Authors: Xi Chen, Yang Cai, Yuan Wu, Bo Xiong, Taesung Park

Published on: February 07, 2024

Impact Score: 8.3

Arxiv code: Arxiv:2402.04618

Summary

• What is new: Adaptation of MBConv blocks specifically for semantic segmentation, not just image classification.
• Why this is important: Lack of exploration of MBConv blocks for semantic segmentation tasks.
• What the research proposes: Modifying MBConv blocks within a U-Net architecture to provide equal segmentation capabilities across varying resolutions.
• Results: Achieved mean IoU scores of 84.5% and 84.0% on the Cityscapes test and validation datasets.

Technical Details

Technological frameworks used: U-Net architecture

Models used: MBConv blocks

Data used: Cityscapes dataset

Potential Impact

Automotive ADAS companies, Urban planning applications, and companies in the image processing software market

Want to implement this idea in a business?

We have generated a startup concept here: Visionary Segments.