Yinlin Hu | EPFL Graph Search

Are you an EPFL student looking for a semester project?

Work with us on data science and visualisation projects, and deploy your project as an app on top of GraphSearch.

I am a researcher in Computer Vision Lab of EPFL, collaborated with Prof. Pascal Fua and Dr. Mathieu Salzmann. The research areas that I involved and interested include optical flow, motion analysis, and object pose estimation. In 2017, I completed my Ph.D. degree from Xidian University under the supervision of Prof. Yunsong Li and Dr. Rui Song. Before that, I've been working as a senior algorithm engineer and technical leader for nearly 4 years in Zienon, LLC. Please visit my personal homepage https://yinlinhu.github.io for more information.

About this result

This page is automatically generated and may contain information that is not correct, complete, up-to-date, or relevant to your search query. The same applies to every other page on this website. Please make sure to verify the information with EPFL's official sources.

Related units

Courses taught by this person

Related research domains

Related publications

People doing similar research

Biography

Official source

About this result

Related units (1)

Related units

Courses taught by this person

No results

Courses taught by this person

Related research domains (9)

Related research domains

Related publications (10)

Related publications

People doing similar research (136)

People doing similar research

Deep learning

Deep learning is part of a broader family of machine learning methods, which is based on artificial neural networks with representation learning. The adjective "deep" in deep learning refers to the

3D pose estimation

3D pose estimation is a process of predicting the transformation of an object from a user-defined reference pose, given an image or a 3D scan. It arises in computer vision or robotics where the pose

Computer vision

Computer vision tasks include methods for , , and understanding digital images, and extraction of high-dimensional data from the real world in order to produce numerical or symbolic information, e.g.

A Stepwise Domain Adaptive Segmentation Network With Covariate Shift Alleviation for Remote Sensing Imagery

Yinlin Hu, Yunpeng Li, Rui Song

Semantic segmentation for remote sensing images (RSI) is critical for the Earth monitoring system. However, the covariate shift between RSI datasets under different capture conditions cannot be alleviated by directly using the unsupervised domain adaptation (UDA) method, which negatively affects the segmentation accuracy in RSI. We propose a stepwise domain adaptive segmentation network with covariate shift alleviation (Cov-DA) for RSI parsing to solve this issue. Specifically, to alleviate domain shift generated by different sensors, both the source and target domains are projected into a colorspace with normalized distribution through an elaborate colorspace mapping unified module (CMUM). The color distributions of these two domains tend to be more uniform. Furthermore, in the target domain, the multistatistics joint evaluation module (MJEM) is proposed to capture different statistical characteristics of subscenarios for selecting plain scenarios regarded as high-confidence segmentation results to assist the further improvement of segmentation performance. In addition, a pyramid perceptual attention module (PPAM) containing omnidirectional features without computational burdens is added to our network for effectively enhancing the multiscale feature capture ability. In the cross-city DA experiments based on the International Society for Photogrammetry and Remote Sensing (ISPRS) and aerial benchmarks, the superiority of our algorithm is significantly demonstrated. Furthermore, we release a large-scale Martian terrain dataset noted as "Mars-Seg" containing 5 K images with pixel-level accurate annotations regarding issues, such as the lack of semantic segmentation datasets for unknown scenes.

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC2022

, ,

2022

Templates for 3D Object Pose Estimation Revisited: Generalization to New Objects and Robustness to Occlusions

Yinlin Hu, Vincent Lepetit, Van Nguyen Nguyen, Mathieu Salzmann, Yang Xiao

We present a method that can recognize new objects and estimate their 3D pose in RGB images even under partial occlusions. Our method requires neither a training phase on these objects nor real images depicting them, only their CAD models. It relies on a small set of training objects to learn local object representations, which allow us to locally match the input image to a set of "templates", rendered images of the CAD models for the new objects. In contrast with the state-of-the-art methods, the new objects on which our method is applied can be very different from the training objects. As a result, we are the first to show generalization without retraining on the LINEMOD and Occlusion-LINEMOD datasets. Our analysis of the failure modes of previous template-based approaches further confirms the benefits of local features for template matching. We outperform the state-of-the-art template matching methods on the LINEMOD, Occlusion-LINEMOD and T-LESS datasets. Our source code and data are publicly available at https://github.com/nv-nguyen/template-pose.

IEEE COMPUTER SOC2022