Search Results for author: Wenjia Wang

Found 34 papers, 12 papers with code

The Surprising Effectiveness of Skip-Tuning in Diffusion Sampling

no code implementations23 Feb 2024 Jiajun Ma, Shuchen Xue, Tianyang Hu, Wenjia Wang, Zhaoqiang Liu, Zhenguo Li, Zhi-Ming Ma, Kenji Kawaguchi

Surprisingly, the improvement persists when we increase the number of sampling steps and can even surpass the best result from EDM-2 (1. 58) with only 39 NFEs (1. 57).

Image Generation

CounterCLR: Counterfactual Contrastive Learning with Non-random Missing Data in Recommendation

no code implementations8 Feb 2024 Jun Wang, Haoxuan Li, Chi Zhang, Dongxu Liang, Enyun Yu, Wenwu Ou, Wenjia Wang

Recommender systems are designed to learn user preferences from observed feedback and comprise many fundamental tasks, such as rating prediction and post-click conversion rate (pCVR) prediction.

Contrastive Learning counterfactual +3

Regret Optimality of GP-UCB

no code implementations3 Dec 2023 Wenjia Wang, Xiaowei Zhang, Lu Zou

We establish new upper bounds on both the simple and cumulative regret of GP-UCB when the objective function to optimize admits certain smoothness property.

Bayesian Optimization

MuSHRoom: Multi-Sensor Hybrid Room Dataset for Joint 3D Reconstruction and Novel View Synthesis

no code implementations5 Nov 2023 Xuqian Ren, Wenjia Wang, Dingding Cai, Tuuli Tuominen, Juho Kannala, Esa Rahtu

Metaverse technologies demand accurate, real-time, and immersive modeling on consumer-grade hardware for both non-human perception (e. g., drone/robot/autonomous car navigation) and immersive technologies like AR/VR, requiring both structural accuracy and photorealism.

3D Reconstruction Novel View Synthesis

Data Upcycling Knowledge Distillation for Image Super-Resolution

no code implementations25 Sep 2023 Yun Zhang, Wei Li, Simiao Li, Jie Hu, Hanting Chen, Hailing Wang, Zhijun Tu, Wenjia Wang, BingYi Jing, Yunhe Wang

In this paper, we put forth an approach from the perspective of effective data utilization, namely, the Data Upcycling Knowledge Distillation (DUKD), which facilitates the student model by the prior knowledge the teacher provided through the upcycled in-domain data derived from the input images.

Image Super-Resolution Knowledge Distillation +1

Learning Dense UV Completion for Human Mesh Recovery

no code implementations20 Jul 2023 Yanjun Wang, Qingping Sun, Wenjia Wang, Jun Ling, Zhongang Cai, Rong Xie, Li Song

Our method utilizes a dense correspondence map to separate visible human features and completes human features on a structured UV map dense human with an attention-based feature completion module.

Human Mesh Recovery

Random Smoothing Regularization in Kernel Gradient Descent Learning

no code implementations5 May 2023 Liang Ding, Tianyang Hu, Jiahang Jiang, Donghao Li, Wenjia Wang, Yuan YAO

In this paper, we aim to bridge this gap by presenting a framework for random smoothing regularization that can adaptively and effectively learn a wide range of ground truth functions belonging to the classical Sobolev spaces.

Data Augmentation

Zolly: Zoom Focal Length Correctly for Perspective-Distorted Human Mesh Reconstruction

1 code implementation ICCV 2023 Wenjia Wang, Yongtao Ge, Haiyi Mei, Zhongang Cai, Qingping Sun, Yanjun Wang, Chunhua Shen, Lei Yang, Taku Komura

As it is hard to calibrate single-view RGB images in the wild, existing 3D human mesh reconstruction (3DHMR) methods either use a constant large focal length or estimate one based on the background environment context, which can not tackle the problem of the torso, limb, hand or face distortion caused by perspective camera projection when the camera is close to the human body.

3D Human Pose Estimation 3D Reconstruction

APAC: Authorized Probability-controlled Actor-Critic For Offline Reinforcement Learning

no code implementations28 Jan 2023 Jing Zhang, Chi Zhang, Wenjia Wang, Bing-Yi Jing

Due to the inability to interact with the environment, offline reinforcement learning (RL) methods face the challenge of estimating the Out-of-Distribution (OOD) points.

reinforcement-learning Reinforcement Learning (RL)

An automated approach to extracting positive and negative clinical research results

no code implementations7 Dec 2022 Xuanyu Shi, Shiyao Xie, Wenjia Wang, Ting Chen, Jian Du

Failure is common in clinical trials since the successful failures presented in negative results always indicate the ways that should not be taken.


Soft BPR Loss for Dynamic Hard Negative Sampling in Recommender Systems

no code implementations25 Nov 2022 Kexin Shi, Yun Zhang, BingYi Jing, Wenjia Wang

In recommender systems, leveraging Graph Neural Networks (GNNs) to formulate the bipartite relation between users and items is a promising way.

