Year: 2024
Type: preprint
Abstract: High-resolution semantic segmentation requires substantial computational resources. Traditional approaches in the field typically downscale the input images before processing and then upscale the low-resolution outputs back to their original dimensions. While this strategy effectively identifies broad regions, it often misses finer details. In this study, we demonstrate that a streamlined model capable of directly producing high-resolution segmentations can match the performance of more complex systems that generate lower-resolution results. By simplifying the network architecture, we enable the processing of images at their native resolution. Our approach leverages a bottom-up information propagation technique across various scales, which we have empirically shown to enhance segmentation accuracy. We have rigorously tested our method using leading-edge semantic segmentation datasets. Specifically, for the Cityscapes dataset, we further boost accuracy by applying the Noisy Student Training technique.
Source: arXiv (Cornell University)
Authors: Singh, Ritambhara, Jain, Abhishek, Perona, Pietro, Agarwal, Shivani, Yang, Junfeng
Institution: Duke University
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4391709565