DeepAI AI Chat
Log In Sign Up

Dynamic Feature Fusion for Semantic Edge Detection

by   Yuan Hu, et al.
National University of Singapore

Features from multiple scales can greatly benefit the semantic edge detection task if they are well fused. However, the prevalent semantic edge detection methods apply a fixed weight fusion strategy where images with different semantics are forced to share the same weights, resulting in universal fusion weights for all images and locations regardless of their different semantics or local context. In this work, we propose a novel dynamic feature fusion strategy that assigns different fusion weights for different input images and locations adaptively. This is achieved by a proposed weight learner to infer proper fusion weights over multi-level features for each location of the feature map, conditioned on the specific input. In this way, the heterogeneity in contributions made by different locations of feature maps and input images can be better considered and thus help produce more accurate and sharper edge predictions. We show that our model with the novel dynamic feature fusion is superior to fixed weight fusion and also the naïve location-invariant weight fusion methods, via comprehensive experiments on benchmarks Cityscapes and SBD. In particular, our method outperforms all existing well established methods and achieves new state-of-the-art.


Semantic Image Fusion

Image fusion methods and metrics for their evaluation have conventionall...

LE2Fusion: A novel local edge enhancement module for infrared and visible image fusion

Infrared and visible image fusion task aims to generate a fused image wh...

Learning Feature Disentanglement and Dynamic Fusion for Recaptured Image Forensic

Image recapture seriously breaks the fairness of artificial intelligent ...

Neuro-inspired edge feature fusion using Choquet integrals

It is known that the human visual system performs a hierarchical informa...

Robust Fusion for Bayesian Semantic Mapping

The integration of semantic information in a map allows robots to unders...

Unsupervised segmentation via semantic-apparent feature fusion

Foreground segmentation is an essential task in the field of image under...

Weight mechanism adding a constant in concatenation of series connect

It is a consensus that feature maps in the shallow layer are more relate...