Equalized Focal Loss for Dense Long-Tailed Object Detection

01/07/2022
by   Bo Li, et al.
0

Despite the recent success of long-tailed object detection, almost all long-tailed object detectors are developed based on the two-stage paradigm. In practice, one-stage detectors are more prevalent in the industry because they have a simple and fast pipeline that is easy to deploy. However, in the long-tailed scenario, this line of work has not been explored so far. In this paper, we investigate whether one-stage detectors can perform well in this case. We discover the primary obstacle that prevents one-stage detectors from achieving excellent performance is: categories suffer from different degrees of positive-negative imbalance problems under the long-tailed data distribution. The conventional focal loss balances the training process with the same modulating factor for all categories, thus failing to handle the long-tailed problem. To address this issue, we propose the Equalized Focal Loss (EFL) that rebalances the loss contribution of positive and negative samples of different categories independently according to their imbalance degrees. Specifically, EFL adopts a category-relevant modulating factor which can be adjusted dynamically by the training status of different categories. Extensive experiments conducted on the challenging LVIS v1 benchmark demonstrate the effectiveness of our proposed method. With an end-to-end training pipeline, EFL achieves 29.2 improvements on rare categories, surpassing all existing state-of-the-art methods. The code is available at https://github.com/ModelTC/EOD.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/15/2020

Equalization Loss v2: A New Gradient Balance Approach for Long-tailed Object Detection

Recently proposed decoupled training methods emerge as a dominant paradi...
research
08/07/2022

Sample hardness based gradient loss for long-tailed cervical cell detection

Due to the difficulty of cancer samples collection and annotation, cervi...
research
03/11/2020

Equalization Loss for Long-Tailed Object Recognition

Object recognition techniques using convolutional neural networks (CNN) ...
research
10/11/2022

The Equalization Losses: Gradient-Driven Training for Long-tailed Object Recognition

Long-tail distribution is widely spread in real-world applications. Due ...
research
08/04/2023

Balanced Classification: A Unified Framework for Long-Tailed Object Detection

Conventional detectors suffer from performance degradation when dealing ...
research
07/08/2023

End-to-End Supervised Multilabel Contrastive Learning

Multilabel representation learning is recognized as a challenging proble...
research
01/23/2023

Long-tail Detection with Effective Class-Margins

Large-scale object detection and instance segmentation face a severe dat...

Please sign up or login with your details

Forgot password? Click here to reset