Alert button
Picture for Andrew Howard

Andrew Howard

Alert button

ReMaX: Relaxing for Better Training on Efficient Panoptic Segmentation

Jun 29, 2023
Shuyang Sun, Weijun Wang, Qihang Yu, Andrew Howard, Philip Torr, Liang-Chieh Chen

Figure 1 for ReMaX: Relaxing for Better Training on Efficient Panoptic Segmentation
Figure 2 for ReMaX: Relaxing for Better Training on Efficient Panoptic Segmentation
Figure 3 for ReMaX: Relaxing for Better Training on Efficient Panoptic Segmentation
Figure 4 for ReMaX: Relaxing for Better Training on Efficient Panoptic Segmentation
Viaarxiv icon

On Label Granularity and Object Localization

Jul 20, 2022
Elijah Cole, Kimberly Wilber, Grant Van Horn, Xuan Yang, Marco Fornoni, Pietro Perona, Serge Belongie, Andrew Howard, Oisin Mac Aodha

Figure 1 for On Label Granularity and Object Localization
Figure 2 for On Label Granularity and Object Localization
Figure 3 for On Label Granularity and Object Localization
Figure 4 for On Label Granularity and Object Localization
Viaarxiv icon

MOSAIC: Mobile Segmentation via decoding Aggregated Information and encoded Context

Dec 22, 2021
Weijun Wang, Andrew Howard

Figure 1 for MOSAIC: Mobile Segmentation via decoding Aggregated Information and encoded Context
Figure 2 for MOSAIC: Mobile Segmentation via decoding Aggregated Information and encoded Context
Figure 3 for MOSAIC: Mobile Segmentation via decoding Aggregated Information and encoded Context
Figure 4 for MOSAIC: Mobile Segmentation via decoding Aggregated Information and encoded Context
Viaarxiv icon

Bridging the Gap Between Object Detection and User Intent via Query-Modulation

Jun 18, 2021
Marco Fornoni, Chaochao Yan, Liangchen Luo, Kimberly Wilber, Alex Stark, Yin Cui, Boqing Gong, Andrew Howard

Figure 1 for Bridging the Gap Between Object Detection and User Intent via Query-Modulation
Figure 2 for Bridging the Gap Between Object Detection and User Intent via Query-Modulation
Figure 3 for Bridging the Gap Between Object Detection and User Intent via Query-Modulation
Figure 4 for Bridging the Gap Between Object Detection and User Intent via Query-Modulation
Viaarxiv icon

BasisNet: Two-stage Model Synthesis for Efficient Inference

May 07, 2021
Mingda Zhang, Chun-Te Chu, Andrey Zhmoginov, Andrew Howard, Brendan Jou, Yukun Zhu, Li Zhang, Rebecca Hwa, Adriana Kovashka

Figure 1 for BasisNet: Two-stage Model Synthesis for Efficient Inference
Figure 2 for BasisNet: Two-stage Model Synthesis for Efficient Inference
Figure 3 for BasisNet: Two-stage Model Synthesis for Efficient Inference
Figure 4 for BasisNet: Two-stage Model Synthesis for Efficient Inference
Viaarxiv icon

SpotPatch: Parameter-Efficient Transfer Learning for Mobile Object Detection

Jan 04, 2021
Keren Ye, Adriana Kovashka, Mark Sandler, Menglong Zhu, Andrew Howard, Marco Fornoni

Figure 1 for SpotPatch: Parameter-Efficient Transfer Learning for Mobile Object Detection
Figure 2 for SpotPatch: Parameter-Efficient Transfer Learning for Mobile Object Detection
Figure 3 for SpotPatch: Parameter-Efficient Transfer Learning for Mobile Object Detection
Figure 4 for SpotPatch: Parameter-Efficient Transfer Learning for Mobile Object Detection
Viaarxiv icon

Large-Scale Generative Data-Free Distillation

Dec 10, 2020
Liangchen Luo, Mark Sandler, Zi Lin, Andrey Zhmoginov, Andrew Howard

Figure 1 for Large-Scale Generative Data-Free Distillation
Figure 2 for Large-Scale Generative Data-Free Distillation
Figure 3 for Large-Scale Generative Data-Free Distillation
Figure 4 for Large-Scale Generative Data-Free Distillation
Viaarxiv icon

Multi-path Neural Networks for On-device Multi-domain Visual Classification

Oct 10, 2020
Qifei Wang, Junjie Ke, Joshua Greaves, Grace Chu, Gabriel Bender, Luciano Sbaiz, Alec Go, Andrew Howard, Feng Yang, Ming-Hsuan Yang, Jeff Gilbert, Peyman Milanfar

Figure 1 for Multi-path Neural Networks for On-device Multi-domain Visual Classification
Figure 2 for Multi-path Neural Networks for On-device Multi-domain Visual Classification
Figure 3 for Multi-path Neural Networks for On-device Multi-domain Visual Classification
Figure 4 for Multi-path Neural Networks for On-device Multi-domain Visual Classification
Viaarxiv icon

Discovering Multi-Hardware Mobile Models via Architecture Search

Aug 18, 2020
Grace Chu, Okan Arikan, Gabriel Bender, Weijun Wang, Achille Brighton, Pieter-Jan Kindermans, Hanxiao Liu, Berkin Akin, Suyog Gupta, Andrew Howard

Figure 1 for Discovering Multi-Hardware Mobile Models via Architecture Search
Figure 2 for Discovering Multi-Hardware Mobile Models via Architecture Search
Figure 3 for Discovering Multi-Hardware Mobile Models via Architecture Search
Figure 4 for Discovering Multi-Hardware Mobile Models via Architecture Search
Viaarxiv icon

Non-discriminative data or weak model? On the relative importance of data and model resolution

Oct 17, 2019
Mark Sandler, Jonathan Baccash, Andrey Zhmoginov, Andrew Howard

Figure 1 for Non-discriminative data or weak model? On the relative importance of data and model resolution
Figure 2 for Non-discriminative data or weak model? On the relative importance of data and model resolution
Figure 3 for Non-discriminative data or weak model? On the relative importance of data and model resolution
Figure 4 for Non-discriminative data or weak model? On the relative importance of data and model resolution
Viaarxiv icon