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.
@article{arxiv.2402.05398,
title = {On the Effect of Image Resolution on Semantic Segmentation},
author = {Ritambhara Singh and Abhishek Jain and Pietro Perona and Shivani Agarwal and Junfeng Yang},
journal= {arXiv preprint arXiv:2402.05398},
year = {2024}
}
Comments
arXiv admin note: text overlap with arXiv:2209.08667 by other authors