No abstract

Many unsupervised domain adaptation (UDA) methods have been proposed to bridge the domain gap by utilizing domain invariant information. Most approaches have chosen depth as such information and achieved remarkable successes. Despite their effectiveness, using depth as domain invariant information in UDA tasks may lead to multiple issues, such as excessively high extraction costs and difficulties in achieving a reliable prediction quality. As a result, we introduce Edge Learning based Domain Adaptation (ELDA), a framework which incorporates edge information into its training process to serve as a type of domain invariant information. In our experiments, we quantitatively and qualitatively demonstrate that the incorporation of edge information is indeed beneficial and effective, and enables ELDA to outperform the contemporary state-of-the-art methods on two commonly adopted benchmarks for semantic segmentation based UDA tasks. In addition, we show that ELDA is able to better separate the feature distributions of different classes. We further provide ablation analysis to justify our design decisions.

No abstract

In this study, we present an effective method to fabricate TiO 2 -based photocathode for hydrogen production. The Pt/TiO 2 composites were synthesized by using TiO 2 nanotube arrays (TNTAs) as a support. The TNTAs were electrochemically fabricated using 20 × 18 mm 2 titanium foils as the anode. Pt ions were loaded onto the TNTAs to form Pt/TiO 2 nanocomposites for the enhancement of photoelectron-chemical performance of water splitting. The highly oriented and ordered TNTAs at about 100 nm in diameter and 17 μm in length was obtained after 8 h of anodization. The TEM images showed that Pt nanoparticles were well-dispersed on the surface of TNTAs with diameters of 1.5-5 nm. In addition, TiO 2 and Pt/TiO 2 nanotube arrays were used for photoelectrochemical water splitting in 0.5 M Na 2 SO 4 electrolyte under UV light irradiation at 10 mW/cm 2 . The photocurrent density at a overpotential of -0.65 V vs. Ag/AgCl (-0.1 V vs. RHE) by Pt/TiO 2 composite was higher than the pure TiO 2 nanotube arrays electrode. In addition, the overpotential of TNTAs in the presence of UV light was 0.1 V lower but and the hydrogen production was 1.3 times higher than that in dark. The hydrogen generation by TNTAs and Pt/TNTAs at -0.85V vs. Ag/AgCl under UV light irradiation was 1.9 and 15.5 times higher than that in dark.

In this paper, we introduce a new concept of incorporating factorized flow maps as mid-level representations, for bridging the perception and the control modules in modular learning based robotic frameworks. To investigate the advantages of factorized flow maps and examine their interplay with the other types of mid-level representations, we further develop a configurable framework, along with four different environments that contain both static and dynamic objects, for analyzing the impacts of factorized optical flow maps on the performance of deep reinforcement learning agents. Based on this framework, we report our experimental results on various scenarios, and offer a set of analyses to justify our hypothesis. Finally, we validate flow factorization in real world scenarios.