TADAM improves few-shot learning by task-dependent metric scaling.
problem Improving few-shot learning models with limited data.
method Task-dependent metric scaling and co-training.
result State-of-the-art performance on mini-Imagenet and new CIFAR100 dataset.
MetaNet learns meta-level knowledge for rapid generalization on new concepts.
problem Rapid generalization on new concepts with small training data.
method Meta learning method that learns meta-level knowledge across tasks and shifts inductive biases.
result MetaNet achieves near human-level performance and outperforms baseline approaches by up to 6%.
A new model trains prior and encoder/decoder networks simultaneously for efficient generation.
problem Complex autoregressive prior in VQ-VAE models leads to slow generation.
method Builds a diffusion bridge between continuous and non-informative prior distributions.
result Model is competitive and efficient in optimization and sampling.
Novel loss function improves few-shot classification performance.
problem Few-shot classification struggles with embedding space for new classes.
method Proposes self-compacting softmax loss (SSL) to prevent embedding space fullness.
result SSL leads to significant improvement in state-of-the-art performance.
Automated meta-learning improves model performance on small datasets.
problem Improving machine learning model performance on limited data.
method Gradient-based meta-learning combined with automated neural architecture search.
result Automatically found meta-learner achieved 74.65% accuracy on 5-shot 5-way Mini-ImageNet, 11.54% better than MAML.
ProtoTransfer learns from unlabeled data to classify unseen tasks.
problem Few-shot classification with limited labeled data.
method Self-supervised prototypical transfer learning.
result ProtoTransfer outperforms unsupervised meta-learning methods.
A new DR formulation improves metric learning for faster and more stable performance.
problem Learning embeddings for class separation in metric learning.
method Distance-ratio (DR) formulation for metric learning.
result DR formulation achieves improved or comparable generalization performances.
Study shows fine-tuning outperforms few-shot learning algorithms in low-resolution datasets.
problem Learning novel classes with limited examples in machine learning.
method Fine-tuning networks with low learning rates and adaptive optimizers, updating entire network for domain shifts.
result Fine-tuning achieves higher accuracy than common few-shot learning algorithms in 1-shot and 5-shot tasks.
Unified neural and associative memory for one-shot learning.
problem One-shot learning with limited data.
method Jointly learns data representation and task binding via slow and fast weights.
result State-of-the-art results on one-shot learning benchmarks.
Algorithm learns from multiple tasks to improve few-shot learning accuracy.
problem Few-shot learning accuracy in transfer learning.
method Variational Bayes neural networks for accumulating knowledge across tasks.
result 74.5% accuracy on 5-shot learning in Mini-Imagenet, new state of the art.
Develops robust few-shot learning models resistant to adversarial attacks.
problem Adversarial vulnerability in few-shot learning models.
method Adversarial Querying (AQ) algorithm for robust meta-learners.
result Achieves superior robust performance on few-shot image classification tasks.
Bayesian meta-learning algorithm improves model calibration and accuracy.
problem Improving model calibration and accuracy in few-shot learning.
method Gradient-based variational inference to learn model parameter distributions.
result State-of-the-art calibration and classification results on few-shot benchmarks.
Enhances few-shot image classification using unlabelled examples.
problem Few-shot image classification with limited labeled data.
method Transductive meta-learning combining soft k-means clustering and neural feature extractor.
result State-of-the-art performance on Meta-Dataset, mini-ImageNet, and tiered-ImageNet benchmarks.
A new method for few-shot learning using directional statistics.
problem Few-shot classification with limited training data.
method Generates class representatives using a mixture of von Mises-Fisher distributions to capture inter-class correlation.
result Outperforms other methods in miniImageNet and tieredImageNet datasets.
New PAC-Bayes meta-learning method improves few-shot learning accuracy and calibration.
problem Few-shot learning with limited data.
method PAC-Bayes framework extended to meta-learning, estimating task-specific posteriors.
result State-of-the-art calibration and classification results on benchmarks.
VIABLE learns a loss function for better few-shot learning.
problem Few-shot learning underfits with standard loss functions.
method Meta-learning to learn a differentiable loss function.
result Learning a relational loss function improves performance and sample efficiency.
Infinite mixture prototypes adapt to complex data for few-shot learning.
problem Few-shot learning with complex data distributions.
method Adaptive representation of classes by clusters, inferring cluster number.
result 25% absolute accuracy improvement on alphabets, state-of-the-art semi-supervised clustering.
Unified RL meta-learning framework for few-shot optimization.
problem Few-shot learning optimization problems.
method Generic RL meta-learning framework that learns optimal optimization algorithms.
result Significantly improved performance on few-shot tasks.
