Hao Yu

Hao Yu

Auto-generated profile, based on publicly available information

Hao Yu

Technical University of Munich, Mnchen, Germany

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
20 March 2023 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
ZQZheng Qin
Zheng Qin
HYHao Yu
Hao Yu
CWChangjian Wang
Changjian Wang
YGYulan Guo
Yulan Guo
YPYuxing Peng
Yuxing Peng
Kai XuKai Xu
Kai Xu
We study the problem of extracting accurate correspondences for point cloud registration. Recent keypoint-free methods have shown great potential through bypassing the detection of repeatable keypoints which is difficult to do especially in low-overlap scenarios. They seek correspondences over downsampled superpoints, which are then propagated to dense points. Superpoints are matched based on whether their neighboring patches overlap. Such sparse and loose matching requires contextual features capturing the geometric structure of the point clouds. We propose Geometric Transformer, or GeoTransformer for short, to learn geometric feature for robust superpoint matching. It encodes pair-wise distances and triplet-wise angles, making it invariant to rigid transformation and robust in low-overlap cases. The simplistic design attains surprisingly high matching accuracy such that no RANSAC is required in the estimation of alignment transformation, leading to 100 times acceleration. Extensive experiments on rich benchmarks encompassing indoor, outdoor, synthetic, multiway and non-rigid demonstrate the efficacy of GeoTransformer. Notably, our method improves the inlier ratio by $18{\sim }31$ percentage points and the registration recall by over 7 points on the challenging 3DLoMatch benchmark.

3 January 2024 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
HYHao Yu
Hao Yu
JHJi Hou
Ji Hou
ZQZheng Qin
Zheng Qin
MSMahdi Saleh
Mahdi Saleh
ISIvan Shugurov
Ivan Shugurov
SISlobodan Ilic
Slobodan Ilic
Successful point cloud registration relies on accurate correspondences established upon powerful descriptors. However, existing neural descriptors either leverage a rotation-variant backbone whose performance declines under large rotations, or encode local geometry that is less distinctive. To address this issue, we introduce RIGA to learn descriptors that are Rotation-Invariant by design and Globally-Aware. From the Point Pair Features (PPFs) of sparse local regions, rotation-invariant local geometry is encoded into geometric descriptors. Global awareness of 3D structures and geometric context is subsequently incorporated, both in a rotation-invariant fashion. More specifically, 3D structures of the whole frame are first represented by our global PPF signatures, from which structural descriptors are learned to help geometric descriptors sense the 3D world beyond local regions. Geometric context from the whole scene is then globally aggregated into descriptors. Finally, the description of sparse regions is interpolated to dense point descriptors, from which correspondences are extracted for registration. To validate our approach, we conduct extensive experiments on both object- and scene-level data. With large rotations, RIGA surpasses the state-of-the-art methods by a margin of 8 ${}^\circ$ in terms of the Relative Rotation Error on ModelNet40 and improves the Feature Matching Recall by at least 5 percentage points on 3DLoMatch.

2 March 2023 in arXiv
Verified
Preprint
Open access
PDF file
JZJiayuan Zhuang
Jiayuan Zhuang
ZQZheng Qin
Zheng Qin
HYHao Yu
Hao Yu
XCXucan Chen
Xucan Chen
Classification and localization are two main sub-tasks in object detection. Nonetheless, these two tasks have inconsistent preferences for feature context, i.e., localization expects more boundary-aware features to accurately regress the bounding box, while more semantic context is preferred for object classification. Exsiting methods usually leverage disentangled heads to learn different feature context for each task. However, the heads are still applied on the same input features, which leads to an imperfect balance between classifcation and localization. In this work, we propose a novel Task-Specific COntext DEcoupling (TSCODE) head which further disentangles the feature encoding for two tasks. For classification, we generate spatially-coarse but semantically-strong feature encoding. For localization, we provide high-resolution feature map containing more edge information to better regress object boundaries. TSCODE is plug-and-play and can be easily incorperated into existing detection pipelines. Extensive experiments demonstrate that our method stably improves different detectors by over 1.0 AP with less computational cost. Our code and models will be publicly released.

