• Publications
  • Influence
Learning to Adapt Structured Output Space for Semantic Segmentation
TLDR
A multi-level adversarial network is constructed to effectively perform output space domain adaptation at different feature levels and it is shown that the proposed method performs favorably against the state-of-the-art methods in terms of accuracy and visual quality.
Fast and accurate image upscaling with super-resolution forests
TLDR
This paper shows the close relation of previous work on single image super-resolution to locally linear regression and demonstrates how random forests nicely fit into this framework, and proposes to directly map from low to high-resolution patches using random forests.
Domain Adaptation for Structured Output via Discriminative Patch Representations
TLDR
A domain adaptation method to adapt the source data to the unlabeled target domain by discovering multiple modes of patch-wise output distribution through the construction of a clustered space and using an adversarial learning scheme to push the feature representations of target patches in the clustered space closer to the distributions of source patches.
Alternating Decision Forests
TLDR
This paper introduces a novel classification method termed Alternating Decision Forests (ADFs), which formulates the training of Random Forests explicitly as a global loss minimization problem, and derives the new classifier and gives a discussion and evaluation on standard machine learning data sets.
You Should Use Regression to Detect Cells
TLDR
It is shown that cells can be detected reliably in images by predicting a monotonous function of the distance to the center of the closest cell, which results in a very simple method, which is easy to implement.
Learning To Simulate
TLDR
This work proposes a reinforcement learning-based method for automatically adjusting the parameters of any (non-differentiable) simulator, thereby controlling the distribution of synthesized data in order to maximize the accuracy of a model trained on that data.
Alternating Regression Forests for Object Detection and Pose Estimation
TLDR
Alternative Regression Forests are presented, a novel regression algorithm that learns a Random Forest by optimizing a global loss function over all trees and outperform the Random Forest baselines in both tasks, illustrating the importance of optimizing a common loss function for all trees.
Deep Network Flow for Multi-object Tracking
TLDR
It is demonstrated that it is possible to learn features for network-flow-based data association via backpropagation, by expressing the optimum of a smoothed network flow problem as a differentiable function of the pairwise association costs.
Domain Adaptive Semantic Segmentation Using Weak Labels
TLDR
A novel framework for domain adaptation in semantic segmentation with image-level weak labels to enable the interplay between feature alignment and pseudo-labeling, improving both in the process of domain adaptation and with respect to the existing state-of-the-arts in UDA.
Shuffle and Attend: Video Domain Adaptation
TLDR
This work proposes an attention mechanism which focuses on more discriminative clips and directly optimizes for video-level alignment and proposes to use the clip order prediction as an auxiliary task, which encourages learning of representations which focus on the humans and objects involved in the actions.
...
...