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

07/23/2020
by   PetsTime, et al.
0

Most existing object instance detection and segmentation models only work well on fairly balanced benchmarks where per-category training sample numbers are comparable, such as COCO. They tend to suffer performance drop on realistic datasets that are usually long-tailed. This work aims to study and address such open challenges. Specifically, we systematically investigate performance drop of the state-of-the-art two-stage instance segmentation model Mask R-CNN on the recent long-tail LVIS dataset, and unveil that a major cause is the inaccurate classification of object proposals. Based on such an observation, we first consider various techniques for improving long-tail classification performance which indeed enhance instance segmentation results. We then propose a simple calibration framework to more effectively alleviate classification head bias with a bi-level class balanced sampling approach. Without bells and whistles, it significantly boosts the performance of instance segmentation for tail classes on the recent LVIS dataset and our sampled COCO-LT dataset. Our analysis provides useful insights for solving long-tail instance detection and segmentation problems, and the straightforward SimCal method can serve as a simple but strong baseline. With the method we have won the 2019 LVIS challenge. Codes and models are available at <https://github.com/twangnh/SimCal>.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/29/2019

Classification Calibration for Long-tail Instance Segmentation

Remarkable progress has been made in object instance detection and segme...
research
06/18/2020

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

Solving long-tail large vocabulary object detection with deep learning b...
research
03/30/2021

Distribution Alignment: A Unified Framework for Long-tail Visual Recognition

Despite the recent success of deep neural networks, it remains challengi...
research
08/17/2021

Exploring Classification Equilibrium in Long-Tailed Object Detection

The conventional detectors tend to make imbalanced classification and su...
research
02/25/2021

FASA: Feature Augmentation and Sampling Adaptation for Long-Tailed Instance Segmentation

Recent methods for long-tailed instance segmentation still struggle on r...
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...
research
08/08/2023

1st Place Solution for CVPR2023 BURST Long Tail and Open World Challenges

Currently, Video Instance Segmentation (VIS) aims at segmenting and cate...

Please sign up or login with your details

Forgot password? Click here to reset