23 January 2025 in IEEE Transactions on Information Forensics and Security
Verified
Journal Article
Closed access
LXLingyun Xiang
Lingyun Xiang
HHHailang Hu
Hailang Hu
QLQian Li
Qian Li
HYHao Yu
Hao Yu
XSXiaobo Shen
Xiaobo Shen
Recently, numerous degraded images have flooded search engines and social networks, finding extensive and practical applications in the real world. However, these images have also posed new challenges to conventional image retrieval tasks. To this end, we introduce a new task of retrieving degraded images through deep hashing from large-scale databases, and further present the Locality-Sensitive Hashing Network (LSHNet) to tackle it in a self-supervised manner. More specifically, we first propose a triplet strategy to enable the self-supervised training of LSHNet in an end-to-end fashion. Due to the designed strategy, the highly semantic similarity and discrimination of degraded images are well-preserved in our learned latent codes without requiring additional human labor in labeling tons of degraded images. Moreover, to tackle large-scale image retrieval efficiently, we further propose to transform the latent codes into locality-sensitive hashing codes such that the degraded images can be retrieved in sublinear time with their representation ability almost unaffected. Extensive experiments are conducted on three public benchmarks where the results demonstrate the superior performance of LSHNet in retrieving similar images under degraded conditions.

14 June 2023 in arXiv
Verified
Preprint
Open access
PDF file
ZKZhigang Kan
Zhigang Kan
LQLinbo Qiao
Linbo Qiao
HYHao Yu
Hao Yu
LPLiwen Peng
Liwen Peng
YGYifu Gao
Yifu Gao
DLDongsheng Li
Dongsheng Li
Large Language Models (LLMs) are gaining increasing attention due to their exceptional performance across numerous tasks. As a result, the general public utilize them as an influential tool for boosting their productivity while natural language processing researchers endeavor to employ them in solving existing or new research problems. Unfortunately, individuals can only access such powerful AIs through APIs, which ultimately leads to the transmission of raw data to the models' providers and increases the possibility of privacy data leakage. Current privacy-preserving methods for cloud-deployed language models aim to protect privacy information in the pre-training dataset or during the model training phase. However, they do not meet the specific challenges presented by the remote access approach of new large-scale language models. This paper introduces a novel task, "User Privacy Protection for Dialogue Models," which aims to safeguard sensitive user information from any possible disclosure while conversing with chatbots. We also present an evaluation scheme for this task, which covers evaluation metrics for privacy protection, data availability, and resistance to simulation attacks. Moreover, we propose the first framework for this task, namely privacy protection through text sanitization. Before sending the input to remote large models, it filters out the sensitive information, using several rounds of text sanitization based on privacy types that users define. Upon receiving responses from the larger model, our framework automatically restores privacy to ensure that the conversation goes smoothly, without intervention from the privacy filter. Experiments based on real-world datasets demonstrate the efficacy of our privacy-preserving approach against eavesdropping from potential attackers.

27 September 2022 in arXiv
Verified
Preprint
Open access
PDF file
HYHao Yu
Hao Yu
JHJi Hou
Ji Hou
ZQZheng Qin
Zheng Qin
MSMahdi Saleh
Mahdi Saleh
ISIvan Shugurov
Ivan Shugurov
SISlobodan Ilic
Slobodan Ilic
Successful point cloud registration relies on accurate correspondences established upon powerful descriptors. However, existing neural descriptors either leverage a rotation-variant backbone whose performance declines under large rotations, or encode local geometry that is less distinctive. To address this issue, we introduce RIGA to learn descriptors that are Rotation-Invariant by design and Globally-Aware. From the Point Pair Features (PPFs) of sparse local regions, rotation-invariant local geometry is encoded into geometric descriptors. Global awareness of 3D structures and geometric context is subsequently incorporated, both in a rotation-invariant fashion. More specifically, 3D structures of the whole frame are first represented by our global PPF signatures, from which structural descriptors are learned to help geometric descriptors sense the 3D world beyond local regions. Geometric context from the whole scene is then globally aggregated into descriptors. Finally, the description of sparse regions is interpolated to dense point descriptors, from which correspondences are extracted for registration. To validate our approach, we conduct extensive experiments on both object- and scene-level data. With large rotations, RIGA surpasses the state-of-the-art methods by a margin of 8\degree in terms of the Relative Rotation Error on ModelNet40 and improves the Feature Matching Recall by at least 5 percentage points on 3DLoMatch.