Fisher Yu (@DrFisherYu) / X

Fisher Yu

446 posts

Fisher Yu

@DrFisherYu

Assistant Professor of Computer Vision @ETH Zürich. Head of Visual Intelligence and Systems @ETH_VIS Group.

Zurich, Switzerland

Joined December 2008

Fisher Yu
@DrFisherYu
Apr 19, 2023
Segment Anything is fun and powerful but still requires full mask annotation for supervised training. Our new work MaskFreeVIS appearing at #CVPR2023 shows we can get accurate video instance segmentation WITHOUT any video or image mask annotations. More at vis.xyz/pub/maskfreevis
00:00
Fisher Yu
@DrFisherYu
May 11, 2023
Monocular depth estimation is “impossible” because one image can’t measure depth geometrically. Our iDisc #CVPR2023 can group pixels w/o supervision and learn depth inductive bias on groups. We get LiDAR-like (but denser) depth from single images! More: vis.xyz/pub/idisc
00:00
Fisher Yu
@DrFisherYu
Mar 30, 2022
Mask Transfiner, appearing @CVPR 2022, produces high-resolution instance segmentation with extreme details without high computation or memory cost. This is enabled by a new principal mechanism called Incoherent Region Prediction. More at vis.xyz/pub/transfiner/
00:00
Fisher Yu
@DrFisherYu
Oct 10, 2021
📢 I am excited to announce that BDD100K model zoo is open for business! It contains more than 100 pre-trained models for various tasks. Each model also comes with results and visualization on val and test sets. You can also put your model in the zoo! 👉github.com/SysCV/bdd100k-…
Fisher Yu
@DrFisherYu
Sep 11, 2017
I just released code for Dilated Residual Networks in @PyTorch. It includes @PyTorch code for semantic segmentation!
GitHub - fyu/drn: Dilated Residual Networks
From github.com
Fisher Yu
@DrFisherYu
May 12, 2022
It is my great pleasure to announce a new release of Scalabel, an open-sourced software that provides a versatile and scalable annotation platform, supporting both 2D and 3D data labeling. Link: github.com/scalabel/scala… 🧵
00:00
Fisher Yu
@DrFisherYu
Mar 27, 2022
Our BDD100K (bdd100k.com) tracking challenges at CVPR 2022 are now live! We hope our challenges can lead to new advances in computer vision and new pragmatic algorithms on self-driving cars. Challenge details: go.yf.io/bdd100k-cvpr22
GIF
Fisher Yu
@DrFisherYu
Nov 16, 2021
While @overleaf was down, it was fueling time for @CVPR at @CVL_ETH
Fisher Yu
@DrFisherYu
Apr 5, 2022
ToMP, appearing @CVPR 2022, is a robust generic object tracker inspired by DCF but employs a Transfomer to predict two sets of model weights used for target classification and bounding box regression. Led by @chris_mayer_ch and @MDanelljan. More at vis.xyz/pub/tomp/
00:00
Fisher Yu
@DrFisherYu
Jul 12, 2019
I am excited to receive the appointment from the Board of ETH today. I will join ETH Zurich next year as Tenure Track Assistant Professor of Computer Vision with affiliation in both EE and CS departments.
Fisher Yu
@DrFisherYu
Feb 15, 2021
I am looking for a postdoc in medical imaging at ETH Zürich. You don't need experience in medical applications, as long as you can show your love for pixels. If interested, please apply at this page go.yf.io/postdoc. Spreading the word is appreciated!
Fisher Yu
@DrFisherYu
Jun 21, 2022
Great day for @CVPR Workshop on Autonomous Driving wad.vision. We need a bigger room next year😂
Fisher Yu
@DrFisherYu
May 31, 2018
We have released BDD100K, a large-scale diverse driving video database with a battery of annotations. If you want to show off your latest detection/segmentation/domain adaptation algorithms, there is still time to participate in our @CVPR challenges!
bair.berkeley.edu
BDD100K: A Large-scale Diverse Driving Video Database
The BAIR Blog
Fisher Yu
@DrFisherYu
Jul 18, 2022
Uncertainty is critical for neural networks to guess what they don't know. Deterministic methods promise strong performance with negligible cost, or do they? We did a reality check. @JanisPostels will present our findings tomorrow at #ICML2022. more at vis.xyz/pub/deu-practi…