GRSDet: Learning to Generate Local Reverse Samples for Few-shot Object Detection
Authors:
Preprint
Abstract
Few-shot object detection (FSOD) aims to achieve object detection only using a few novel class training data. Most of the existing methods usually adopt a transfer-learning strategy to construct the novel class distribution by transferring the base class knowledge. However, this direct way easily results in confusion between the novel class and other similar categories in the decision space. To address the problem, we propose generating local reverse samples (LRSamples) in Prototype Reference Frames to adaptively adjust the center position and boundary range of the novel class distribution to learn more discriminative novel class samples for FSOD. Firstly, we propose a Center Calibration Variance Augmentation (CCVA) module, which contains the selection rule of LRSamples, the generator of LRSamples, and augmentation on the calibrated distribution centers. Specifically, we design an intra-class feature converter (IFC) as the generator of CCVA to learn the selecting rule. By transferring the knowledge of IFC from the base training to fine-tuning, the IFC generates plentiful novel samples to calibrate the novel class distribution. Moreover, we propose a Feature Density Boundary Optimization (FDBO) module to adaptively adjust the importance of samples depending on their distance from the decision boundary. It can emphasize the importance of the high-density area of the similar class (closer decision boundary area) and reduce the weight of the low-density area of the similar class (farther decision boundary area), thus optimizing a clearer decision boundary for each category. We conduct extensive experiments to demonstrate the effectiveness of our proposed method. Our method achieves consistent improvement on the Pascal VOC and MS COCO datasets based on DeFRCN and MFDC baselines.Keywords
All Related Versions
This publication has 12 references indexed in Scilit:
- MGML: Momentum group meta-learning for few-shot image classificationNeurocomputing, 2022
- Augmentative contrastive learning for one-shot object detectionNeurocomputing, 2022
- Sampling-invariant fully metric learning for few-shot object detectionNeurocomputing, 2022
- Query Adaptive Few-Shot Object Detection with Heterogeneous Graph Convolutional Networks2021
- Universal-Prototype Enhancing for Few-Shot Object Detection2021
- DeFRCN: Decoupled Faster R-CNN for Few-Shot Object Detection2021
- Learning Dynamic Alignment via Meta-filter for Few-shot Learning2021
- RepMet: Representative-Based Metric Learning for Classification and Few-Shot Object Detection2019
- Low-Shot Visual Recognition by Shrinking and Hallucinating Features2017
- The Pascal Visual Object Classes (VOC) ChallengeInternational Journal of Computer Vision, 2009