RepMet: Representative-Based Metric Learning for Classification and Few-Shot Object Detection
Distance metric learning (DML) has been successfully applied to object classification, both in the standard regime of rich training data and in the few-shot scenario, where each category is represented by only a few examples. In this work, we propose a new method for DML that simultaneously learns the backbone network parameters, the embedding space, and the multi-modal distribution of each of the training categories in that space, in a single end-to-end training process. Our approach outperforms state-of-the-art methods for DML-based object classification on a variety of standard fine-grained datasets. Furthermore, we demonstrate the effectiveness of our approach on the problem of few-shot object detection, by incorporating the proposed DML architecture as a classification head into a standard object detection model. We achieve the best results on the ImageNet-LOC dataset compared to strong baselines, when only a few training examples are available. We also offer the community a new episodic benchmark based on the ImageNet dataset for the few-shot object detection task.
Code (1)
Tasks
ClassificationFew-Shot Object DetectionGeneral ClassificationMetric LearningObjectobject-detectionObject DetectionSimilar Papers 제목 키워드 기반
Restoring Negative Information in Few-Shot Object Detection
Few-shot learning has recently emerged as a new challenge in the deep learning field: unlike conventional methods that train the deep neural networks (DNNs) with a large number of labeled data, it asks for the generaliza…
Few-Shot LearningFew-Shot Object Detectionimage-classificationImage Classification+4RepMet: Representative-based metric learning for classification and one-shot object detection
Distance metric learning (DML) has been successfully applied to object classification, both in the standard regime of rich training data and in the few-shot scenario, where each category is represented by only a few exam…
ClassificationFew-Shot Object DetectionGeneral ClassificationMetric Learning+4Discriminative Few-Shot Learning Based on Directional Statistics
Metric-based few-shot learning methods try to overcome the difficulty due to the lack of training examples by learning embedding to make comparison easy. We propose a novel algorithm to generate class representatives for…
Few-Shot LearningGeneral ClassificationGenerating Representative Samples for Few-Shot Classification
Few-shot learning (FSL) aims to learn new categories with a few visual samples per class. Few-shot class representations are often biased due to data scarcity. To mitigate this issue, we propose to generate visual sample…
Few-Shot LearningGeneral ClassificationDisambiguation of One-Shot Visual Classification Tasks: A Simplex-Based Approach
The field of visual few-shot classification aims at transferring the state-of-the-art performance of deep learning visual systems onto tasks where only a very limited number of training samples are available. The main so…