Towards Balanced Learning for Instance Recognition

by   Jiangmiao Pang, et al.
SenseTime Corporation
The University of Sydney
Zhejiang University
The Chinese University of Hong Kong

Instance recognition is rapidly advanced along with the developments of various deep convolutional neural networks. Compared to the architectures of networks, the training process, which is also crucial to the success of detectors, has received relatively less attention. In this work, we carefully revisit the standard training practice of detectors, and find that the detection performance is often limited by the imbalance during the training process, which generally consists in three levels - sample level, feature level, and objective level. To mitigate the adverse effects caused thereby, we propose Libra R-CNN, a simple yet effective framework towards balanced learning for instance recognition. It integrates IoU-balanced sampling, balanced feature pyramid, and objective re-weighting, respectively for reducing the imbalance at sample, feature, and objective level. Extensive experiments conducted on MS COCO, LVIS and Pascal VOC datasets prove the effectiveness of the overall balanced design.


page 4

page 5

page 11

page 12

page 13

page 14


Libra R-CNN: Towards Balanced Learning for Object Detection

Compared with model architectures, the training process, which is also c...

Dynamic Multi-Scale Loss Optimization for Object Detection

With the continuous improvement of the performance of object detectors v...

Balance-Oriented Focal Loss with Linear Scheduling for Anchor Free Object Detection

Most existing object detectors suffer from class imbalance problems that...

ProbaNet: Proposal-balanced Network for Object Detection

Candidate object proposals generated by object detectors based on convol...

Gaussian Guided IoU: A Better Metric for Balanced Learning on Object Detection

For most of the anchor-based detectors, Intersection over Union(IoU) is ...

Data Augmentation for Object Detection via Progressive and Selective Instance-Switching

Collection of massive well-annotated samples is effective in improving o...

DINF: Dynamic Instance Noise Filter for Occluded Pedestrian Detection

Occlusion issue is the biggest challenge in pedestrian detection. RCNN-b...

Please sign up or login with your details

Forgot password? Click here to reset