Papers Unsupervised Few-Shot Learning
“Unsupervised Few-Shot Learning” 태그가 달린 논문 22편 · 필터 해제
MICM: Rethinking Unsupervised Pretraining for Enhanced Few-shot Learning
Humans exhibit a remarkable ability to learn quickly from a limited number of labeled samples, a capability that starkly contrasts with that of current machine learning systems. Unsupervised Few-Shot Learning (U-FSL) see…
Contrastive LearningFew-Shot LearningUnsupervised Few-Shot LearningBECLR: Batch Enhanced Contrastive Few-Shot Learning
Learning quickly from very few labeled samples is a fundamental attribute that separates machines and humans in the era of deep representation learning. Unsupervised few-shot learning (U-FSL) aspires to bridge this gap b…
Contrastive LearningFew-Shot Image ClassificationFew-Shot LearningRepresentation Learning+2Contrastive Prototypical Network with Wasserstein Confidence Penalty
Unsupervised few-shot learning aims to learn the inductive bias from unlabeled dataset for solving the novel few-shot tasks. The existing unsupervised few-shot learning models and the contrastive learning models follow a…
Contrastive LearningFew-Shot LearningInductive BiasUnsupervised Few-Shot Image Classification+1Self-Attention Message Passing for Contrastive Few-Shot Learning
Humans have a unique ability to learn new representations from just a handful of examples with little to no supervision. Deep learning models, however, require an abundance of data and supervision to perform at a satisfa…
Contrastive LearningFew-Shot LearningUnsupervised Few-Shot Image ClassificationUnsupervised Few-Shot LearningUnsupervised Few-shot Learning via Deep Laplacian Eigenmaps
Learning a new task from a handful of examples remains an open challenge in machine learning. Despite the recent progress in few-shot learning, most methods rely on supervised pretraining or meta-learning on labeled meta…
Few-Shot LearningLinear evaluationMeta-LearningSelf-Supervised Learning+2Self-Supervision Can Be a Good Few-Shot Learner
Existing few-shot learning (FSL) methods rely on training with a large labeled dataset, which prevents them from leveraging abundant unlabeled data. From an information-theoretic perspective, we propose an effective unsu…
cross-domain few-shot learningFew-Shot Image ClassificationFew-Shot LearningUnsupervised Few-Shot Image Classification+1Trip-ROMA: Self-Supervised Learning with Triplets and Random Mappings
Contrastive self-supervised learning (SSL) methods, such as MoCo and SimCLR, have achieved great success in unsupervised visual representation learning. They rely on a large number of negative pairs and thus require eith…
Few-Shot LearningRepresentation LearningSelf-Supervised LearningTriplet+1Trainable Class Prototypes for Few-Shot Learning
Metric learning is a widely used method for few shot learning in which the quality of prototypes plays a key role in the algorithm. In this paper we propose the trainable prototypes for distance measure instead of the ar…
Few-Shot LearningMetric LearningSelf-Supervised LearningUnsupervised Few-Shot Image Classification+1UVStyle-Net: Unsupervised Few-shot Learning of 3D Style Similarity Measure for B-Reps
Boundary Representations (B-Reps) are the industry standard in 3D Computer Aided Design/Manufacturing (CAD/CAM) and industrial design due to their fidelity in representing stylistic details. However, they have been ignor…
Computational EfficiencyFew-Shot LearningUnsupervised Few-Shot LearningMeta-GMVAE: Mixture of Gaussian VAE for Unsupervised Meta-Learning
Unsupervised learning aims to learn meaningful representations from unlabeled data which can captures its intrinsic structure, that can be transferred to downstream tasks. Meta-learning, whose objective is to learn to ge…
Meta-LearningUnsupervised Few-Shot Image ClassificationUnsupervised Few-Shot LearningVariational InferenceRevisiting Unsupervised Meta-Learning via the Characteristics of Few-Shot Tasks
Meta-learning has become a practical approach towards few-shot image classification, where "a strategy to learn a classifier" is meta-learned on labeled base classes and can be applied to tasks with novel classes. We rem…
Few-Shot Image ClassificationFew-Shot Learningimage-classificationImage Classification+3Shot in the Dark: Few-Shot Learning with No Base-Class Labels
Few-shot learning aims to build classifiers for new classes from a small number of labeled examples and is commonly facilitated by access to examples from a distinct set of 'base classes'. The difference in data distribu…
Few-Shot LearningInductive BiasSelf-Supervised LearningUnsupervised Few-Shot Image Classification+1Few-Shot Image Classification via Contrastive Self-Supervised Learning
Most previous few-shot learning algorithms are based on meta-training with fake few-shot tasks as training samples, where large labeled base classes are required. The trained model is also limited by the type of tasks. I…
ClassificationFew-Shot Image ClassificationFew-Shot LearningGeneral Classification+5Self-Supervised Prototypical Transfer Learning for Few-Shot Classification
Most approaches in few-shot learning rely on costly annotated data related to the goal task domain during (pre-)training. Recently, unsupervised meta-learning methods have exchanged the annotation requirement for a reduc…
ClassificationFew-Shot LearningGeneral ClassificationMeta-Learning+4Diversity Helps: Unsupervised Few-shot Learning via Distribution Shift-based Data Augmentation
Few-shot learning aims to learn a new concept when only a few training examples are available, which has been extensively explored in recent years. However, most of the current works heavily rely on a large-scale labeled…
Data AugmentationDiversityFew-Shot LearningUnsupervised Few-Shot Image Classification+1Rethinking Class Relations: Absolute-relative Supervised and Unsupervised Few-shot Learning
The majority of existing few-shot learning methods describe image relations with binary labels. However, such binary relations are insufficient to teach the network complicated real-world relations, due to the lack of de…
Few-Shot LearningRelationUnsupervised Few-Shot Image ClassificationUnsupervised Few-Shot LearningUnsupervised Few-shot Learning via Self-supervised Training
Learning from limited exemplars (few-shot learning) is a fundamental, unsolved problem that has been laboriously explored in the machine learning community. However, current few-shot learners are mostly supervised and re…
BIG-bench Machine LearningClusteringFew-Shot LearningPerson Re-Identification+2Program synthesis performance constrained by non-linear spatial relations in Synthetic Visual Reasoning Test
Despite remarkable advances in automated visual recognition by machines, some visual tasks remain challenging for machines. Fleuret et al. (2011) introduced the Synthetic Visual Reasoning Test (SVRT) to highlight this po…
Few-Shot LearningProgram SynthesisUnsupervised Few-Shot LearningVisual ReasoningUnsupervised Few Shot Learning via Self-supervised Training
Learning from limited exemplars (few-shot learning) is a fundamental, unsolved problem that has been laboriously explored in the machine learning community. However, current few-shot learners are mostly supervised and re…
Few-Shot LearningPerson Re-IdentificationUnsupervised Few-Shot LearningAssume, Augment and Learn: Unsupervised Few-Shot Meta-Learning via Random Labels and Data Augmentation
The field of few-shot learning has been laboriously explored in the supervised setting, where per-class labels are available. On the other hand, the unsupervised few-shot learning setting, where no labels of any kind are…
Data AugmentationFew-Shot LearningMeta-LearningUnsupervised Few-Shot Image Classification+1