Search Results for author:
Found 29 papers, 14 papers with code
Robust Training of Neural Networks at Arbitrary Precision and Sparsity
The discontinuous operations inherent in quantization and sparsification introduce obstacles to backpropagation.
Custom Gradient Estimators are Straight-Through Estimators in Disguise
Quantization-aware training comes with a fundamental challenge: the derivative of quantization functions such as rounding are zero almost everywhere and nonexistent elsewhere.
MobileNetV4 -- Universal Models for the Mobile Ecosystem
We present the latest generation of MobileNets, known as MobileNetV4 (MNv4), featuring universally efficient architecture designs for mobile devices.
Ranked #430 on
Image Classification
on ImageNet
PikeLPN: Mitigating Overlooked Inefficiencies of Low-Precision Neural Networks
Our analysis reveals that non-quantized elementwise operations which are prevalent in layers such as parameterized activation functions batch normalization and quantization scaling dominate the inference cost of low-precision models.
ReMaX: Relaxing for Better Training on Efficient Panoptic Segmentation
This paper presents a new mechanism to facilitate the training of mask transformers for efficient panoptic segmentation, democratizing its deployment.
On Label Granularity and Object Localization
Weakly supervised object localization (WSOL) aims to learn representations that encode object location using only image-level category labels.
MOSAIC: Mobile Segmentation via decoding Aggregated Information and encoded Context
We present a next-generation neural network architecture, MOSAIC, for efficient and accurate semantic image segmentation on mobile devices.
Bridging the Gap Between Object Detection and User Intent via Query-Modulation
When interacting with objects through cameras, or pictures, users often have a specific intent.
BasisNet: Two-stage Model Synthesis for Efficient Inference
With early termination, the average cost can be further reduced to 198M MAdds while maintaining accuracy of 80. 0% on ImageNet.
Ranked #724 on
Image Classification
on ImageNet
Dynamical orbital evolution scenarios of the wide-orbit eccentric planet HR 5183b
In this paper, we explore scenarios for the excitation of the eccentricity of the planet in binary systems such as this, considering planet-planet scattering, Lidov-Kozai cycles from the binary acting on a single-planet system, or Lidov-Kozai cycles acting on a two-planet system that also undergoes scattering.
Earth and Planetary Astrophysics
SpotPatch: Parameter-Efficient Transfer Learning for Mobile Object Detection
In this paper we address the question: can task-specific detectors be trained and represented as a shared set of weights, plus a very small set of additional weights for each task?
Large-Scale Generative Data-Free Distillation
Knowledge distillation is one of the most popular and effective techniques for knowledge transfer, model compression and semi-supervised learning.
The Occurrence of Rocky Habitable Zone Planets Around Solar-Like Stars from Kepler Data
We present occurrence rates for rocky planets in the habitable zones (HZ) of main-sequence dwarf stars based on the Kepler DR25 planet candidate catalog and Gaia-based stellar properties.
Earth and Planetary Astrophysics Solar and Stellar Astrophysics
Multi-path Neural Networks for On-device Multi-domain Visual Classification
This approach effectively reduces the total number of parameters and FLOPS, encouraging positive knowledge transfer while mitigating negative interference across domains.
Discovering Multi-Hardware Mobile Models via Architecture Search
Hardware-aware neural architecture designs have been predominantly focusing on optimizing model performance on single hardware and model development complexity, where another important factor, model deployment complexity, has been largely ignored.
Non-discriminative data or weak model? On the relative importance of data and model resolution
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 layers ("internal resolution").
Visual Wake Words Dataset
To facilitate the development of microcontroller friendly models, we present a new dataset, Visual Wake Words, that represents a common microcontroller vision use-case of identifying whether a person is present in the image or not, and provides a realistic benchmark for tiny vision models.
Geo-Aware Networks for Fine-Grained Recognition
By leveraging geolocation information we improve top-1 accuracy in iNaturalist from 70. 1% to 79. 0% for a strong baseline image-only model.
Searching for MobileNetV3
We achieve new state of the art results for mobile classification, detection and segmentation.
Ranked #9 on
Dichotomous Image Segmentation
on DIS-TE1
K For The Price Of 1: Parameter Efficient Multi-task And Transfer Learning
We introduce a novel method that enables parameter-efficient transfer and multitask learning.
Low-Power Computer Vision: Status, Challenges, Opportunities
In addition to mobile phones, many autonomous systems rely on visual data for making decisions and some of these systems have limited energy (such as unmanned aerial vehicles also called drones and mobile robots).
K for the Price of 1: Parameter-efficient Multi-task and Transfer Learning
We introduce a novel method that enables parameter-efficient transfer and multi-task learning with deep neural networks.
2018 Low-Power Image Recognition Challenge
The Low-Power Image Recognition Challenge (LPIRC, https://rebootingcomputing. ieee. org/lpirc) is an annual competition started in 2015.
MnasNet: Platform-Aware Neural Architecture Search for Mobile
In this paper, we propose an automated mobile neural architecture search (MNAS) approach, which explicitly incorporate model latency into the main objective so that the search can identify a model that achieves a good trade-off between accuracy and latency.
Ranked #902 on
Image Classification
on ImageNet
Large Scale Fine-Grained Categorization and Domain-Specific Transfer Learning
We propose a measure to estimate domain similarity via Earth Mover's Distance and demonstrate that transfer learning benefits from pre-training on a source domain that is similar to the target domain by this measure.
Ranked #33 on
Fine-Grained Image Classification
on CUB-200-2011
Fine-Grained Image Classification
Fine-Grained Visual Categorization
+1
NetAdapt: Platform-Aware Neural Network Adaptation for Mobile Applications
This work proposes an algorithm, called NetAdapt, that automatically adapts a pre-trained deep neural network to a mobile platform given a resource budget.
MobileNetV2: Inverted Residuals and Linear Bottlenecks
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 a spectrum of different model sizes.
Ranked #7 on
Retinal OCT Disease Classification
on OCT2017
Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference
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.
The Unreasonable Effectiveness of Noisy Data for Fine-Grained Recognition
Current approaches for fine-grained recognition do the following: First, recruit experts to annotate a dataset of images, optionally also collecting more structured data in the form of part annotations and bounding boxes.
Ranked #6 on
Fine-Grained Image Classification
on CUB-200-2011
(using extra training data)
