9.8k citations · 12.4k across the 20 of their papers we have counts for
21 papers
ReMaX: Relaxing for Better Training on Efficient Panoptic Segmentation
Shuyang Sun, Weijun Wang, Qihang Yu +3
This paper presents a new mechanism to facilitate the training of mask transformers for efficient panoptic segmentation, democratizing its deployment. We observe that due to its hi…
On Label Granularity and Object Localization
Elijah Cole, Kimberly Wilber, Grant Van Horn +6
Weakly supervised object localization (WSOL) aims to learn representations that encode object location using only image-level category labels. However, many objects can be labeled…
MOSAIC: Mobile Segmentation via decoding Aggregated Information and encoded Context
Weijun Wang, Andrew Howard
We present a next-generation neural network architecture, MOSAIC, for efficient and accurate semantic image segmentation on mobile devices. MOSAIC is designed using commonly suppor…
Bridging the Gap Between Object Detection and User Intent via Query-Modulation
Marco Fornoni, Chaochao Yan, Liangchen Luo +5
When interacting with objects through cameras, or pictures, users often have a specific intent. For example, they may want to perform a visual search. With most object detection mo…
BasisNet: Two-stage Model Synthesis for Efficient Inference
Mingda Zhang, Chun-Te Chu, Andrey Zhmoginov +6
In this work, we present BasisNet which combines recent advancements in efficient neural network architectures, conditional computation, and early termination in a simple new form.…
SpotPatch: Parameter-Efficient Transfer Learning for Mobile Object Detection
Keren Ye, Adriana Kovashka, Mark Sandler +3
Deep learning based object detectors are commonly deployed on mobile devices to solve a variety of tasks. For maximum accuracy, each detector is usually trained to solve one single…
Large-Scale Generative Data-Free Distillation
Liangchen Luo, Mark Sandler, Zi Lin +2
Knowledge distillation is one of the most popular and effective techniques for knowledge transfer, model compression and semi-supervised learning. Most existing distillation approa…
Multi-path Neural Networks for On-device Multi-domain Visual Classification
Qifei Wang, Junjie Ke, Joshua Greaves +9
Learning multiple domains/tasks with a single model is important for improving data efficiency and lowering inference cost for numerous vision tasks, especially on resource-constra…
Discovering Multi-Hardware Mobile Models via Architecture Search
Grace Chu, Okan Arikan, Gabriel Bender +7
Hardware-aware neural architecture designs have been predominantly focusing on optimizing model performance on single hardware and model development complexity, where another impor…
Non-discriminative data or weak model? On the relative importance of data and model resolution
Mark Sandler, Jonathan Baccash, Andrey Zhmoginov +1
We explore the question of how the resolution of the input image ("input resolution") affects the performance of a neural network when compared to the resolution of the hidden laye…
Visual Wake Words Dataset
Aakanksha Chowdhery, Pete Warden, Jonathon Shlens +2
The emergence of Internet of Things (IoT) applications requires intelligence on the edge. Microcontrollers provide a low-cost compute platform to deploy intelligent IoT application…
Geo-Aware Networks for Fine-Grained Recognition
Grace Chu, Brian Potetz, Weijun Wang +5
Fine-grained recognition distinguishes among categories with subtle visual differences. In order to differentiate between these challenging visual categories, it is helpful to leve…
Searching for MobileNetV3
Andrew Howard, Mark Sandler, Grace Chu +9
We present the next generation of MobileNets based on a combination of complementary search techniques as well as a novel architecture design. MobileNetV3 is tuned to mobile phone…
Low-Power Computer Vision: Status, Challenges, Opportunities
Sergei Alyamkin, Matthew Ardi, Alexander C. Berg +41
Computer vision has achieved impressive progress in recent years. Meanwhile, mobile phones have become the primary computing platforms for millions of people. In addition to mobile…
2018 Low-Power Image Recognition Challenge
Sergei Alyamkin, Matthew Ardi, Achille Brighton +38
The Low-Power Image Recognition Challenge (LPIRC, https://rebootingcomputing.ieee.org/lpirc) is an annual competition started in 2015. The competition identifies the best technolog…
K for the Price of 1: Parameter-efficient Multi-task and Transfer Learning
Pramod Kaushik Mudrakarta, Mark Sandler, Andrey Zhmoginov +1
We introduce a novel method that enables parameter-efficient transfer and multi-task learning with deep neural networks. The basic approach is to learn a model patch - a small set…
Large Scale Fine-Grained Categorization and Domain-Specific Transfer Learning
Yin Cui, Yang Song, Chen Sun +2
Transferring the knowledge learned from large scale datasets (e.g., ImageNet) via fine-tuning offers an effective solution for domain-specific fine-grained visual categorization (F…
NetAdapt: Platform-Aware Neural Network Adaptation for Mobile Applications
Tien-Ju Yang, Andrew Howard, Bo Chen +5
This work proposes an algorithm, called NetAdapt, that automatically adapts a pre-trained deep neural network to a mobile platform given a resource budget. While many existing algo…
MobileNetV2: Inverted Residuals and Linear Bottlenecks
Mark Sandler, Andrew Howard, Menglong Zhu +2
In this paper we describe a new mobile architecture, MobileNetV2, that improves the state of the art performance of mobile models on multiple tasks and benchmarks as well as across…
Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference
Benoit Jacob, Skirmantas Kligys, Bo Chen +5
The rising popularity of intelligent mobile devices and the daunting computational cost of deep learning-based models call for efficient and accurate on-device inference schemes. W…
MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
Andrew G. Howard, Menglong Zhu, Bo Chen +5
We present a class of efficient models called MobileNets for mobile and embedded vision applications. MobileNets are based on a streamlined architecture that uses depth-wise separa…