• Publications
  • Influence
MobileNetV2: Inverted Residuals and Linear Bottlenecks
TLDR
A new mobile architecture, MobileNetV2, is described 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 and allows decoupling of the input/output domains from the expressiveness of the transformation.
Searching for MobileNetV3
TLDR
This paper starts the exploration of how automated search algorithms and network design can work together to harness complementary approaches improving the overall state of the art of MobileNets.
Inverted Residuals and Linear Bottlenecks: Mobile Networks for Classification, Detection and Segmentation
TLDR
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 is described.
CycleGAN, a Master of Steganography
TLDR
An intriguing property of CycleGAN is demonstrated: CycleGAN learns to "hide" information about a source image into the images it generates in a nearly imperceptible, high-frequency signal, to satisfy the cyclic consistency requirement, while the generated image remains realistic.
K For The Price Of 1: Parameter Efficient Multi-task And Transfer Learning
TLDR
A novel method that enables parameter-efficient transfer and multi-task learning with deep neural networks and shows that re-learning existing low-parameter layers while keeping the rest of the network frozen also improves transfer-learning accuracy significantly.
Using mixture models for collaborative filtering
TLDR
This work develops recommendation algorithms with provable performance guarantees in a probabilistic mixture model for collaborative filtering proposed by Hoffman and Puzicha, and introduces a technique based on generalized pseudoinverse matrices and linear programming for handling sets of high-dimensional vectors.
Inverting face embeddings with convolutional neural networks
TLDR
This work uses neural networks to effectively invert low-dimensional face embeddings while producing realistically looking consistent images and demonstrates that a gradient ascent style approaches can be used to reproduce consistent images, with a help of a guiding image.
Large-Scale Generative Data-Free Distillation
TLDR
This work proposes a new method to train a generative image model by leveraging the intrinsic normalization layers' statistics of the trained teacher network, which enables an ensemble of generators without training data that can efficiently produce substitute inputs for subsequent distillation.
Network failure detection and graph connectivity
TLDR
It is shown that detection set bounds can be made considerably stronger when parameterized by these connectivity values, and for an adversary that can delete κλ edges, there is always a detection set of size <i>O</i>((κ/ε) log (1/ε)) which can be found by random sampling.
Modeling the Parallel Execution of Black-Box Services
TLDR
This paper presents a model that can be used to estimate parent latency given RPC latencies, where the parallel dependencies among of child services are modeled by an "execution flow", a direct acyclic graph.
...
...