DeepAI AI Chat
Log In Sign Up

TriangleNet: Edge Prior Augmented Network for Semantic Segmentation through Cross-Task Consistency

by   Dan Zhang, et al.

Semantic segmentation is a classic computer vision problem dedicated to labeling each pixel with its corresponding category. As a basic task for advanced tasks such as industrial quality inspection, remote sensing information extraction, medical diagnostic aid, and autonomous driving, semantic segmentation has been developed for a long time in combination with deep learning, and a lot of works have been accumulated. However, neither the classic FCN-based works nor the popular Transformer-based works have attained fine-grained localization of pixel labels, which remains the main challenge in this field. Recently, with the popularity of autonomous driving, the segmentation of road scenes has received more and more attention. Based on the cross-task consistency theory, we incorporate edge priors into semantic segmentation tasks to obtain better results. The main contribution is that we provide a model-agnostic method that improves the accuracy of semantic segmentation models with zero extra inference runtime overhead, verified on the datasets of road and non-road scenes. From our experimental results, our method can effectively improve semantic segmentation accuracy.


Superpixel clustering with deep features for unsupervised road segmentation

Vision-based autonomous driving requires classifying each pixel as corre...

An Active and Contrastive Learning Framework for Fine-Grained Off-Road Semantic Segmentation

Off-road semantic segmentation with fine-grained labels is necessary for...

Using Image Priors to Improve Scene Understanding

Semantic segmentation algorithms that can robustly segment objects acros...

Fine-Grained Off-Road Semantic Segmentation and Mapping via Contrastive Learning

Road detection or traversability analysis has been a key technique for a...

Edge-aware Plug-and-play Scheme for Semantic Segmentation

Semantic segmentation is a classic and fundamental computer vision probl...

PaRK-Detect: Towards Efficient Multi-Task Satellite Imagery Road Extraction via Patch-Wise Keypoints Detection

Automatically extracting roads from satellite imagery is a fundamental y...