	65.55	Self-Supervision Can Be a Good Few-Shot Learner	-
MCT	78.55	Meta-Learned Confidence for Few-shot Learning	-
R2-D2+Task Aug	65.95	Task Augmentation by Rotating for Meta-Learning	-
MSENet	66.57	Enhancing Few-Shot Image Classification through Learnable Multi-Scale Embedding and Attention Mechanisms	-
SimpleShot (CL2N-DenseNet)	64.29	SimpleShot: Revisiting Nearest-Neighbor Classification for Few-Shot Learning	-
TIM-GD	77.80	Transductive Information Maximization For Few-Shot Learning	-
CPEA	71.97	Class-Aware Patch Embedding Adaptation for Few-Shot Image Classification
TRIDENT	86.11	Transductive Decoupled Variational Inference for Few-Shot Classification	-
Transductive CNAPS	55.6	Enhancing Few-Shot Image Classification with Unlabelled Examples	-
PEMbE-NCM (inductive)	68.43	Squeezing Backbone Feature Distributions to the Max for Efficient Few-Shot Learning	-
SSFormers	67.25	Sparse Spatial Transformers for Few-Shot Learning	-
MetaOptNet-SVM+Task Aug	65.38	Task Augmentation by Rotating for Meta-Learning	-
VAMPIRE	51.54	Uncertainty in Model-Agnostic Meta-Learning using Variational Inference	-
Invariance-Equivariance	67.28	Exploring Complementary Strengths of Invariant and Equivariant Representations for Few-Shot Learning	-
ProtoNet MTM SPSA-Track	61.94	Simultaneous Perturbation Method for Multi-Task Weight Optimization in One-Shot Meta-Learning	-
DN4 (k=3)	51.24	Revisiting Local Descriptor based Image-to-Class Measure for Few-shot Learning	-
EASY 3xResNet12 (transductive)	84.04	EASY: Ensemble Augmented-Shot Y-shaped Learning: State-Of-The-Art Few-Shot Classification with Simple Ingredients	-
feat+ (ProtoNet-ResNet)	61.72	Few-Shot Learning via Embedding Adaptation with Set-to-Set Functions	-
Reptile + Transduction	49.97	On First-Order Meta-Learning Algorithms	-
adaResNet (DF)	56.88	Rapid Adaptation with Conditionally Shifted Neurons	-

0 of 105 row(s) selected.