Get our free extension to see links to code for papers anywhere online!

 Add to Chrome

 Add to Firefox

CatalyzeX Code Finder - Browser extension linking code for ML papers across the web! | Product Hunt Embed
Efficient Scale-Permuted Backbone with Learned Resource Distribution

Oct 22, 2020
Xianzhi Du, Tsung-Yi Lin, Pengchong Jin, Yin Cui, Mingxing Tan, Quoc Le, Xiaodan Song

* ECCV2020 

  Access Paper or Ask Questions

SoDA: Multi-Object Tracking with Soft Data Association

Aug 19, 2020
Wei-Chih Hung, Henrik Kretzschmar, Tsung-Yi Lin, Yuning Chai, Ruichi Yu, Ming-Hsuan Yang, Dragomir Anguelov


  Access Paper or Ask Questions

Mask2CAD: 3D Shape Prediction by Learning to Segment and Retrieve

Jul 26, 2020
Weicheng Kuo, Anelia Angelova, Tsung-Yi Lin, Angela Dai

* ECCV 2020 (Spotlight) 

  Access Paper or Ask Questions

Rethinking Pre-training and Self-training

Jun 11, 2020
Barret Zoph, Golnaz Ghiasi, Tsung-Yi Lin, Yin Cui, Hanxiao Liu, Ekin D. Cubuk, Quoc V. Le


  Access Paper or Ask Questions

Improving Semantic Segmentation through Spatio-Temporal Consistency Learned from Videos

Apr 11, 2020
Ankita Pasad, Ariel Gordon, Tsung-Yi Lin, Anelia Angelova


  Access Paper or Ask Questions

SpineNet: Learning Scale-Permuted Backbone for Recognition and Localization

Dec 10, 2019
Xianzhi Du, Tsung-Yi Lin, Pengchong Jin, Golnaz Ghiasi, Mingxing Tan, Yin Cui, Quoc V. Le, Xiaodan Song


  Access Paper or Ask Questions

MnasFPN: Learning Latency-aware Pyramid Architecture for Object Detection on Mobile Devices

Dec 02, 2019
Bo Chen, Golnaz Ghiasi, Hanxiao Liu, Tsung-Yi Lin, Dmitry Kalenichenko, Hartwig Adams, Quoc V. Le

* 10 pages, 7 figures 

  Access Paper or Ask Questions

Learning Data Augmentation Strategies for Object Detection

Jun 26, 2019
Barret Zoph, Ekin D. Cubuk, Golnaz Ghiasi, Tsung-Yi Lin, Jonathon Shlens, Quoc V. Le


  Access Paper or Ask Questions

NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detection

Apr 16, 2019
Golnaz Ghiasi, Tsung-Yi Lin, Ruoming Pang, Quoc V. Le

* Accepted at CVPR 2019 

  Access Paper or Ask Questions

ShapeMask: Learning to Segment Novel Objects by Refining Shape Priors

Apr 05, 2019
Weicheng Kuo, Anelia Angelova, Jitendra Malik, Tsung-Yi Lin


  Access Paper or Ask Questions

Class-Balanced Loss Based on Effective Number of Samples

Jan 16, 2019
Yin Cui, Menglin Jia, Tsung-Yi Lin, Yang Song, Serge Belongie

* Code is available at: https://github.com/richardaecn/class-balanced-loss 

  Access Paper or Ask Questions

DropBlock: A regularization method for convolutional networks

Oct 30, 2018
Golnaz Ghiasi, Tsung-Yi Lin, Quoc V. Le

* Accepted at NIPS 2018 

  Access Paper or Ask Questions

Focal Loss for Dense Object Detection

Feb 07, 2018
Tsung-Yi Lin, Priya Goyal, Ross Girshick, Kaiming He, Piotr Dollár


  Access Paper or Ask Questions

Feature Pyramid Networks for Object Detection

Apr 19, 2017
Tsung-Yi Lin, Piotr Dollár, Ross Girshick, Kaiming He, Bharath Hariharan, Serge Belongie


  Access Paper or Ask Questions

A MultiPath Network for Object Detection

Aug 08, 2016
Sergey Zagoruyko, Adam Lerer, Tsung-Yi Lin, Pedro O. Pinheiro, Sam Gross, Soumith Chintala, Piotr Dollár


  Access Paper or Ask Questions

Learning to Refine Object Segments

Jul 26, 2016
Pedro O. Pinheiro, Tsung-Yi Lin, Ronan Collobert, Piotr DollĂ r

* extended version of ECCV camera-ready (figures 6-9 only in arXiv) 

  Access Paper or Ask Questions

Microsoft COCO Captions: Data Collection and Evaluation Server

Apr 03, 2015
Xinlei Chen, Hao Fang, Tsung-Yi Lin, Ramakrishna Vedantam, Saurabh Gupta, Piotr Dollar, C. Lawrence Zitnick

* arXiv admin note: text overlap with arXiv:1411.4952 

  Access Paper or Ask Questions

Microsoft COCO: Common Objects in Context

Feb 21, 2015
Tsung-Yi Lin, Michael Maire, Serge Belongie, Lubomir Bourdev, Ross Girshick, James Hays, Pietro Perona, Deva Ramanan, C. Lawrence Zitnick, Piotr Dollár

* 1) updated annotation pipeline description and figures; 2) added new section describing datasets splits; 3) updated author list 

  Access Paper or Ask Questions