262 citations · 339 across the 7 of their papers we have counts for
8 papers
Multi-headed Neural Ensemble Search
Ashwin Raaghav Narayanan, Arber Zela, Tonmoy Saikia +2
Ensembles of CNN models trained with different seeds (also known as Deep Ensembles) are known to achieve superior performance over a single copy of the CNN. Neural Ensemble Search…
Improving robustness against common corruptions with frequency biased models
Tonmoy Saikia, Cordelia Schmid, Thomas Brox
CNNs perform remarkably well when the training and test distributions are i.i.d, but unseen image corruptions can cause a surprisingly large drop in performance. In various real sc…
Towards Understanding Adversarial Robustness of Optical Flow Networks
Simon Schrodi, Tonmoy Saikia, Thomas Brox
Recent work demonstrated the lack of robustness of optical flow networks to physical patch-based adversarial attacks. The possibility to physically attack a basic component of auto…
Optimized Generic Feature Learning for Few-shot Classification across Domains
Tonmoy Saikia, Thomas Brox, Cordelia Schmid
To learn models or features that generalize across tasks and domains is one of the grand goals of machine learning. In this paper, we propose to use cross-domain, cross-task data a…
Understanding and Robustifying Differentiable Architecture Search
Arber Zela, Thomas Elsken, Tonmoy Saikia +3
Differentiable Architecture Search (DARTS) has attracted a lot of attention due to its simplicity and small search costs achieved by a continuous relaxation and an approximation of…
AutoDispNet: Improving Disparity Estimation With AutoML
Tonmoy Saikia, Yassine Marrakchi, Arber Zela +2
Much research work in computer vision is being spent on optimizing existing network architectures to obtain a few more percentage points on benchmarks. Recent AutoML approaches pro…
Occlusions, Motion and Depth Boundaries with a Generic Network for Disparity, Optical Flow or Scene Flow Estimation
Eddy Ilg, Tonmoy Saikia, Margret Keuper +1
Occlusions play an important role in disparity and optical flow estimation, since matching costs are not available in occluded areas and occlusions indicate depth or motion boundar…
FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks
Eddy Ilg, Nikolaus Mayer, Tonmoy Saikia +3
The FlowNet demonstrated that optical flow estimation can be cast as a learning problem. However, the state of the art with regard to the quality of the flow has still been defined…