Specifically, FBSNet employs a symmetrical encoder-decoder structure with two branches, semantic information branch, and spatial detail branch.
This paper pays close attention to the cross-modality visible-infrared person re-identification (VI Re-ID) task, which aims to match human samples between visible and infrared modes.
In this work, we treat the mask occlusion as image noise and construct a joint and collaborative learning network, called JDSR-GAN, for the masked face super-resolution task.
(i) To learn more robust and discriminative features, we desire to adaptively fuse the contextual features from different layers.
In recent years, how to strike a good trade-off between accuracy and inference speed has become the core issue for real-time semantic segmentation applications, which plays a vital role in real-world scenarios such as autonomous driving systems and drones.
Recently, the single image super-resolution (SISR) approaches with deep and complex convolutional neural network structures have achieved promising performance.
LEDNet: A Lightweight Encoder-Decoder Network for Real-time Semantic Segmentation
Ranked #21 on Real-Time Semantic Segmentation on Cityscapes test