Hang Zhao Massachusetts Institute of Technology Last years - PowerPoint PPT Presentation

Hang Zhao Massachusetts Institute of Technology

Last year’s challenge at ECCV

ADE Dataset

New tasks this year …

Instance Segmentation

Instance Segmentation 2.5 × 10 4 # instances • Sta$s$cs: 2 • 100 foreground categories • 200k instances 1.5 • #Instances per category: 200 ~ 20k • #Instances per image: ~11 1 • Evalua$on: • Mean AP over 100 categories 0.5 0 10 20 30 40 50 60 70 80 90 100

Semantic Boundary Detection Perceptual Edges

Semantic Boundary Detection Binary Edges Category-aware Semantic Boundaries

Semantic Boundary Detection Boundary between: person and chair Boundary between: person and sofa Boundaries reveal object interac8ons

Semantic Boundary Detection • 150 categories • Inter-class boundaries • Intra-class boundaries • Evalua$on: • F-measure at op$mal dataset scale (F-ODS)

Results – Scene Parsing Final Score = (mean IoU + pixel accuracy) / 2 CASIA_IVA_JD Jun Fu, Jing Liu, Longteng Guo, Haijie Team Name Final Score Tian, Fei Liu, Yong Li, Yongjun Bao, CASIA_IVA_JD 0.5547 Weipeng Yan, Hanqing Lu CASIA IVA and JD.com WinterIsComing 0.5544 xdliang 0.5447 lijc15 0.5294 WinterIsComing … … Riwei Chen, Qi Chen, Xinglong Wu, Yifan Lu, Yudong Jiang, Linfu Wen baseline-DilatedNet 0.4567 Tou8ao AI Lab, ByteDance * We received 30 submissions from 10 teams in this task. Full ranking can be found on places challenge website.

Sample Results Scene Parsing

Image Ground Truth Predic$on

Results – Instance Segmentation Megvii (Face++) Team Name mean AP * Tete Xiao, * Ruixuan Luo, * Borui Jiang, Shuai Shao, Yuning Jiang, Yadong Mu, Megvii (Face++) 0.2977 Jieqi Shi, Chi Zhang, Jian Sun Megvii Research and Peking University G-RMI 0.2415 BlueSky 0.1551 … … G-RMI Alireza Fathi, Nori Kanazawa, Kai Yang, baseline 0.200 Kevin Murphy Google Research Machine Intelligence * We received 15 submissions from 5 teams in this task. Full ranking can be found on places challenge website.

Sample Results Instance Segmentation

Results – Semantic Boundary Detection State-of-the-art: CASENet CVPR’17 hmp://www.merl.com/research/license#CASENet Z. Yu, et al. CASENet: Deep category-aware semantic edge detection

Sample Results Semantic Boundary Detection

Image Ground Truth Predic$on

Awards Winner of Scene Parsing: CASIA_IVA_JD Jun Fu, Jing Liu, Longteng Guo, Haijie Tian, Fei Liu, Yong Li, Yongjun Bao, Weipeng Yan, Hanqing Lu CASIA IVA and JD.com Prize: Titan Xp GPU Sponsored by: NVIDIA

Awards Winner of Instance Segmenta8on: Megvii (Face++) * Tete Xiao, * Ruixuan Luo, * Borui Jiang, Shuai Shao, Yuning Jiang, Yadong Mu, Jieqi Shi, Chi Zhang, Jian Sun Megvii Research and Peking University Prize: Titan Xp GPU Sponsored by: NVIDIA

Hang Zhao Massachusetts Institute of Technology Last years - PowerPoint PPT Presentation

Hang Zhao Massachusetts Institute of Technology Last years challenge at ECCV ADE Dataset New tasks this year Instance Segmentation Instance Segmentation 2.5 10 4 # instances Sta$s$cs: 2 100 foreground categories 200k

More Sums than Differences Sets and Beyond Yufei Zhao Massachusetts Institute of Technology

Extremal results for sparse pseudorandom graphs Yufei Zhao Massachusetts Institute of Technology

Transverse Hadron Structures from Lattice QCD with LaMET Yong Zhao Massachusetts Institute of

Parton Distributions from Large-Momentum Effective Theory Yong Zhao Massachusetts Institute of

III-V CMOS: Quo Vadis? J. A. del Alamo, X. Cai, W. Lu, A. Vardi, and X. Zhao Microsystems

Towards Sub-10 nm Diameter I nGaAs Vertical Nanowire MOSFETs and TFETs J. A. del Alamo, X. Zhao,

Sub-10 nm Diameter InGaAs Vertical Nanowire MOSFETs X. Zhao, C. Heidelberger, E. A. Fitzgerald,

Towards Sub-10 nm Diameter III-V VNW Transistors Wenjie Lu, Xin Zhao, Jess A. del Alamo

Quo Vad adis? = = Wher ere e are e you going? 2 I I I -V CMOS: The Promise Scaling: Voltage

CMOS beyond Si: Nanometer-Scale I I I -V MOSFETs J. A. del Alamo, X. Cai, J. Lin, W. Lu, A.