New algorithm constructs PAC prediction sets for meta-learning.
problem Uncertainty quantification in safety-critical systems.
method Proposes a novel algorithm to construct PAC prediction sets.
result Prediction sets satisfy a PAC guarantee with high probability over future tasks.
Sharp-MAML improves MAML by reducing saddle points in few-shot learning.
problem Challenges in optimizing MAML due to complex loss landscape.
method Sharpness-aware minimization applied to MAML.
result Sharp-MAML and its variant outperform plain MAML on few-shot learning tasks.
Novel GNN model tackles few-shot learning with improved performance.
problem Few-shot learning with GNN suffers from over-fitting and over-smoothing.
method Proposes Attentive GNN with triple-attention mechanism.
result Improves GNN performance for few-shot learning tasks.
Baseline for few-shot image classification outperforms state-of-the-art.
problem Few-shot image classification challenges.
method Fine-tuning deep networks trained with cross-entropy loss, transductively.
result Outperforms state-of-the-art on various datasets.
A simple approach improves performance on both past and future tasks in lifelong learning.
problem Forgetting in lifelong learning, where performance on past tasks degrades when learning new tasks.
method Representation ensembling to improve performance on both future and past tasks.
result Representation ensembling demonstrates both forward and backward transfer across various datasets.
AAL method generates few-shot tasks from unlabeled data for unsupervised few-shot learning.
problem Lack of unsupervised few-shot learning methods.
method Randomly label a subset of images, apply data augmentation, and use generated labels for target sets.
result Learned models achieve good generalization on Omniglot and Mini-Imagenet.
New method improves FO-BLO convergence without increasing memory or time complexity.
problem Lack of theoretical understanding of FO-BLO convergence.
method Unbiased first-order bilevel optimization (UFO-BLO) to improve convergence.
result Theoretical guarantee of convergence for FO-BLO-based stochastic optimization.
Meta-learning framework improves model performance on few-shot classification tasks.
problem Improving model performance on few-shot classification tasks.
method Empirical Bayes formulation with synthetic gradients for transductive meta-learning.
result Meta-learning framework outperforms previous state-of-the-art methods on benchmarks.
A proxy network for few-shot learning improves model generalization.
problem Training models with limited data for new classes.
method Meta-learning architecture with a proxy network that learns class representatives and distance metrics.
result The proxy network outperforms state-of-the-art methods in few-shot learning tasks.
Improves few-shot learning with Manifold Mixup and self-supervised features.
problem Learning robust representations for unseen classes with few labeled examples.
method Combines self-supervised learning and Manifold Mixup regularization.
result Significantly improves few-shot learning performance across various datasets.
Deep kernels learn from embeddings to capture data similarity efficiently.
problem Capturing similarity between high-dimensional data points with small labeled data.
method Probabilistic neural network to learn deep kernels on probabilistic embeddings.
result Our approach outperforms state-of-the-art GP kernel learning in various settings.
A new method for automatically learning metric scaling in metric-based meta-learning.
problem Lack of principled method for learning metric scaling parameter.
method Developed a variational metric scaling framework for automatic metric scaling parameter learning.
result Consistently improves the performance of existing metric-based meta-algorithms.
Improved few-shot learning with unlabeled data using random walks.
problem Few-shot learning with limited labeled data.
method Prototypical Random Walk Networks (PRWN) with semi-supervised loss.
result Significant performance improvements in most benchmarks.
A new framework improves few-shot classification by learning to generalize to unseen classes.
problem Training metric-based meta-learning approaches for few-shot classification often fails to generalize to unseen classes.
method Proposes a bilevel optimization framework to explicitly constrain meta-training to reduce unseen classification error.
result Significantly improves performance on unseen classes compared to episodic training.
SCA learns to learn from target-set examples, improving few-shot learning performance.
problem Limited labelled examples in few-shot learning tasks.
method SCA learns a label-free loss function via self-critique and adapts the base-model for new tasks.
result SCA achieves substantially reduced error-rates and state-of-the-art performance.
This paper bridges MTL and meta-learning, showing their shared structure and efficiency.
problem Improving generalization and adaptation in multi-task and few-shot learning.
method Theoretical analysis and empirical investigation of MTL and gradient-based meta-learning.
result MTL and GBML share similar optimization formulations and predictions over unseen tasks.
Random convolutional neural network improves image classification and retrieval.
problem Improving image classification and retrieval performance.
method Random depthwise signed convolutional neural network.
result Higher accuracy in image classification and retrieval compared to baseline models.