Zilong's Home Page

Zilong Huang / 黄子龙

I am now a research scientist at ByteDance. I received my Ph.D. degree and B.E. degree from Huazhong University of Science and Technology (HUST) in 2020 and 2015 respectively, advised by Prof. Wenyu Liu and Prof. Xinggang Wang. I was working as a visiting student (2018-2019) in the IFP group at the University of Illinois at Urbana-Champaign (UIUC), advised by Prof. Thomas S. Huang, Prof. Yunchao Wei and Prof. Humphrey Shi.

I work on computer vision problems with special focus on Multimodal learning, Efficient model design and training.

CV / Email / GitHub / Google Scholar / LinkedIn

Highlights

[Call for paper] Image and Vision Computing Special Issue on "Advancing Transparency and Privacy: Explainable AI and Synthetic Data in Biometrics and Computer Vision"

[Oct 2024] SuperClass and Depth-Anything V2 are accepted by NeurIPS 2024.
[Sep 2024] Ranked as The World’s Top 2% Scientists 2024 by Stanford University/Elsevier.
[May 2024] Co-organizing the ECCV 2024 Workshop Synthetic Data for Computer Vision
[Feb 2024] Depth-Anything is accepted by CVPR 2024.
[Dec 2023] Meta Prompts is released.
[Oct 2023] Ranked as The World’s Top 2% Scientists 2023 by Stanford University/Elsevier.
[Nov 2023] Disentangled Pre-training for Image Matting is accepted by WACV 2024 as Oral
[Feb 2023] Motion Latent-based Diffusion is accepted by CVPR 2023
[Jan 2023] SeaFormer is accepted by ICLR 2023 and DCNet is accepted by TCSVT
[Sep 2022] COCO-Nerf is accepted by NeurIPS 2022
[Mar 2022] Topformer is accepted by CVPR 2022
[Dec 2021] Delighted to receive CSIG Excellent Doctoral Dissertation Award
[May 2021] AlignSeg is accepted by TPAMI
[May 2021] Selected as Global Top 100 Chinese Rising Stars in Artificial Intelligence by Baidu Scholar
[Mar 2021] Win two champions on Single Image Depth Estimation Challenge of Mobile AI 2021 and Short-video Face Parsing Challenge of The 3rd Person in Context (PIC) Workshop

Publications

My selected publications are listed here. The complete list of publications can be seen from my Google Scholar page.

