• Publications
  • Influence
Wide Residual Networks
Deep residual networks were shown to be able to scale up to thousands of layers and still have improving performance. However, each fraction of a percent of improved accuracy costs nearly doublingExpand
  • 2,289
  • 523
  • Open Access
Learning to compare image patches via convolutional neural networks
In this paper we show how to learn directly from image data (i.e., without resorting to manually-designed features) a general similarity function for comparing image patches, which is a task ofExpand
  • 848
  • 129
  • Open Access
Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer
Attention plays a critical role in human visual experience. Furthermore, it has recently been demonstrated that attention can also play an important role in the context of applying artificial neuralExpand
  • 476
  • 90
  • Open Access
A MultiPath Network for Object Detection
The recent COCO object detection dataset presents several new challenges for object detection. In particular, it contains objects at a broad range of scales, less prototypical images, and requiresExpand
  • 149
  • 17
  • Open Access
Scaling the Scattering Transform: Deep Hybrid Networks
We use the scattering network as a generic and fixed initialization of the first layers of a supervised hybrid deep network. We show that early layers do not necessarily need to be learned, providingExpand
  • 75
  • 9
  • Open Access
DiracNets: Training Very Deep Neural Networks Without Skip-Connections
Deep neural networks with skip-connections, such as ResNet, show excellent performance in various image classification benchmarks. It is though observed that the initial motivation behind them -Expand
  • 32
  • 3
  • Open Access
BENCHMARKING DEEP LEARNING FRAMEWORKS FOR THE CLASSIFICATION OF VERY HIGH RESOLUTION SATELLITE MULTISPECTRAL DATA
Abstract. In this paper we evaluated deep-learning frameworks based on Convolutional Neural Networks for the accurate classification of multispectral remote sensing data. Certain state-of-the-artExpand
  • 41
  • 3
  • Open Access
End-to-End Object Detection with Transformers
We present a new method that views object detection as a direct set prediction problem. Our approach streamlines the detection pipeline, effectively removing the need for many hand-designedExpand
  • 28
  • 2
  • Open Access
Scattering Networks for Hybrid Representation Learning
Scattering networks are a class of designed Convolutional Neural Networks (CNNs) with fixed weights. We argue they can serve as generic representations for modelling images. In particular, by workingExpand
  • 16
  • 2
  • Open Access
A MRF shape prior for facade parsing with occlusions
We present a new shape prior formalism for the segmentation of rectified facade images. It combines the simplicity of split grammars with unprecedented expressive power: the capability of encodingExpand
  • 32
  • 2
  • Open Access