Research Area
Year Published

99 Results

September 9, 2018

Memory Aware Synapses: Learning what (not) to forget

European Conference on Computer Vision (ECCV)

Humans can learn in a continuous manner. Old rarely utilized knowledge can be overwritten by new incoming information while important, frequently used knowledge is prevented from being erased. In artificial learning systems, lifelong learning so far has focused mainly on accumulating knowledge over tasks and overcoming catastrophic forgetting. In this paper, we argue that, given the limited model capacity and the unlimited new information to be learned, knowledge has to be preserved or erased selectively.

By: Rahaf Aljundi, Francesca Babiloni, Mohamed Elhoseiny, Marcus Rohrbach, Tinne Tuytelaars
September 9, 2018

Choose Your Neuron: Incorporating Domain Knowledge through Neuron-Importance

European Conference on Computer Vision (ECCV)

Individual neurons in convolutional neural networks supervised for image-level classification tasks have been shown to implicitly learn semantically meaningful concepts ranging from simple textures and shapes to whole or partial objects – forming a “dictionary” of concepts acquired through the learning process. In this work we introduce a simple, efficient zero-shot learning approach based on this observation.

By: Ramprasaath R. Selvaraju, Prithvijit Chattopadhyay, Mohamed Elhoseiny, Tilak Sharma, Dhruv Batra, Devi Parikh, Stefan Lee
September 8, 2018

DeepWrinkles: Accurate and Realistic Clothing Modeling

European Conference on Computer Vision (ECCV)

We present a novel method to generate accurate and realistic clothing deformation from real data capture. Previous methods for realistic cloth modeling mainly rely on intensive computation of physics-based simulation (with numerous heuristic parameters), while models reconstructed from visual observations typically suffer from lack of geometric details.

By: Zorah Lähner, Daniel Cremers, Tony Tung
September 7, 2018

Joint Future Semantic and Instance Segmentation Prediction

ECCV Anticipating Human Behavior Workshop

In this work, we introduce a novel prediction approach that encodes instance and semantic segmentation information in a single representation based on distance maps.

By: Camille Couprie, Pauline Luc, Jakob Verbeek
September 7, 2018

Recycle-GAN: Unsupervised Video Retargeting

European Conference on Computer Vision (ECCV)

We introduce a data-driven approach for unsupervised video retargeting that translates content from one domain to another while preserving the style native to a domain, i.e., if contents of John Oliver’s speech were to be transferred to Stephen Colbert, then the generated content/speech should be in Stephen Colbert’s style.

By: Aayush Bansal, Shugao Ma, Deva Ramanan, Yaser Sheikh
September 7, 2018

Object Level Visual Reasoning in Videos

European Conference on Computer Vision (ECCV)

We propose a model capable of learning to reason about semantically meaningful spatio-temporal interactions in videos.

By: Fabien Baradel, Natalia Neverova, Christian Wolf, Julien Mille, Greg Mori
September 7, 2018

Group Normalization

European Conference on Computer Vision (ECCV)

Batch Normalization (BN) is a milestone technique in the development of deep learning, enabling various networks to train. However, normalizing along the batch dimension introduces problems — BN’s error increases rapidly when the batch size becomes smaller, caused by inaccurate batch statistics estimation. This limits BN’s usage for training larger models and transferring features to computer vision tasks including detection, segmentation, and video, which require small batches constrained by memory consumption. In this paper, we present Group Normalization (GN) as a simple alternative to BN.

By: Yuxin Wu, Kaiming He
September 4, 2018

Mass Displacement Networks

British Machine Vision Convention (BMVC)

Despite the large improvements in performance attained by deep learning in computer vision, one can often further improve results with some additional post-processing that exploits the geometric nature of the underlying task. This commonly involves displacing the posterior distribution of a CNN in a way that makes it more appropriate for the task at hand, e.g. better aligned with local image features, or more compact. In this work we integrate this geometric post-processing within a deep architecture, introducing a differentiable and probabilistically sound counterpart to the common geometric voting technique used for evidence accumulation in vision.

By: Natalia Neverova, Iasonas Kokkinos
September 4, 2018

Self-Supervised Feature Learning for Semantic Segmentation of Overhead Imagery

British Machine Vision Convention (BMVC)

In this work, we study various self-supervised feature learning techniques for semantic segmentation of overhead imageries.

By: Suriya Singh, Anil Batra, Guan Pang, Lorenzo Torresani, Saikat Basu, Manohar Paluri, C.V. Jawahar
September 3, 2018

QuaterNet: A Quaternion-based Recurrent Model for Human Motion

British Machine Vision Convention (BMVC)

Deep learning for predicting or generating 3D human pose sequences is an active research area. Previous work regresses either joint rotations or joint positions. The former strategy is prone to error accumulation along the kinematic chain, as well as discontinuities when using Euler angle or exponential map parameterizations. The latter requires re-projection onto skeleton constraints to avoid bone stretching and invalid configurations. This work addresses both limitations.

By: Dario Pavllo, David Grangier, Michael Auli