Yang Yang

PhD Candidate

School of Computing, Australian National University

Biography

Yang Yang is a second-year Computer Science Ph.D. student at the Australian National University, supervised by Prof. Liang Zheng. She obtained her B.E. degree at the School of Electronic Information and Communications, Huazhong University of Science and Technology. Her research interests lie within deep learning for Computer Vision, particularly in large vision models, model generalization and data-centric problems.

Actively looking for internships!

Interests

Large Vision Models
Data-centric Problems
Model Generalization

Education

PhD in Engineering and Computer Science, 2022 ~ now

Australian National University
BSc in Electronic Information, 2017 ~ 2021

Huazhong University of Science and Technology

Recent Publications

Bounding Box Stability against Feature Dropout Reflects Detector Generalization across Environments [iclr2024 spotlight]

Bounding boxes uniquely characterize object detection, where a good detector gives accurate bounding boxes of categories of interest. …

Yang Yang, Wenhai Wang, Zhe Chen, Jifeng Dai, Liang Zheng

PDF

CIFAR-10-Warehouse: Broad and More Realistic Testbeds in Model Generalization Analysis [iclr2024]

Analyzing model performance in various unseen environments is a critical research problem in the machine learning community. To study …

Xiaoxiao Sun, Xingjian Leng, Zijian Wang, Yang Yang, Zi Huang, Liang Zheng

PDF

Internchat: Solving vision-centric tasks by interacting with chatbots beyond language

We present an interactive visual framework named InternGPT, or iGPT for short. The framework integrates chatbots that have planning and …

Zhaoyang Liu, Yinan He, Wenhai Wang, Weiyun Wang, Yi Wang, Shoufa Chen, Qinglong Zhang, Yang Yang, Qingyun Li, Jiashuo Yu, Kunchang Li, Zhe Chen, Xue Yang, Xizhou Zhu, Yali Wang, Limin Wang, Ping Luo, Jifeng Dai, Yu Qiao

PDF

Does Keypoint Estimation Beneﬁt Object Detection? An Empirical Study of One-stage and Two-stage Detectors [fg2021]

Abstract — This paper studies the benefit of keypoint estimation on object detection. In particular, we focus on the paradigmatic …

Yang Yang, Akshay Asthana, Liang Zheng

PDF

Experience

Research Intern, supervised by Wenhai Wang

Shanghai AI Laboratory

Jan 2022 – May 2023 Shanghai, China

We find a strong positive correlation between the detection mAP and box stability score. This relationship allows us to predict the accuracy of detectors on various real-world test sets without accessing test ground truths, verified on vehicle detection and pedestrian detection tasks. To our knowledge, we are the first to propose the problem of unsupervised evaluation of object detection. The work was accepted by ICLR 2024 (spotlight).
To study the problem of analyzing classification performance in various unseen environments, we introduce CIFAR-10-W, which is a testbed with out-of-distribution test sets that have broad coverage of environmental discrepancies. We conduct extensive benchmarking and show that CIFAR-10-W offers interesting insights inherent to domain generalization and model accuracy prediction tasks. The work is submitted to ICLR 2024.
Automatic evaluation of the alignment for image generation. Work in progress.

Research Intern, supervised by Bo Li and Yiru Wang

Urban Computing Group of Sensetime Co., LTD.

May 2021 – Jan 2022 Beijing, China

Build efficient transformer module toolkit for CV, borrowing from efficient MSA in NLP (e.g. Linformer).
Study the information redundancy phenomenon existing in Transformer based on ViT, including token redundancy, and head redundancy.
From multi-scale and feature selection views, research the pyramid structure networks such as Swin and PVT for dense prediction tasks such as detection and segmentation.

Research Assistant, supervised remotely by Prof. Liang Zheng

Australian National University & Seeing Machines Co., LTD

Sep 2020 – May 2021 Australian

Study the impact of keypoint branch on one-stage detectors and two-stage detectors, and improve the CenterNet network to solve multiple lightweight detection tasks. The result achieves the state of the art on COCO-Wholebody and WiderFace dataset, and the work was accepted by FG 2021.

The Computer Vision Researcher, supervised by Prof. Jiaya Jia

Chinese University of Hong Kong & SmartMore Co., LTD.

Jun 2020 – Sep 2020 Shenzhen, China

Multi-Object Tracking. Familiar with detectron2 framework, added RoI expansion, Deepsort tracking module in the two-stage target detector. I practiced FairMot, MaskTrackRCNN and other models. The model was successfully deployed in the border vehicle detection scenario.

Research Assistant, supervised by Associate Prof. Xinggang Wang

Media and Communications Laboratory, Huazhong University of Science and Technology

Jun 2019 – Present Wuhan, China

Different from these methods that considering bounding box as a whole, we research a novel object bounding box representation using points and links.