Xiaohong Zhang

TL;DR: A Mutual Encouragement Network (MENet), which includes a semantic segmentation branch and a disparity regression branch, and simultaneously generates semantic map and visual disparity, and can outperform the state-of-the-art methods on both visual disparity generation and semantic segmentsation.

TL;DR: A novel multi-level UDA model named Confidence-and-Refinement Adaptation Model (CRAM), which contains a confidence-aware entropy alignment (CEA) module and a style feature alignment (SFA) module, which achieves comparable performance with the existing state-of-the-art works with advantages in simplicity and convergence speed.

TL;DR: Zhang et al. as discussed by the authors proposed a target-targeted domain adaptation approach by focusing the training on target domain, which consists of two components: the Image-to-image Translation (IIT) module to translate the source image to target domain and the Target-Targeted Segmentation Adaptation (TSA) module, which bridges the domain gap at the segmentation map level.

TL;DR: In this article , an entropy-weighted adversarial framework is designed to enhance the discriminativeness and transferability of the presented model to the target domain via an autoencoder-based discriminator.

TL;DR: Li et al. as mentioned in this paper proposed a novel LiDAR-Camera 3D object detection method, namely the Multi-scale Spatial Transformer Network (MST-Net), which exploits an innovative spatial alignment scheme based on the projection transformer network (PTN) to mitigate the effects of the perspective view caused by sensors.