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.

My research is mainly about computer vision, and my research interests include:

  • Developing image recognition algorithms under insufficient human annotations
  • Learning good visual representaiton in an unsupervised way
  • Designing high-performance nerual network architectures

Previously, I did my MSc in computer science at Boston University and my BEng in computer science at the University of Science and Technology of China.

Conference Papers

Prediction-Guided Distillation for Dense Object Detection

ECCV 2022 (To appear)

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

PGD is a knowledge distillation framework designed for dense object detectors. It distills every object in a few key predictive regions and uses an adaptive weighting scheme to compute feature imitation loss in such 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. It is based on the cascaded sparse query mechanism: rough object locations are first found on low-resolution features, then they are accurately detected on high-resolution features in a sparse way.

Disentangle Your Dense Object Detector

ACM Multimedia 2021 (Oral)

Chenhongyi Yang*, Zehui Chen*, 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 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, requiring only a simple neural 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 NMS algorithm designed for detecting heavily-occluded objects. It is based on a novel embedding mechanism, in which the semantic and geometric features of the detected boxes are jointly exploited.

Preprint Papers

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

Chenhongyi Yang, Lichao Huang, Elliot J. Crowley.

CCOP is an object-level self-supervised learning framework. It uses rough object boxes to build an inter-image contrastive loss and an intra-image discrimination loss to learn detailed regional features. Moreover, a curriculum learning mechanism is designed to alleviate the gradient vanishing problem.

Latest update:

Thanks to Jack Turner for the website template.