profile
viewpoint
If you are wondering where the data of this site comes from, please visit https://api.github.com/users/tfzhou/events. GitMemory does not store any data, but only uses NGINX to cache data for a period of time. The idea behind GitMemory is simply to give users a better reading experience.
Tianfei Zhou tfzhou Computer Vision Laboratory, ETH Zurich Switzerland http://www.tfzhou.com/

tfzhou/ContrastiveSeg 234

ICCV2021 (Oral) - Exploring Cross-Image Pixel Contrast for Semantic Segmentation

tfzhou/MATNet 126

Motion-Attentive Transition for Zero-Shot Video Object Segmentation (AAAI2020)

hlesmqh/WS3D 81

Official version of 'Weakly Supervised 3D object detection from Lidar Point Cloud'(ECCV2020)

tfzhou/C-HOI 72

Cascaded Human-Object Interaction Recognition (CVPR2020)

Lixy1997/Group-WSSS 53

Group-Wise Semantic Mining for Weakly Supervised Semantic Segmentation

tfzhou/MG-HumanParsing 46

Differentiable Multi-Granularity Human Representation Learning for Instance-Aware Human Semantic Parsing

tfzhou/BINGObjectness 24

BING Objectness proposal estimator Matlab wrapper. More in http://mmcheng.net/bing/

tfzhou/FFIW 15

Face Forensics in the Wild

tfzhou/Detectron-with-tensorboard 6

FAIR's research platform for object detection research, implementing popular algorithms like Mask R-CNN and RetinaNet.

issue closedtfzhou/ContrastiveSeg

Code/main_contrastive.py

Hi, Dr.Zhou. Sorry to bother you, but could you please give an example to conduct the command file? Considering various version of bash files, it would be nice to give an description about your naming style. For example, (1) "run_ideal_spatial_ocrnet.sh", "xxx_ideal_gather_ocrnet.sh", and "xxx_ideal_distribute_octnet.sh" (2) "run_ideal_spatial_ocrnet.sh", "run_ideal_spatial_ocrnet_b.sh", and "run_ideal_spatial_ocrnet_c.sh"

Thank you, and looking forward to your reponse.

closed time in 4 days

VivianBB

issue closedtfzhou/ContrastiveSeg

tsne

hi, how do you use tsne in a segmentation network to have such visualization? thanks

closed time in 4 days

tahmine88

issue commenttfzhou/ContrastiveSeg

tsne

Hi, you may save the embeddings into numpy files and then visualize tsne plots.

tahmine88

comment created time in 4 days

issue commenttfzhou/ContrastiveSeg

implementation of memory bank?

Thanks for your interest. Now I have updated the codes. I will close this, but feel free to reopen if you have more questions.

jiangzhengkai

comment created time in 4 days

issue closedtfzhou/ContrastiveSeg

implementation of memory bank?

Hi, thanks for your great work. Will you update the code for the memory bank?

closed time in 4 days

jiangzhengkai

issue closedtfzhou/ContrastiveSeg

memory using?

Hello, Dr. Zhou, I have not seen the application of memory bank in the code base?

closed time in 4 days

InvictusRichard

issue commenttfzhou/ContrastiveSeg

memory using?

Thanks for your interest. Now I have updated the codes. I will close this, but feel free to reopen if you have more questions.

InvictusRichard

comment created time in 4 days

issue commenttfzhou/ContrastiveSeg

Code/main_contrastive.py

Hi, please refer to the files with names "job_xxxx.sh", which show how to start training. For more training and inference details, please also refer to the original OpenSeg repo.

VivianBB

comment created time in 4 days

issue closedtfzhou/ContrastiveSeg

test with my own images

How do I run inference on my own images?

Thanks,

closed time in 4 days

fjremnav

issue closedtfzhou/ContrastiveSeg

about the loss_contrast.py

Thank you very much for sharing.There is a place in the code that I don't understand. Could you please tell me, In loss_contrast.py what is meanning of the _hard_anchor_sampling.Would you please explain its use to me

closed time in 4 days

PanPan0210

push eventtfzhou/ContrastiveSeg

tfzhou

commit sha c5862b926c7d84b06a1ab51d526584700e75570b

Add memory code

view details

tfzhou

commit sha 2ab84d8ec679adc7f7be1853c8684b44bf899273

Update readme

view details

push time in 4 days

startedrichzhang/webpage-template

started time in 9 days

fork tfzhou/andreea7b.github.io

A beautiful Jekyll theme for academics

fork in 20 days

issue closedtfzhou/ContrastiveSeg

When you provide pretrained model?

When you provide pretrained model?

closed time in a month

Megumi-cs

issue commenttfzhou/ContrastiveSeg

When you provide pretrained model?

I will close this since some checkpoints are available.

Megumi-cs

comment created time in a month

issue commenttfzhou/ContrastiveSeg

about the loss_contrast.py

Please see first the "Segmentation-Aware Hard Anchor Sampling" of Sec 3.2 in our paper.

PanPan0210

comment created time in a month

issue commenttfzhou/ContrastiveSeg

test with my own images

Hi @fjremnav , sorry for that I have no plan to write this script. It will be perfect if you would write it. The file may have a simple pipeline:

# 1. define the model and load the pretrained weight
# 2. load the image using opencv
# 3. convert the image array to tensor with shape 1 x 3 x h x w
# 4. call the forward function of the model

you can also refer to this line.

fjremnav

comment created time in a month

push event0liliulei/Mem3D

Tianfei Zhou

commit sha 31c3a40e149b1922778cd7d11de6425297f28020

Update README.md

view details

push time in a month

issue commenttfzhou/ContrastiveSeg

test with my own images

Hi, there is no inference script for testing a single image now. But I guess it will not be hard to do that.

fjremnav

comment created time in a month

push eventtfzhou/ContrastiveSeg

tfzhou

commit sha fa9ebe0cf04db92633d4ff481c1256e54edf1a2d

Fix markdown

view details

push time in a month

push eventtfzhou/ContrastiveSeg

tfzhou

commit sha 310120712ad4b6ecea45c3ac1143118f959c86e4

update deeplabv3

view details

push time in a month

push eventtfzhou/MG-HumanParsing

tfzhou

commit sha 9df83d2bd6cae9c1daa8cd565d0a1fb0c929d0e6

update script name

view details

push time in a month

push eventtfzhou/MG-HumanParsing

tfzhou

commit sha f241b52aeba74348c1cb3899f8d4ce02a2c717ae

remove idea

view details

push time in a month

push eventtfzhou/MG-HumanParsing

tfzhou

commit sha 8729c115079120c424e8faf20d895d80f9c8b2f2

Initial commit

view details

push time in a month

push eventtfzhou/ContrastiveSeg

tfzhou

commit sha 76e319aedacdd09a4e2be5b36f13093c26f9ce01

update README

view details

push time in a month

push eventtfzhou/ContrastiveSeg

tfzhou

commit sha 31da9d2149c30a0278e71d2b49d2920bbe125763

update README

view details

push time in a month

created tagtfzhou/pretrained_weights

tagv0.1

created time in a month

push eventtfzhou/ContrastiveSeg

tfzhou

commit sha e575f101b8b0c7694f764b80733284edd8448c9e

Bump pytorch version to 1.7

view details

push time in a month