no code implementations • 22 Mar 2024 • Hanrong Ye, Dan Xu
It designs a joint diffusion and denoising paradigm to model a potential noisy distribution in the task prediction or feature maps and generate rectified outputs for different tasks.
no code implementations • 6 Nov 2023 • Hanrong Ye, Jason Kuen, Qing Liu, Zhe Lin, Brian Price, Dan Xu
On the highly competitive ADE20K and COCO benchmarks, our data generation method markedly improves the performance of state-of-the-art segmentation models in semantic segmentation, panoptic segmentation, and instance segmentation.
1 code implementation • ICCV 2023 • Hanrong Ye, Dan Xu
Furthermore, to establish long-range modeling of the task-specific representations from different layers of TaskExpert, we design a multi-task feature memory that updates at each layer and acts as an additional feature expert for dynamic task-specific feature decoding.
no code implementations • 16 Jul 2023 • Siwei Yang, Hanrong Ye, Dan Xu
A core objective in design is how to effectively model cross-task interactions to achieve a comprehensive improvement on different tasks based on their inherent complementarity and consistency.
1 code implementation • 8 Jun 2023 • Hanrong Ye, Dan Xu
And then, we design a transformer decoder to establish spatial and cross-task interaction globally, and a novel UP-Transformer block is devised to increase the resolutions of multi-task features gradually and establish cross-task interaction at different scales.
1 code implementation • 3 Apr 2023 • Hanrong Ye, Dan Xu
TaskPrompter introduces a new multi-task benchmark based on Cityscapes-3D dataset, which requires the multi-task model to concurrently generate predictions for monocular 3D vehicle detection, semantic segmentation, and monocular depth estimation.
Ranked #1 on Monocular Depth Estimation on Cityscapes 3D
1 code implementation • 15 Mar 2022 • Hanrong Ye, Dan Xu
Multi-task dense scene understanding is a thriving research domain that requires simultaneous perception and reasoning on a series of correlated tasks with pixel-wise prediction.
Ranked #1 on Boundary Detection on NYU-Depth V2
no code implementations • 18 Nov 2020 • Bo Xiong, Yimin Huang, Hanrong Ye, Steffen Staab, Zhenguo Li
MOFA pursues several rounds of HPO, where each round alternates between exploration of hyperparameter space by factorial design and exploitation of evaluation results by factorial analysis.
1 code implementation • 11 Jul 2020 • Yimin Huang, Yu-Jun Li, Hanrong Ye, Zhenguo Li, Zhihua Zhang
The evaluation of hyperparameters, neural architectures, or data augmentation policies becomes a critical model selection problem in advanced deep learning with a large hyperparameter search space.
1 code implementation • 1 Jun 2020 • Hanrong Ye, Hong Liu, Fanyang Meng, Xia Li
As an angularly discriminative feature space is important for classifying the human images based on their embedding vectors, in this paper, we propose a novel ranking loss function, named Bi-directional Exponential Angular Triplet Loss, to help learn an angularly separable common feature space by explicitly constraining the included angles between embedding vectors.
1 code implementation • 6 Nov 2018 • Hanrong Ye, Xia Li, Hong Liu, Wei Shi, Mengyuan Liu, Qianru Sun
Rain removal aims to extract and remove rain streaks from images.
1 code implementation • 11 Aug 2018 • Bochen Guan, Hanrong Ye, Hong Liu, William A. Sethares
Estimation of the frequency and duration of logos in videos is important and challenging in the advertisement industry as a way of estimating the impact of ad purchases.