Recommendation Systems

Your Contrastive Learning Is Secretly Doing Stochastic Neighbor Embedding

2 code implementations30 May 2022 Tianyang Hu, Zhili Liu, Fengwei Zhou, Wenjia Wang, Weiran Huang

Contrastive learning, especially self-supervised contrastive learning (SSCL), has achieved great success in extracting powerful features from unlabeled data.

Contrastive Learning Data Augmentation +2

WegFormer: Transformers for Weakly Supervised Semantic Segmentation

no code implementations16 Mar 2022 Chunmeng Liu, Enze Xie, Wenjia Wang, Wenhai Wang, Guangyao Li, Ping Luo

Although convolutional neural networks (CNNs) have achieved remarkable progress in weakly supervised semantic segmentation (WSSS), the effective receptive field of CNN is insufficient to capture global context information, leading to sub-optimal results.

Segmentation Weakly supervised Semantic Segmentation +1

Differentiable and Scalable Generative Adversarial Models for Data Imputation

no code implementations10 Jan 2022 Yangyang Wu, Jun Wang, Xiaoye Miao, Wenjia Wang, Jianwei Yin

DIM leverages a new masking Sinkhorn divergence function to make an arbitrary generative adversarial imputation model differentiable, while for such a differentiable imputation model, SSE can estimate an appropriate sample size to ensure the user-specified imputation accuracy of the final model.


Understanding Square Loss in Training Overparametrized Neural Network Classifiers

no code implementations7 Dec 2021 Tianyang Hu, Jun Wang, Wenjia Wang, Zhenguo Li

Comparing to cross-entropy, square loss has comparable generalization error but noticeable advantages in robustness and model calibration.

Segmenting Transparent Object in the Wild with Transformer

2 code implementations21 Jan 2021 Enze Xie, Wenjia Wang, Wenhai Wang, Peize Sun, Hang Xu, Ding Liang, Ping Luo

This work presents a new fine-grained transparent object segmentation dataset, termed Trans10K-v2, extending Trans10K-v1, the first large-scale transparent object segmentation dataset.

Object Segmentation +2

Neural Network Gaussian Process Considering Input Uncertainty for Composite Structures Assembly

no code implementations21 Nov 2020 Cheolhei Lee, Jianguo Wu, Wenjia Wang, Xiaowei Yue

Developing machine learning enabled smart manufacturing is promising for composite structures assembly process.

Regularization Matters: A Nonparametric Perspective on Overparametrized Neural Network

no code implementations6 Jul 2020 Tianyang Hu, Wenjia Wang, Cong Lin, Guang Cheng

Overparametrized neural networks trained by gradient descent (GD) can provably overfit any training data.

Segmenting Transparent Objects in the Wild

1 code implementation ECCV 2020 Enze Xie, Wenjia Wang, Wenhai Wang, Mingyu Ding, Chunhua Shen, Ping Luo

To address this important problem, this work proposes a large-scale dataset for transparent object segmentation, named Trans10K, consisting of 10, 428 images of real scenarios with carefully manual annotations, which are 10 times larger than the existing datasets.

Segmentation Semantic Segmentation +1

PGU-net+: Progressive Growing of U-net+ for Automated Cervical Nuclei Segmentation

1 code implementation4 Nov 2019 Jie Zhao, Lei Dai, Mo Zhang, Fei Yu, Meng Li, Hongfeng Li, Wenjia Wang, Li Zhang

The experimental results show that the PGU-net+ has superior accuracy than the previous state-of-the-art methods on cervical nuclei segmentation.


TextSR: Content-Aware Text Super-Resolution Guided by Recognition

1 code implementation16 Sep 2019 Wenjia Wang, Enze Xie, Peize Sun, Wenhai Wang, Lixun Tian, Chunhua Shen, Ping Luo

Nonetheless, most of the previous methods may not work well in recognizing text with low resolution which is often seen in natural scene images.

Scene Text Recognition Super-Resolution

Efficient and Accurate Arbitrary-Shaped Text Detection with Pixel Aggregation Network

6 code implementations ICCV 2019 Wenhai Wang, Enze Xie, Xiaoge Song, Yuhang Zang, Wenjia Wang, Tong Lu, Gang Yu, Chunhua Shen

Recently, some methods have been proposed to tackle arbitrary-shaped text detection, but they rarely take the speed of the entire pipeline into consideration, which may fall short in practical applications. In this paper, we propose an efficient and accurate arbitrary-shaped text detector, termed Pixel Aggregation Network (PAN), which is equipped with a low computational-cost segmentation head and a learnable post-processing.

Scene Text Detection Segmentation +1

Automated Segmentation of Pulmonary Lobes using Coordination-Guided Deep Neural Networks

2 code implementations19 Apr 2019 Wenjia Wang, Junxuan Chen, Jie Zhao, Ying Chi, Xuansong Xie, Li Zhang, Xian-Sheng Hua

The proposed model is trained and evaluated on a few publicly available datasets and has achieved the state-of-the-art accuracy with a mean Dice coefficient index of 0. 947 $\pm$ 0. 044.


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