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. Our experiments 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.

Abstract: A method of a graphics-processing unit (GPU) for tile-based rendering of a display area and a graphics-processing apparatus are provided. The method includes the steps of computing vertex positions of a plurality of vertexes, wherein the first vertex corresponds to a first thread and the second vertex corresponds to a second thread; determining whether a thread merge condition is satisfied; merging the first thread and the second thread to a thread group when determining that the thread merge condition is satisfied; computing vertex varyings of the plurality of vertexes, wherein when the first thread and the second thread are merged to the thread group, a varying of the first vertex and a varying of the second vertex are computed with respect to a program counter.

Abstract: A graphics processing system includes a decision logic and a varying buffer control circuit. The decision logic sets a control signal by checking at least one criterion, wherein the at least one criterion includes a first criterion, and a checking result of the first criterion depends on a size of a primitive. The varying buffer control circuit refers to the control signal to determine whether to store varying variables of the primitive into a varying buffer.

Abstract: A method of a graphics-processing unit (GPU) for tile-based rendering of a display area and a graphics-processing apparatus are provided. The method includes the steps of computing vertex positions of a plurality of vertexes, wherein the first vertex corresponds to a first thread and the second vertex corresponds to a second thread; determining whether a thread merge condition is satisfied; merging the first thread and the second thread to a thread group when determining that the thread merge condition is satisfied; computing vertex varyings of the plurality of vertexes, wherein when the first thread and the second thread are merged to the thread group, a varying of the first vertex and a varying of the second vertex are computed with respect to a program counter.

Abstract: A graphics processing system includes a decision logic and a varying buffer control circuit. The decision logic sets a control signal by checking at least one criterion, wherein the at least one criterion includes a first criterion, and a checking result of the first criterion depends on a size of a primitive. The varying buffer control circuit refers to the control signal to determine whether to store varying variables of the primitive into a varying buffer.