I I I -V MOSFETs for Future CMOS J. A. del Alamo, D. A. Antoniadis, J. Lin, W. Lu, A. Vardi and

IMAGE RESTORATION WITH NEURAL NETWORKS Orazio Gallo Work with Hang Zhao, Iuri Frosio, Jan Kautz

11/27/2006 Massachusetts Institute of Technology Motivation Would like robotic manipulators

11/27/2006 Massachusetts Institute of Technology Outline Motivation Example Generalized

Ma Match chin ing ti ti e Q e Qua uasi P i Par tp tp n Dis ts ts ibu tj tj on in a Momentu tum

Symmetry tests using () mesons Mike Williams Massachusetts Institute of Technology

3 rd Data Prefetching Championship June 23 rd , 2019 Held in conjunction with ISCA 2019 Seth

CSEP504: Advanced topics in software systems Tonight India trip report Apologies and

FairWare 2018 http://fairware.cs.umass.edu Welcome from the organizers Brittany Johnson

iCub Whole-Body Control Through Force Regulation on Rigid Non-Coplanar Contacts Francesco Nori

Code Similarity via Natural Language Descriptions Meital Ben Sinai & Eran Yahav Technion

Criticality Aware Tiered Cache Hierarchy (CATCH) Anant Nori, Jayesh Gaur, Siddharth Rai # ,

Probabilistic Programming Frank Wood frank@invrea.com

Make your code count Quantum simulations and collaborative code QuTiP: Shahnawaz Ahmed The

Hang Zhao Massachusetts Institute of Technology Last years - PowerPoint PPT Presentation

Hang Zhao Massachusetts Institute of Technology Last years challenge at ECCV ADE Dataset New tasks this year Instance Segmentation Instance Segmentation 2.5 10 4 # instances Sta$s$cs: 2 100 foreground categories 200k

More Sums than Differences Sets and Beyond Yufei Zhao Massachusetts Institute of Technology

Extremal results for sparse pseudorandom graphs Yufei Zhao Massachusetts Institute of Technology

Transverse Hadron Structures from Lattice QCD with LaMET Yong Zhao Massachusetts Institute of

Parton Distributions from Large-Momentum Effective Theory Yong Zhao Massachusetts Institute of

III-V CMOS: Quo Vadis? J. A. del Alamo, X. Cai, W. Lu, A. Vardi, and X. Zhao Microsystems

Towards Sub-10 nm Diameter I nGaAs Vertical Nanowire MOSFETs and TFETs J. A. del Alamo, X. Zhao,

Sub-10 nm Diameter InGaAs Vertical Nanowire MOSFETs X. Zhao, C. Heidelberger, E. A. Fitzgerald,

Towards Sub-10 nm Diameter III-V VNW Transistors Wenjie Lu, Xin Zhao, Jess A. del Alamo

Quo Vad adis? = = Wher ere e are e you going? 2 I I I -V CMOS: The Promise Scaling: Voltage

CMOS beyond Si: Nanometer-Scale I I I -V MOSFETs J. A. del Alamo, X. Cai, J. Lin, W. Lu, A.

I I I -V MOSFETs for Future CMOS J. A. del Alamo, D. A. Antoniadis, J. Lin, W. Lu, A. Vardi and

IMAGE RESTORATION WITH NEURAL NETWORKS Orazio Gallo Work with Hang Zhao, Iuri Frosio, Jan Kautz

11/27/2006 Massachusetts Institute of Technology Motivation Would like robotic manipulators

11/27/2006 Massachusetts Institute of Technology Outline Motivation Example Generalized

Ma Match chin ing ti ti e Q e Qua uasi P i Par tp tp n Dis ts ts ibu tj tj on in a Momentu tum

Symmetry tests using () mesons Mike Williams Massachusetts Institute of Technology

3 rd Data Prefetching Championship June 23 rd , 2019 Held in conjunction with ISCA 2019 Seth

CSEP504: Advanced topics in software systems Tonight India trip report Apologies and

FairWare 2018 http://fairware.cs.umass.edu Welcome from the organizers Brittany Johnson

iCub Whole-Body Control Through Force Regulation on Rigid Non-Coplanar Contacts Francesco Nori

Code Similarity via Natural Language Descriptions Meital Ben Sinai &amp; Eran Yahav Technion

Criticality Aware Tiered Cache Hierarchy (CATCH) Anant Nori*, Jayesh Gaur*, Siddharth Rai # ,

Probabilistic Programming Frank Wood frank@invrea.com

Make your code count Quantum simulations and collaborative code QuTiP: Shahnawaz Ahmed The

Code Similarity via Natural Language Descriptions Meital Ben Sinai & Eran Yahav Technion

Criticality Aware Tiered Cache Hierarchy (CATCH) Anant Nori, Jayesh Gaur, Siddharth Rai # ,