Overcoming Classifier Imbalance for Long-tail Object Detection with Balanced Group Softmax

06/18/2020
by   Yu Li, et al.
12

Solving long-tail large vocabulary object detection with deep learning based models is a challenging and demanding task, which is however under-explored.In this work, we provide the first systematic analysis on the underperformance of state-of-the-art models in front of long-tail distribution. We find existing detection methods are unable to model few-shot classes when the dataset is extremely skewed, which can result in classifier imbalance in terms of parameter magnitude. Directly adapting long-tail classification models to detection frameworks can not solve this problem due to the intrinsic difference between detection and classification.In this work, we propose a novel balanced group softmax (BAGS) module for balancing the classifiers within the detection frameworks through group-wise training. It implicitly modulates the training process for the head and tail classes and ensures they are both sufficiently trained, without requiring any extra sampling for the instances from the tail classes.Extensive experiments on the very recent long-tail large vocabulary object recognition benchmark LVIS show that our proposed BAGS significantly improves the performance of detectors with various backbones and frameworks on both object detection and instance segmentation. It beats all state-of-the-art methods transferred from long-tail image classification and establishes new state-of-the-art.Code is available at https://github.com/FishYuLi/BalancedGroupSoftmax.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/23/2020

The Devil is in Classification: A Simple Framework for Long-tail Instance Segmentation

Most existing object instance detection and segmentation models only wor...
research
11/10/2021

Feature Generation for Long-tail Classification

The visual world naturally exhibits an imbalance in the number of object...
research
03/31/2022

Logit Normalization for Long-tail Object Detection

Real-world data exhibiting skewed distributions pose a serious challenge...
research
06/24/2022

Bag of Tricks for Long-Tail Visual Recognition of Animal Species in Camera Trap Images

Camera traps are a strategy for monitoring wildlife that collects a larg...
research
10/29/2019

Classification Calibration for Long-tail Instance Segmentation

Remarkable progress has been made in object instance detection and segme...
research
01/23/2023

Long-tail Detection with Effective Class-Margins

Large-scale object detection and instance segmentation face a severe dat...
research
08/13/2020

Forest R-CNN: Large-Vocabulary Long-Tailed Object Detection and Instance Segmentation

Despite the previous success of object analysis, detecting and segmentin...

Please sign up or login with your details

Forgot password? Click here to reset