Search Results for author: Haoqian Wu

Found 15 papers, 10 papers with code

Fingerprint Presentation Attack Detector Using Global-Local Model

no code implementations20 Feb 2024 Haozhe Liu, Wentian Zhang, Feng Liu, Haoqian Wu, Linlin Shen

While by using the texture in-painting-based local module, a local spoofness score predicted from fingerprint patches is obtained.

Text-Guided 3D Face Synthesis -- From Generation to Editing

no code implementations1 Dec 2023 Yunjie Wu, Yapeng Meng, Zhipeng Hu, Lincheng Li, Haoqian Wu, Kun Zhou, Weiwei Xu, Xin Yu

In the editing stage, we first employ a pre-trained diffusion model to update facial geometry or texture based on the texts.

Face Generation Texture Synthesis

Collaborative Noisy Label Cleaner: Learning Scene-aware Trailers for Multi-modal Highlight Detection in Movies

1 code implementation CVPR 2023 Bei Gan, Xiujun Shu, Ruizhi Qiao, Haoqian Wu, Keyu Chen, Hanjun Li, Bo Ren

Based on existing efforts, this work has two observations: (1) For different annotators, labeling highlight has uncertainty, which leads to inaccurate and time-consuming annotations.

Highlight Detection Learning with noisy labels +1

Improving GAN Training via Feature Space Shrinkage

1 code implementation2 Mar 2023 Haozhe Liu, Wentian Zhang, Bing Li, Haoqian Wu, Nanjun He, Yawen Huang, Yuexiang Li, Bernard Ghanem, Yefeng Zheng

The evaluation results demonstrate that our AdaptiveMix can facilitate the training of GANs and effectively improve the image quality of generated samples.

Out of Distribution (OOD) Detection

Towards Unbiased Volume Rendering of Neural Implicit Surfaces With Geometry Priors

no code implementations CVPR 2023 Yongqiang Zhang, Zhipeng Hu, Haoqian Wu, Minda Zhao, Lincheng Li, Zhengxia Zou, Changjie Fan

In this paper, we argue that this limited accuracy is due to the bias of their volume rendering strategies, especially when the viewing direction is close to be tangent to the surface.

Surface Reconstruction

AdaptiveMix: Improving GAN Training via Feature Space Shrinkage

1 code implementation CVPR 2023 Haozhe Liu, Wentian Zhang, Bing Li, Haoqian Wu, Nanjun He, Yawen Huang, Yuexiang Li, Bernard Ghanem, Yefeng Zheng

The evaluation results demonstrate that our AdaptiveMix can facilitate the training of GANs and effectively improve the image quality of generated samples.

Out of Distribution (OOD) Detection

Decoupled Mixup for Generalized Visual Recognition

1 code implementation26 Oct 2022 Haozhe Liu, Wentian Zhang, Jinheng Xie, Haoqian Wu, Bing Li, Ziqi Zhang, Yuexiang Li, Yawen Huang, Bernard Ghanem, Yefeng Zheng

Since the observation is that noise-prone regions such as textural and clutter backgrounds are adverse to the generalization ability of CNN models during training, we enhance features from discriminative regions and suppress noise-prone ones when combining an image pair.

Combating Mode Collapse in GANs via Manifold Entropy Estimation

1 code implementation25 Aug 2022 Haozhe Liu, Bing Li, Haoqian Wu, Hanbang Liang, Yawen Huang, Yuexiang Li, Bernard Ghanem, Yefeng Zheng

In this paper, we propose a novel training pipeline to address the mode collapse issue of GANs.

See Finer, See More: Implicit Modality Alignment for Text-based Person Retrieval

1 code implementation18 Aug 2022 Xiujun Shu, Wei Wen, Haoqian Wu, Keyu Chen, Yiran Song, Ruizhi Qiao, Bo Ren, Xiao Wang

To explore the fine-grained alignment, we further propose two implicit semantic alignment paradigms: multi-level alignment (MLA) and bidirectional mask modeling (BMM).

Person Retrieval Retrieval +3

Robust Representation via Dynamic Feature Aggregation

1 code implementation16 May 2022 Haozhe Liu, Haoqin Ji, Yuexiang Li, Nanjun He, Haoqian Wu, Feng Liu, Linlin Shen, Yefeng Zheng

With the regularization and orthogonal classifier, a more compact embedding space can be obtained, which accordingly improves the model robustness against adversarial attacks.

Out of Distribution (OOD) Detection

Manifold-preserved GANs

no code implementations18 Sep 2021 Haozhe Liu, Hanbang Liang, Xianxu Hou, Haoqian Wu, Feng Liu, Linlin Shen

Generative Adversarial Networks (GANs) have been widely adopted in various fields.

Group-wise Inhibition based Feature Regularization for Robust Classification

1 code implementation ICCV 2021 Haozhe Liu, Haoqian Wu, Weicheng Xie, Feng Liu, Linlin Shen

The convolutional neural network (CNN) is vulnerable to degraded images with even very small variations (e. g. corrupted and adversarial samples).

Classification Domain Generalization +2

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