• Publications
  • Influence
Fine-Grained Visual Classification of Aircraft
TLDR
This paper introduces FGVC-Aircraft, a new dataset containing 10,000 images of aircraft spanning 100 aircraft models, organised in a three-level hierarchy. Expand
  • 525
  • 119
  • PDF
Beyond sliding windows: Object localization by efficient subwindow search
TLDR
We propose a simple yet powerful branch-and-bound scheme that allows efficient maximization of a large class of classifier functions over all possible subimages. Expand
  • 797
  • 82
  • PDF
Efficient Subwindow Search: A Branch and Bound Framework for Object Localization
TLDR
We propose Efficient Subwindow Search (ESS), a method for object localization that does not suffer from these drawbacks. Expand
  • 402
  • 52
  • PDF
Learning to Localize Objects with Structured Output Regression
TLDR
We model object localization in a principled way by posing it as a problem of predicting structured data: we model the problem not as binary classification, but as the prediction of the bounding box. Expand
  • 363
  • 35
  • PDF
Learning a category independent object detection cascade
TLDR
Cascades are a popular framework to speed up object detection systems. Expand
  • 177
  • 27
  • PDF
The Lovasz-Softmax Loss: A Tractable Surrogate for the Optimization of the Intersection-Over-Union Measure in Neural Networks
TLDR
We present a method for direct optimization of the mean intersection-over-union loss in neural networks, in the context of semantic image segmentation, based on the convex Lovász extension of submodular losses. Expand
  • 203
  • 21
  • PDF
Unsupervised Object Discovery: A Comparison
TLDR
The goal of this paper is to evaluate and compare models and methods for learning to recognize basic entities in images in an unsupervised setting. Expand
  • 215
  • 19
  • PDF
A Discriminatively Trained Fully Connected Conditional Random Field Model for Blood Vessel Segmentation in Fundus Images
TLDR
We present an extensive description and evaluation of our method for blood vessel segmentation in fundus images based on a discriminatively trained fully connected conditional random field model. Expand
  • 229
  • 16
Correlational spectral clustering
TLDR
We present a new method for spectral clustering with paired data based on kernel canonical correlation analysis and show consistent empirical improvement over spectral clusters on a variety of datasets of images with text. Expand
  • 196
  • 14
  • PDF
Bond Behavior of CFRP Strips Glued into Slits
  • 74
  • 12
...
1
2
3
4
5
...