Zobrazeno 1 - 10
of 1 233
pro vyhledávání: '"Tieliang An"'
Publikováno v:
Geofluids, Vol 2023 (2023)
Various diseases and failures inevitably appear on expressway roadways in water-rich strata under the long-term erosion of water. It is very difficult to support the surrounding rock of a water-rich roadway because water will corrode the anchorage bo
Externí odkaz:
https://doaj.org/article/3a7d80387a744321a0079d7e168642d8
Classifier-Free Guidance (CFG), which combines the conditional and unconditional score functions with two coefficients summing to one, serves as a practical technique for diffusion model sampling. Theoretically, however, denoising with CFG cannot be
Externí odkaz:
http://arxiv.org/abs/2410.18737
Non-maximum suppression (NMS) is an indispensable post-processing step in object detection. With the continuous optimization of network models, NMS has become the ``last mile'' to enhance the efficiency of object detection. This paper systematically
Externí odkaz:
http://arxiv.org/abs/2409.20520
Autor:
Wang, Jiahao, Yan, Caixia, Zhang, Weizhan, Lin, Haonan, Wang, Mengmeng, Dai, Guang, Gong, Tieliang, Sun, Hao, Wang, Jingdong
Text-to-image diffusion models significantly enhance the efficiency of artistic creation with high-fidelity image generation. However, in typical application scenarios like comic book production, they can neither place each subject into its expected
Externí odkaz:
http://arxiv.org/abs/2409.04801
Modern GPUs incorporate specialized matrix units such as Tensor Cores to accelerate GEMM operations central to deep learning workloads. However, existing matrix unit designs are tightly coupled to the SIMT core, limiting the size and energy efficienc
Externí odkaz:
http://arxiv.org/abs/2408.12073
Domain generalization aims to learn invariance across multiple training domains, thereby enhancing generalization against out-of-distribution data. While gradient or representation matching algorithms have achieved remarkable success, these methods g
Externí odkaz:
http://arxiv.org/abs/2406.09745
Autor:
Wang, Jiahao, Yan, Caixia, Lin, Haonan, Zhang, Weizhan, Wang, Mengmeng, Gong, Tieliang, Dai, Guang, Sun, Hao
Text-to-image diffusion models benefit artists with high-quality image generation. Yet their stochastic nature hinders artists from creating consistent images of the same subject. Existing methods try to tackle this challenge and generate consistent
Externí odkaz:
http://arxiv.org/abs/2404.10267
Publikováno v:
International Journal of Distributed Sensor Networks, Vol 15 (2019)
Understanding the acoustic emission effects on bolts under cyclic loading is of great significance for the support of roadways. The presented research focuses on the acoustic emission characteristics of bolts under cyclic loading. The following main
Externí odkaz:
https://doaj.org/article/ae57aabe6613438facfa9c5271c02bb8
Publikováno v:
Advances in Civil Engineering, Vol 2019 (2019)
With the recovery of the wind oxidation zone in 13116 working face of Gubei Coal Mine as the engineering background, the occurrence condition of coal seam and the bedrock wind oxidation zone characteristics were analyzed. On this basis, the time-vary
Externí odkaz:
https://doaj.org/article/2f3c1583030d48a49c5e31b8f09886ad
Recently, information theoretic analysis has become a popular framework for understanding the generalization behavior of deep neural networks. It allows a direct analysis for stochastic gradient/Langevin descent (SGD/SGLD) learning algorithms without
Externí odkaz:
http://arxiv.org/abs/2305.01143