• Publications
  • Influence
Depth Map Prediction from a Single Image using a Multi-Scale Deep Network
TLDR
This paper employs two deep network stacks: one that makes a coarse global prediction based on the entire image, and another that refines this prediction locally, and applies a scale-invariant error to help measure depth relations rather than scale.
OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks
TLDR
This integrated framework for using Convolutional Networks for classification, localization and detection is the winner of the localization task of the ImageNet Large Scale Visual Recognition Challenge 2013 and obtained very competitive results for the detection and classifications tasks.
Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-scale Convolutional Architecture
  • D. Eigen, R. Fergus
  • Computer Science
    IEEE International Conference on Computer Vision…
  • 17 November 2014
In this paper we address three different computer vision tasks using a single basic architecture: depth prediction, surface normal estimation, and semantic labeling. We use a multiscale convolutional
Restoring an Image Taken through a Window Covered with Dirt or Rain
TLDR
This work presents a post-capture image processing solution that can remove localized rain and dirt artifacts from a single image, and demonstrates effective removal of dirt and rain in outdoor test conditions.
Nonparametric image parsing using adaptive neighbor sets
  • D. Eigen, R. Fergus
  • Computer Science
    IEEE Conference on Computer Vision and Pattern…
  • 16 June 2012
TLDR
Two novel mechanisms are added: a principled and efficient method for learning per-descriptor weights that minimizes classification error, and a context-driven adaptation of the training set used for each query, which conditions on common classes to improve performance on rare ones.
Finding Task-Relevant Features for Few-Shot Learning by Category Traversal
TLDR
A Category Traversal Module is introduced that can be inserted as a plug-and-play module into most metric-learning based few-shot learners, identifying task-relevant features based on both intra-class commonality and inter-class uniqueness in the feature space.
End-to-end integration of a Convolutional Network, Deformable Parts Model and non-maximum suppression
TLDR
This work trains a new model using a new structured loss function that considers all bounding boxes within an image, rather than isolated object instances, and enables the non-maximal suppression operation, previously treated as a separate post-processing stage, to be integrated into the model.
Learning Factored Representations in a Deep Mixture of Experts
TLDR
The Mixtures of Experts is extended to a stacked model, the Deep Mixture of Experts, with multiple sets of gating and experts, which exponentially increases the number of effective experts by associating each input with a combination of experts at each layer, yet maintains a modest model size.
Unsupervised Learning of Spatiotemporally Coherent Metrics
TLDR
This work focuses on feature learning from unlabeled video data, using the assumption that adjacent video frames contain semantically similar information, and establishes a connection between slow feature learning and metric learning.
Understanding Deep Architectures using a Recursive Convolutional Network
TLDR
The notion that adding layers alone increases computational power, within the context of convolutional layers is empirically confirmed and the number of feature maps appears ancillary, and finds most of its benefit through the introduction of more weights.
...
1
2
...