Learning from Small Sample Sets by Combining Unsupervised Meta-Training with CNNs
This work explores CNNs for the recognition of novel categories from few examples. Inspired by the transferability properties of CNNs, we introduce an additional unsupervised meta-training stage that exposes multiple top layer units to a large amount of unlabeled real-world images. By encouraging these units to learn diverse sets of low-density separators across the unlabeled data, we capture a more generic, richer description of the visual world, which decouples these units from ties to a specific set of categories. We propose an unsupervised margin maximization that jointly estimates compact high-density regions and infers low-density separators. The low-density separator (LDS) modules can be plugged into any or all of the top layers of a standard CNN architecture. The resulting CNNs significantly improve the performance in scene classification, fine-grained recognition, and action recognition with small training samples.
Code (0)
등록된 구현이 없습니다.
Tasks
Action RecognitionGeneral ClassificationScene ClassificationTemporal Action LocalizationSimilar Papers 제목 키워드 기반
Unsupervised Meta Learning With Multiview Constraints for Hyperspectral Image Small Sample set Classification
The difficulties of obtaining sufficient labeled samples have always been one of the factors hindering deep learning models from obtaining high accuracy in hyperspectral image (HSI) classification. To reduce the dependen…
Classificationdomain classificationMeta-LearningRelation NetworkMeta Pairwise Relationship Distillation for Unsupervised Person Re-Identification
Unsupervised person re-identification (Re-ID) remains challenging due to the lack of ground-truth labels. Existing methods often rely on estimated pseudo labels via iterative clustering and classification, and they a…
Person Re-IdentificationUnsupervised Person Re-IdentificationMSDA: Combining Pseudo-labeling and Self-Supervision for Unsupervised Domain Adaptation in ASR
In this work, we investigate the Meta PL unsupervised domain adaptation framework for Automatic Speech Recognition (ASR). We introduce a Multi-Stage Domain Adaptation pipeline (MSDA), a sample-efficient, two-stage adapta…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Domain AdaptationSelf-Supervised Learning+3Unsupervised Representation Learning to Aid Semi-Supervised Meta Learning
Few-shot learning or meta-learning leverages the data scarcity problem in machine learning. Traditionally, training data requires a multitude of samples and labeling for supervised learning. To address this issue, we pro…
Few-Shot LearningMeta-LearningRelation NetworkRepresentation Learning+1Unsupervised Learning via Meta-Learning
A central goal of unsupervised learning is to acquire representations from unlabeled data or experience that can be used for more effective learning of downstream tasks from modest amounts of labeled data. Many prior uns…
ClusteringDisentanglementMeta-LearningUnsupervised Few-Shot Image Classification+1