CVMar 11, 2020

Equalization Loss for Long-Tailed Object Recognition

arXiv:2003.05176v2539 citationsHas Code
AI Analysis

This addresses the challenge of recognizing rare objects in large vocabulary datasets, which is crucial for applications like autonomous driving and surveillance, and is an incremental improvement over existing methods.

The paper tackles the problem of poor performance on long-tailed object recognition datasets like LVIS by proposing an equalization loss that ignores discouraging gradients for rare categories, achieving AP gains of 4.1% and 4.8% for rare and common categories compared to a baseline.

Object recognition techniques using convolutional neural networks (CNN) have achieved great success. However, state-of-the-art object detection methods still perform poorly on large vocabulary and long-tailed datasets, e.g. LVIS. In this work, we analyze this problem from a novel perspective: each positive sample of one category can be seen as a negative sample for other categories, making the tail categories receive more discouraging gradients. Based on it, we propose a simple but effective loss, named equalization loss, to tackle the problem of long-tailed rare categories by simply ignoring those gradients for rare categories. The equalization loss protects the learning of rare categories from being at a disadvantage during the network parameter updating. Thus the model is capable of learning better discriminative features for objects of rare classes. Without any bells and whistles, our method achieves AP gains of 4.1% and 4.8% for the rare and common categories on the challenging LVIS benchmark, compared to the Mask R-CNN baseline. With the utilization of the effective equalization loss, we finally won the 1st place in the LVIS Challenge 2019. Code has been made available at: https: //github.com/tztztztztz/eql.detectron2

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes