• Publications
  • Influence
CNN Features Off-the-Shelf: An Astounding Baseline for Recognition
TLDR
We use features extracted from the OverFeat network as a generic image representation to tackle the diverse range of recognition tasks of object image classification, scene recognition, fine grained recognition, attribute detection and image retrieval applied to a diverse set of datasets. Expand
  • 3,624
  • 237
  • PDF
Visual Instance Retrieval with Deep Convolutional Networks
TLDR
This paper provides an extensive study on the availability of image representations based on convolutional networks (ConvNets) for the task of visual instance retrieval. Expand
  • 231
  • 38
  • PDF
Factors of Transferability for a Generic ConvNet Representation
TLDR
This paper introduces and investigates several factors affecting the transferability of such representations. Expand
  • 209
  • 25
  • PDF
From generic to specific deep representations for visual recognition
TLDR
This paper thoroughly investigates the transferability of such representations w.r.t. several factors. Expand
  • 323
  • 19
  • PDF
A Baseline for Visual Instance Retrieval with Deep Convolutional Networks
TLDR
This paper presents a simple pipeline for visual instance retrieval exploiting image representations based on convolutional networks, and demonstrates that ConvNet image representations outperform other state-of-the-art image representations on six standard image retrieval datasets for the first time. Expand
  • 110
  • 16
  • PDF
Artificial intelligence for analyzing orthopedic trauma radiographs
Background and purpose — Recent advances in artificial intelligence (deep learning) have shown remarkable performance in classifying non-medical images, and the technology is believed to be the nextExpand
  • 86
Estimating Attention in Exhibitions Using Wearable Cameras
TLDR
This paper demonstrates a system for automatic detection of visual attention and identification of salient items at exhibitions (e.g. museum or an auction). Expand
  • 6
  • PDF
The Preimage of Rectifier Network Activities
TLDR
We give a procedure for explicitly computing the complete preimage of activities of a layer in a rectifier network with fully connected layers, from knowledge of the weights in the network. Expand
  • 4
  • PDF
Persistent Evidence of Local Image Properties in Generic ConvNets
TLDR
This paper addresses this, in particular, exploiting the image representation at the first fully connected layer, i.e. the global image descriptor which has been recently shown to be most effective in a range of visual recognition tasks. Expand
  • 6
  • PDF
Ankle fracture classification using deep learning: automating detailed AO Foundation/Orthopedic Trauma Association (AO/OTA) 2018 malleolar fracture identification reaches a high degree of correct
Background and purpose - Classification of ankle fractures is crucial for guiding treatment but advanced classifications such as the AO Foundation/Orthopedic Trauma Association (AO/OTA) are often tooExpand