#### Filter Results:

- Full text PDF available (21)

#### Publication Year

2008

2017

- This year (1)
- Last 5 years (17)
- Last 10 years (22)

#### Publication Type

#### Co-author

#### Journals and Conferences

#### Data Set Used

#### Key Phrases

Learn More

- Philipp Krähenbühl, Vladlen Koltun
- NIPS
- 2011

where the partition function is defined as Z = ∑ x P̃ (x). Let’s define an approximate distribution Q(X) = ∏ iQi(Xi) as a product of independent marginals Qi(Xi) over each variable in the CRF. For notational clarity we use Qi(Xi) to denote the marginal over variable Xi, rather than the more commonly used Q(Xi). The mean field approximation models a… (More)

- Federico Perazzi, Philipp Krähenbühl, Yael Pritch, Alexander Sorkine-Hornung
- 2012 IEEE Conference on Computer Vision and…
- 2012

Saliency estimation has become a valuable tool in image processing. Yet, existing approaches exhibit considerable variation in methodology, and it is often difficult to attribute improvements in result quality to specific algorithm properties. In this paper we reconsider some of the design choices of previous methods and propose a conceptually clear and… (More)

- Philipp Krähenbühl, Vladlen Koltun
- ECCV
- 2014

We present an approach for identifying a set of candidate objects in a given image. This set of candidates can be used for object recognition, segmentation, and other object-based image parsing tasks. To generate the proposals, we identify critical level sets in geodesic distance transforms computed for seeds placed in the image. The seeds are placed by… (More)

- Deepak Pathak, Philipp Krähenbühl, Jeff Donahue, Trevor Darrell, Alexei A. Efros
- 2016 IEEE Conference on Computer Vision and…
- 2016

We present an unsupervised visual feature learning algorithm driven by context-based pixel prediction. By analogy with auto-encoders, we propose Context Encoders - a convolutional neural network trained to generate the contents of an arbitrary image region conditioned on its surroundings. In order to succeed at this task, context encoders need to both… (More)

- Deepak Pathak, Philipp Krähenbühl, Trevor Darrell
- 2015 IEEE International Conference on Computer…
- 2015

We present an approach to learn a dense pixel-wise labeling from image-level tags. Each image-level tag imposes constraints on the output labeling of a Convolutional Neural Network (CNN) classifier. We propose Constrained CNN (CCNN), a method which uses a novel loss function to optimize for any set of linear constraints on the output space (i.e. predicted… (More)

- Jeff Donahue, Philipp Krähenbühl, Trevor Darrell
- ArXiv
- 2016

The ability of the Generative Adversarial Networks (GANs) framework to learn generative models mapping from simple latent distributions to arbitrarily complex data distributions has been demonstrated empirically, with compelling results showing generators learn to “linearize semantics” in the latent space of such models. Intuitively, such latent spaces may… (More)

- Philipp Krähenbühl, Vladlen Koltun
- ICML
- 2013

Dense random fields are models in which all pairs of variables are directly connected by pairwise potentials. It has recently been shown that mean field inference in dense random fields can be performed efficiently and that these models enable significant accuracy gains in computer vision applications. However, parameter estimation for dense random fields… (More)

- Adam Szalkowski, Christian Ledergerber, Philipp Krähenbühl, Christophe Dessimoz
- BMC Research Notes
- 2008

We present swps3, a vectorized implementation of the Smith-Waterman local alignment algorithm optimized for both the Cell/BE and ×86 architectures. The paper describes swps3 and compares its performances with several other implementations. Our benchmarking results show that swps3 is currently the fastest implementation of a vectorized Smith-Waterman on the… (More)

Realistic image manipulation is challenging because it requires modifying the image appearance in a user-controlled way, while preserving the realism of the result. Unless the user has considerable artistic skill, it is easy to “fall off” the manifold of natural images while editing. In this paper, we propose to learn the natural image manifold directly… (More)

- Philipp Krähenbühl, Vladlen Koltun
- 2015 IEEE Conference on Computer Vision and…
- 2015

We present an approach for highly accurate bottom-up object segmentation. Given an image, the approach rapidly generates a set of regions that delineate candidate objects in the image. The key idea is to train an ensemble of figure-ground segmentation models. The ensemble is trained jointly, enabling individual models to specialize and complement each… (More)