330 papers with code ·
Computer Vision

The main technical challenge we consider is the design of best response oracles that can be implemented in a Multiplicative Weight Updates framework to find equilibrium strategies in the zero-sum game.

In light of a recent study on the mutual influence between robustness and accuracy over 18 different ImageNet models, this paper investigates how training data affect the accuracy and robustness of deep neural networks.

Restricting the number of templates yields a flexible hybridization of traditional CNNs and recurrent networks.

A convolutional neural network for image classification can be constructed mathematically since it can be regarded as a multi-period dynamical system.

Our study shows that ZO signSGD requires $\sqrt{d}$ times more iterations than signSGD, leading to a convergence rate of $O(\sqrt{d}/\sqrt{T})$ under mild conditions, where $d$ is the number of optimization variables, and $T$ is the number of iterations.

In federated learning problems, data is scattered across different servers and exchanging or pooling it is often impractical or prohibited.

In this work, we rigorously test these questions, and find that deformation stability in convolutional networks is more nuanced than it first appears: (1) Deformation invariance is not a binary property, but rather that different tasks require different degrees of deformation stability at different layers.

We demonstrate that a simple linear mapping can be learned from sensitivity maps to bounding box coordinates, localizing the recognized object.

Data parallelism has become a dominant method to scale Deep Neural Network (DNN) training across multiple nodes.

High throughput and low latency inference of deep neural networks are critical for the deployment of deep learning applications.

IMAGE CLASSIFICATION OBJECT DETECTION SEMANTIC SEGMENTATION SUPER RESOLUTION