Search Results for author: Jia Wan

Found 12 papers, 2 papers with code

Residual Regression With Semantic Prior for Crowd Counting

1 code implementation CVPR 2019 Jia Wan, Wenhan Luo, Baoyuan Wu, Antoni B. Chan, Wei Liu

We also observe that the adversarial loss can be used to improve the quality of predicted density maps, thus leading to an improvement in crowd counting.

Crowd Counting regression

Adaptive Density Map Generation for Crowd Counting

no code implementations ICCV 2019 Jia Wan, Antoni Chan

In particular, the density map could be considered as an intermediate representation used to train a crowd counting network.

Crowd Counting

Fine-Grained Crowd Counting

no code implementations13 Jul 2020 Jia Wan, Nikil Senthil Kumar, Antoni B. Chan

Second, we propose a complementary attention model to share information between the two branches.

Crowd Counting Management +1

Modeling Noisy Annotations for Crowd Counting

no code implementations NeurIPS 2020 Jia Wan, Antoni Chan

The annotation noise in crowd counting is not modeled in traditional crowd counting algorithms based on crowd density maps.

Crowd Counting

Weight Rescaling: Effective and Robust Regularization for Deep Neural Networks with Batch Normalization

no code implementations6 Feb 2021 Ziquan Liu, Yufei Cui, Jia Wan, Yu Mao, Antoni B. Chan

On the one hand, when the non-adaptive learning rate e. g. SGD with momentum is used, the effective learning rate continues to increase even after the initial training stage, which leads to an overfitting effect in many neural architectures.

Crowd Counting Image Classification +3

Progressive Unsupervised Learning for Visual Object Tracking

no code implementations CVPR 2021 Qiangqiang Wu, Jia Wan, Antoni B. Chan

In this paper, we propose a progressive unsupervised learning (PUL) framework, which entirely removes the need for annotated training videos in visual tracking.

Contrastive Learning Object +2

A Generalized Loss Function for Crowd Counting and Localization

no code implementations CVPR 2021 Jia Wan, Ziquan Liu, Antoni B. Chan

In this paper, we investigate learning the density map representation through an unbalanced optimal transport problem, and propose a generalized loss function to learn density maps for crowd counting and localization.

Crowd Counting

Crowd Counting in the Frequency Domain

1 code implementation CVPR 2022 Weibo Shu, Jia Wan, Kay Chen Tan, Sam Kwong, Antoni B. Chan

By transforming the density map into the frequency domain and using the nice properties of the characteristic function, we propose a novel method that is simple, effective, and efficient.

Crowd Counting

Diffusion-based Data Augmentation for Object Counting Problems

no code implementations25 Jan 2024 Zhen Wang, Yuelei Li, Jia Wan, Nuno Vasconcelos

Our proposed smoothed density map input for ControlNet significantly improves ControlNet's performance in generating crowds in the correct locations.

Crowd Counting Data Augmentation +2

TriSAM: Tri-Plane SAM for zero-shot cortical blood vessel segmentation in VEM images

no code implementations25 Jan 2024 Jia Wan, Wanhua Li, Atmadeep Banerjee, Jason Ken Adhinarta, Evelina Sjostedt, Jingpeng Wu, Jeff Lichtman, Hanspeter Pfister, Donglai Wei

Furthermore, we developed a zero-shot cortical blood vessel segmentation method named TriSAM, which leverages the powerful segmentation model SAM for 3D segmentation.

Benchmarking Segmentation

Analysing the Sample Complexity of Opponent Shaping

no code implementations8 Feb 2024 Kitty Fung, Qizhen Zhang, Chris Lu, Jia Wan, Timon Willi, Jakob Foerster

Providing theoretical guarantees for M-FOS is hard because A) there is little literature on theoretical sample complexity bounds for meta-reinforcement learning B) M-FOS operates in continuous state and action spaces, so theoretical analysis is challenging.

Meta Reinforcement Learning

Robust Unsupervised Crowd Counting and Localization with Adaptive Resolution SAM

no code implementations27 Feb 2024 Jia Wan, Qiangqiang Wu, Wei Lin, Antoni B. Chan

The existing crowd counting models require extensive training data, which is time-consuming to annotate.

Crowd Counting

Cannot find the paper you are looking for? You can Submit a new open access paper.