^ students mentored by me. * equal contribution

	Classification Done Right for Vision-Language Pre-Training Zilong Huang, Qinghao Ye, Bingyi Kang, Jiashi Feng, Haoqi Fan NeurIPS, 2024 code / pdf We introduce SuperClass, a super simple classification method for vision-language pre-training on image-text data.
	Depth Anything V2 Lihe Yang, Bingyi Kang, Zilong Huang, Zhen Zhao, Xiaogang Xu, Jiashi Feng, Hengshuang Zhao NeurIPS, 2024 code / pdf Depth Anything V2 is trained from 595K synthetic labeled images and 62M+ real unlabeled images.
	DiG: Scalable and Efficient Diffusion Models with Gated Linear Attention Lianghui Zhu, Zilong Huang, Bencheng Liao, Jun Hao Liew, Hanshu Yan, Jiashi Feng, Xinggang Wang Arxiv, 2024 code / pdf This work presents Diffusion GLA, the first exploration for diffusion backbone with linear attention transformer.
	Harnessing Diffusion Models for Visual Perception with Meta Prompts Qiang Wan, Zilong Huang, Bingyi Kang, Jiashi Feng, Li Zhang. Arxiv, 2024 code / pdf This work presents Meta Prompts, a simple yet effective scheme to harness a diffusion model for visual perception tasks.
	Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data Lihe Yang, Bingyi Kang, Zilong Huang, Xiaogang Xu, Jiashi Feng, Hengshuang Zhao. CVPR, 2024 code / pdf This work presents Depth Anything, a highly practical solution for robust monocular depth estimation by training on a combination of 1.5M labeled images and 62M+ unlabeled images.
	Disentangled Pre-training for Image Matting Yanda Li^, Zilong Huang, Gang Yu, Ling Chen, Yunchao Wei, Jianbo Jiao WACV, 2024 code / pdf we propose the first self-supervised large-scale pretraining approach for image matting.
	Executing your Commands via Motion Diffusion in Latent Space Xin Chen, Biao Jiang, Wen Liu, Zilong Huang, Bin Fu, Tao Chen, Jingyi Yu, Gang Yu CVPR, 2023 code / pdf we propose a Motion Latent-based Diffusion model (MLD) could produce vivid motion sequences conforming to the given conditional inputs.
	SeaFormer: Squeeze-enhanced Axial Transformer for Mobile Semantic Segmentation Qiang Wan^, Zilong Huang, Jiachen Lu, Gang Yu, Li Zhang ICLR, 2023 code / pdf we design a generic attention block characterized by the formulation of squeeze Axial and detail enhancement for mobile vision.
	Coordinates Are NOT Lonely - Codebook Prior Helps Implicit Neural 3D Representations Fukun Yin, Wen Liu, Zilong Huang, Pei Cheng, Tao Chen, Gang Yu NeurIPS, 2022 code / pdf CoCo-INR is a novel framework for implicit neural 3D representations, which builds a connection between each coordinate and the prior information.
	TopFormer: Token Pyramid Transformer for Mobile Semantic Segmentation Wenqiang Zhang^, Zilong Huang, Guozhong Luo, Tao Chen, Xinggang Wang, Wenyu Liu, Gang Yu, Chunhua Shen CVPR, 2022 code / pdf Topformer is the first work that makes transformer real-time on mobile devices for segmentation tasks.
	Shuffle Transformer: Rethinking Spatial Shuffle for Vision Transformer Zilong Huang, Youcheng Ben, Guozhong Luo, Pei Cheng, Gang Yu, Bin Fu arXiv, 2021 code / pdf we revisit the spatial shuffle as an efficient way to build connections among windows in window-based self-attention.
	AlignSeg: Feature-Aligned Segmentation Networks Zilong Huang, Yunchao Wei, Xinggang Wang, Wenyu Liu, Thomas S. Huang, Humphrey Shi TPAMI, 2021 code / pdf we focus on the feature misalignment issue in previous popular feature aggregation architectures for semantic segmentation.
	Human De-occlusion: Invisible Perception and Recovery for Humans Qiang Zhou, Shiyin Wang, Yitong Wang, Zilong Huang, Xinggang Wang CVPR, 2021 dataset / pdf we tackle the problem of human de-occlusion which reasons about occluded segmentation masks and invisible appearance content of humans.
	High-Resolution Deep Image Matting Haichao Yu, Ning Xu, Zilong Huang, Yuqian Zhou, Humphrey Shi. AAAI, 2021 pdf we propose HDMatt, a first deep learning based image matting approach for high-resolution inputs.
	Agriculture-Vision: A Large Aerial Image Database for Agricultural Pattern Analysis Mang Tik Chiu, Xingqian Xu, Yunchao Wei, Zilong Huang, Alexander Schwing, Robert Brunner, Hrant Khachatrian, Hovnatan Karapetyan, Ivan Dozier, Greg Rose, David Wilson, Adrian Tudor, Naira Hovakimyan, Thomas S Huang, Honghui Shi CVPR, 2020 dataset / pdf / video we present Agriculture-Vision: a large-scale aerial farmland image dataset for semantic segmentation of agricultural patterns.
	CCNet: Criss-Cross Attention for Semantic Segmentation Zilong Huang, Xinggang Wang, Yunchao Wei, Lichao Huang, Humphrey Shi, Wenyu Liu, Thomas S. Huang ICCV, 2019 \|TPAMI, 2020 code / pdf More than 3000 citations, PaperDigest Most Influential ICCV 2019 papers (5th). Applications of CCNet also include AlphaFold2. we propose a Criss-Cross Network (CCNet) for obtaining full-image contextual information in a very effective and efficient way.
	SPGNet: Semantic Prediction Guidance for Scene Parsing Bowen Cheng, Liang-Chieh Chen, Yunchao Wei, Yukun Zhu, Zilong Huang, Jinjun Xiong, Thomas Huang, Wen-Mei Hwu, Humphrey Shi. ICCV, 2019 pdf we propose a Semantic Prediction Guidance (SPG) module which learns to re-weight the local features through the guidance from pixel-wise semantic prediction.
	Semantic Image Segmentation by Scale-Adaptive Networks Zilong Huang, Chunyu Wang, Xinggang Wang, Wenyu Liu, Jingdong Wang TIP, 2019 code / pdf we propose a Scale-Adaptive Network (SAN) which consists of multiple branches with each one taking charge of the segmentation of the objects of a certain range of scales.
	Devil in the Details: Towards Accurate Single and Multiple Human Parsing Tao Ruan, Ting Liu, Zilong Huang, Yunchao Wei, Shikui Wei, Yao Zhao, Thomas Huang AAAI, 2019 code / pdf we identify several useful properties, including feature resolution, global context information and edge details, and perform rigorous analyses to reveal how to leverage them to benefit the human parsing task.
	Weakly-supervised semantic segmentation network with deep seeded region growing Zilong Huang, Xinggang Wang, Jiasi Wang, Wenyu Liu, Jingdong Wang CVPR, 2018 code / pdf we propose to train a semantic segmentation network starting from the discriminative regions and progressively increase the pixel-level supervision using by seeded region growing.

Last updated on March 09, 2022. Thanks to Jon Barron for this minimalist website template.