HCNet: Hierarchical Context Network for Semantic Segmentation

no code implementations • 10 Oct 2020 • Yanwen Chong, Congchong Nie, Yulong Tao, Xiaoshu Chen, Shaoming Pan

In order to solve the above problem, we propose a hierarchical context network to differentially model homogeneous pixels with strong correlations and heterogeneous pixels with weak correlations.

Feature Correlation Semantic Segmentation

A New Dataset, Poisson GAN and AquaNet for Underwater Object Grabbing

no code implementations • 3 Mar 2020 • Chongwei Liu, Zhihui Wang, Shijie Wang, Tao Tang, Yulong Tao, Caifei Yang, Haojie Li, Xing Liu, Xin Fan

We also propose a novel Poisson-blending Generative Adversarial Network (Poisson GAN) and an efficient object detection network (AquaNet) to address two common issues within related datasets: the class-imbalance problem and the problem of mass small object, respectively.

4k Generative Adversarial Network +2