Yihong Sun's Homepage

About Me

I am a third-year CS PhD candidate at Cornell University, advised by Prof. Bharath Hariharan. Previously, I obtained my Bachelor's degree from Johns Hopkins University, advised by Prof. Alan Yuille.

My work is supported by NSF GRFP and my research interests are computer vision and machine learning, especially in building visual perception systems that can learn from minimal supervision.

If you would like to chat with me, please drop me an email!

Publications (show selected / show all)

	Video Creation by Demonstration Yihong Sun, Hao Zhou, Liangzhe Yuan, Jennifer J. Sun, Yandong Li, Xuhui Jia, Hartwig Adam, Bharath Hariharan, Long Zhao, Ting Liu arXiv 2024 Paper / Project Page We generate videos that continue naturally from the context images while carrying out the action concepts from the demonstration videos.
	Learning 3D Perception from Others' Predictions Jinsu Yoo, Zhenyang Feng, Tai-Yu Pan, Yihong Sun, Cheng Perng Phoo, Xiangyu Chen, Mark Campbell, Kilian Q. Weinberger, Bharath Hariharan, Wei-Lun Chao ICLR 2025 Paper / Code / Project Page We construct 3D object detectors by learning from the predictions of a nearby unit that is equipped with an accurate detector.
	MOD-UV: Learning Mobile Object Detectors from Unlabeled Videos Yihong Sun, Bharath Hariharan ECCV 2024 Paper / Code / Poster / Project Page We build an unsupervised mobile object detector from unlabeled videos only by leveraging independent motion information.
	Dynamo-Depth: Fixing Unsupervised Depth Estimation for Dynamical Scenes Yihong Sun, Bharath Hariharan NeurIPS 2023 Paper / Code / Poster / Project Page We improve unsupervised monocular depth estimation for dynamical scenes by modeling 3D independent flow and motion segmentation.
	Amodal Segmentation through Out-of-Task and Out-of-Distribution Generalization with a Bayesian Model Yihong Sun, Adam Kortylewski, Alan Yuille CVPR 2022 Paper / Code / Poster / Supplementary We estimate amodal segmentation using a Bayesian generative model trained from non-occluded images and box-level annotations only.
	Robust Instance Segmentation through Reasoning about Multi-Object Occlusion Xiaoding Yuan, Adam Kortylewski, Yihong Sun, Alan Yuille CVPR 2021 Paper / Code We reason about multi-object self-occlusions by inspecting part-level activations of a Bayesian generative model.
	Robust Object Detection Under Occlusion With Context-Aware CompositionalNets Angtian Wang(), Yihong Sun()*, Adam Kortylewski, Alan Yuille CVPR 2020* Paper / Video / Data (*) indicates joint first authors We improve object detection under partial occlusion by regulating contextual bias and enhancing localization via compositional part voting.
	Compositional Convolutional Neural Networks: A Robust and Interpretable Model for Object Recognition under Occlusion Adam Kortylewski, Qing Liu, Angtian Wang, Yihong Sun, Alan Yuille IJCV 2020 Paper / Code We propose CompositionalNets, interpretable deep architectures with innate robustness to partial occlusion, for image classification and object detection.

Experience

Student Researcher

May 2024 - Dec 2024

- Hosts: Ting Liu, Long Zhao, Hao Zhou, Liangzhe Yuan, Jennifer Sun.

- Worked on Video Creation by Demonstration.

Teaching

	Graduate Teaching Assistant Bowers CIS College of Computing and Information Science - CS4670/5670 Introduction to Computer Vision (SP23) - CS4787/5777 Principles of Large-Scale Machine Learning (FA22)
	Undergraduate Course Assistant Department of Computer Science - EN.601.783 Vision as Bayesian Inference (SP22) - AS.050.375/675 Probabilistic Models of the Visual Cortex (FA21, FA20) - EN.601.226 Data Structures (SP21, FA20, SP20)