Chenhongyi Yang 杨陈弘毅
pdb

I am a PhD student at the School of Engineering, University of Edinburgh. My principal supervisor is Dr. Elliot J. Crowley. I am also a member of the BayesWatch group. In addition, I am also an external research collaborator at Meta Reality Labs, working on egocentric computer vision problems.

My research lies in computer vision and machine learning. For now, I am working on 3D visual recognition problems. My past research is mainly about visual recognition, for example, developing annotation-efficient algorithms for visual recognition and enabling object detectors to handle difficult situations.

Previously, I did my MSc degree in computer science at Boston University, where I worked with Prof. Margrit Betke and Dr. Vitaly Ablavsky on computer vision problems. Before that, I obtained my BEng degree in computer science from the University of Science and Technology of China.

Preprint Papers

WidthFormer: Toward Efficient Transformer-based BEV View Transformation

Preprint, 01/2024

Chenhongyi Yang, Tianwei Lin, Lichao Huang, Elliot J. Crowley

WidthFormer is an efficient and robust transformer-based BEV transformation method. It is built upon a feature compression mechanism and an effective 3D positional encoding mechanism. Moreover, our new 3D positional encoding is also beneficial for sparse 3D object detectors.

Contrastive Object-level Pre-training with Spatial Noise Curriculum Learning

Preprint, 11/2021

Chenhongyi Yang, Lichao Huang, Elliot J. Crowley

CCOP is an object-level self-supervised learning framework. It is based on contrasting the regional features of rough object boxes, which are found using an unsupervised way. We also develop a curriculum learning mechanism to alleviate the gradient vanishing problem.

Conference and Journal Papers

Plug and Play Active Learning for Object Detection

Accepted by CVPR 2024

Chenhongyi Yang, Lichao Huang, Elliot J. Crowley

PPAL is a plug-and-play active learning framework for object detection. It is based on two innotations: a novel object-level uncertainty re-weighting mechanism and a new similarity computing method for designed multi-instance images.

DETRDistill: A Universal Knowledge Distillation Framework for DETR-families

ICCV 2023

Jiahao Chang*, Shuo Wang*, Haiming Xu, Zehui Chen, Chenhongyi Yang, Feng Zhao

DETRDistill is a knolwedge distillation framework designed for the DETR family, the transformer-based object detection architectures. The distillation is conducted in three parts: instance query distillation, visual feature distillation and bipartite matching distillation.

GPViT: A High Resolution Non-Hierarchical Vision Transformer with Group Propagation

ICLR 2023 (Spotlight)

Chenhongyi Yang*, Jiarui Xu*, Shalini De Mello, Elliot J. Crowley, Xiaolong Wang

Group Propagation Vision Transformer (GPViT) is a non-hierarchical vision transformer designed for general visual recognition with high-resolution features, whose core is the Group Propagation block that can exchange global information with a linear complexity.

Prediction-Guided Distillation for Dense Object Detection

ECCV 2022

Chenhongyi Yang, Mateusz Ochal, Amos Storkey, Elliot J. Crowley

PGD is a high-performing knowledge distillation framework designed for single-stage object detectors. It distills every object in a few key predictive regions and uses an adaptive weighting scheme to compute the foreground feature imitation loss in those regions.

QueryDet: Cascaded Sparse Query for Accelerating High-Resolution Small Object Detection

CVPR 2022 (Oral)

Chenhongyi Yang, Zehao Huang, Naiyan Wang

QueryDet achieves fast and accurate small object detection. Its core is the cascaded sparse query mechanism: rough locations of small objects are first found on low-resolution features, then those objects are accurately detected on high-resolution features using the efficient sparse convolution.

DDOD: Dive Deeper into the Disentanglement of Object Detector

IEEE Transactions on Multimedia (TMM)

Zehui Chen, Chenhongyi Yang, Qiaofei Li, Feng Zhao, Zheng-Jun Zha, Feng Wu

This work studies the conjunction problem and extends the DDOD structure to all three forms of modern object detectors: one-stage, two stage and transformer-based detectors.

Disentangle Your Dense Object Detector

ACM Multimedia 2021 (Oral)

Zehui Chen*, Chenhongyi Yang*, Qiaofei Li, Feng Zhao, Zheng-Jun Zha, Feng Wu

We investigated the conjunction problem in the modern dense object detectors, based on which we proposed the Disentangled Dense Object Detector (DDOD) where three effective disentanglement mechanisms were designed for boosting dense object detectors' performance.

Consistency Regularization with High-dimensional Non-adversarial Source-guided Perturbation for Unsupervised Domain Adaptation in Segmentation

AAAI 2021

Kaihong Wang, Chenhongyi Yang, Margrit Betke

BiSIDA is a bidirectional style-induced domain adaptation method that employs consistency regularization to exploit information from the unlabeled target domain dataset. BiSIDA is easy to train because the domain adaptation is achieved with a simple nerual style transfer model.

Learning to Separate: Detecting Heavily-Occluded Objects in Urban Scenes

ECCV 2020

Chenhongyi Yang, Vitaly Ablavsky, Kaihong Wang, Qi Feng, Margrit Betke

SG-NMS is a new non-maximum-suppression algorithm designed for detecting heavily-occluded objects. It is based on the semantic-geometry embedding mechanism where the embeddings of boxes belonging to the same object are pulled together and embeddings of boxes belong to different objects are pushed away. Then NMS is conducted based on the embedding distances.

Latest update:

Thanks to Jack Turner for the website template.