Scaling Semantic Segmentation Beyond 1K Classes on a Single GPU

12/14/2020
by   Shipra Jain, et al.
0

The state-of-the-art object detection and image classification methods can perform impressively on more than 9k and 10k classes, respectively. In contrast, the number of classes in semantic segmentation datasets is relatively limited. This is not surprising when the restrictions caused by the lack of labeled data and high computation demand for segmentation are considered. In this paper, we propose a novel training methodology to train and scale the existing semantic segmentation models for a large number of semantic classes without increasing the memory overhead. In our embedding-based scalable segmentation approach, we reduce the space complexity of the segmentation model's output from O(C) to O(1), propose an approximation method for ground-truth class probability, and use it to compute cross-entropy loss. The proposed approach is general and can be adopted by any state-of-the-art segmentation model to gracefully scale it for any number of semantic classes with only one GPU. Our approach achieves similar, and in some cases, even better mIoU for Cityscapes, Pascal VOC, ADE20k, COCO-Stuff10k datasets when adopted to DeeplabV3+ model with different backbones. We demonstrate a clear benefit of our approach on a dataset with 1284 classes, bootstrapped from LVIS and COCO annotations, with three times better mIoU than the DeeplabV3+ model.

READ FULL TEXT

page 8

page 13

page 16

page 17

research
11/25/2016

Semantic Segmentation using Adversarial Networks

Adversarial training has been shown to produce state of the art results ...
research
08/01/2018

A Network Structure to Explicitly Reduce Confusion Errors in Semantic Segmentation

Confusing classes that are ubiquitous in real world often degrade perfor...
research
04/26/2023

Compensation Learning in Semantic Segmentation

Label noise and ambiguities between similar classes are challenging prob...
research
11/17/2019

Learning with Hierarchical Complement Objective

Label hierarchies widely exist in many vision-related problems, ranging ...
research
08/13/2018

Fast, Better Training Trick -- Random Gradient

In this paper, we will show an unprecedented method to accelerate traini...
research
07/17/2020

Edge-Preserving Guided Semantic Segmentation for VIPriors Challenge

Semantic segmentation is one of the most attractive research fields in c...
research
08/04/2021

Specialize and Fuse: Pyramidal Output Representation for Semantic Segmentation

We present a novel pyramidal output representation to ensure parsimony w...

Please sign up or login with your details

Forgot password? Click here to reset