Top-Related Meta-Learning Method for Few-Shot Object Detection
Many meta-learning methods are proposed for few-shot detection. However, previous most methods have two main problems, poor detection APs, and strong bias because of imbalance and insufficient datasets. Previous works mainly alleviate these issues by additional datasets, multi-relation attention mechanisms and sub-modules. However, they require more cost. In this work, for meta-learning, we find that the main challenges focus on related or irrelevant semantic features between categories. Therefore, based on semantic features, we propose a Top-C classification loss (i.e., TCL-C) for classification task and a category-based grouping mechanism for category-based meta-features obtained by the meta-model. The TCL-C exploits the true-label prediction and the most likely C-1 false classification predictions to improve detection performance on few-shot classes. According to similar appearance (i.e., visual appearance, shape, and limbs etc.) and environment in which objects often appear, the category-based grouping mechanism splits categories into disjoint groups to make similar semantic features more compact between categories within a group and obtain more significant difference between groups, alleviating the strong bias problem and further improving detection APs. The whole training consists of the base model and the fine-tuning phases. According to grouping mechanism, we group the meta-features vectors obtained by meta-model, so that the distribution difference between groups is obvious, and the one within each group is less. Extensive experiments on Pascal VOC dataset demonstrate that ours which combines the TCL-C with category-based grouping significantly outperforms previous state-of-the-art methods for few-shot detection. Compared with previous competitive baseline, ours improves detection APs by almost 4% for few-shot detection.
Code (1)
Tasks
Few-Shot Object DetectionMeta-Learningobject-detectionObject DetectionSimilar Papers 제목 키워드 기반
Multi-Modal Few-Shot Object Detection with Meta-Learning-Based Cross-Modal Prompting
We study multi-modal few-shot object detection (FSOD) in this paper, using both few-shot visual examples and class semantic information for detection, which are complementary to each other by definition. Most of the prev…
Few-Shot LearningFew-Shot Object DetectionKnowledge DistillationMeta-Learning+3Meta-RCNN: Meta Learning for Few-Shot Object Detection
Despite significant advances in object detection in recent years, training effective detectors in a small data regime remains an open challenge. Labelling training data for object detection is extremely expensive, and th…
Cross-Domain Few-Shot Object DetectionFew-Shot Object DetectionMeta-LearningObject+3Meta-tuning Loss Functions and Data Augmentation for Few-shot Object Detection
Few-shot object detection, the problem of modelling novel object detection categories with few training instances, is an emerging topic in the area of few-shot learning and object detection. Contemporary techniques can b…
Data AugmentationFew-Shot LearningFew-Shot Object DetectionMeta-Learning+4Meta-DETR: Image-Level Few-Shot Object Detection with Inter-Class Correlation Exploitation
Few-shot object detection has been extensively investigated by incorporating meta-learning into region-based detection frameworks. Despite its success, the said paradigm is constrained by several factors, such as (i) low…
Few-Shot Object DetectionMeta-Learningobject-detectionObject Detection+1Meta-DETR: Image-Level Few-Shot Detection with Inter-Class Correlation Exploitation
Few-shot object detection has been extensively investigated by incorporating meta-learning into region-based detection frameworks. Despite its success, the said paradigm is still constrained by several factors, such as (…
Few-Shot Object DetectionMeta-LearningObjectobject-detection+1