No abstract

No abstract

The state of the art in semantic segmentation is steadily increasing in performance, resulting in more precise and reliable segmentations in many different applications. However, progress is limited by the cost of generating labels for training, which sometimes requires hours of manual labor for a single image. Because of this, semi-supervised methods have been applied to this task, with varying degrees of success. A key challenge is that common augmentations used in semi-supervised classification are less effective for semantic segmentation. We propose a novel data augmentation mechanism called ClassMix, which generates augmentations by mixing unlabelled samples, by leveraging on the network's predictions for respecting object boundaries. We evaluate this augmentation technique on two common semi-supervised semantic segmentation benchmarks, showing that it attains state-of-theart results. Lastly, we also provide extensive ablation studies comparing different design decisions and training regimes. Code is available at: https://github.com/WilhelmT/ClassMix.

Evaluating the performance of multi-object tracking (MOT) methods is not straightforward, and existing performance measures fail to consider all the available uncertainty information in the MOT context. This can lead practitioners to select models which produce uncertainty estimates of lower quality, negatively impacting any downstream systems that rely on them. Additionally, most MOT performance measures have hyperparameters, which makes comparisons of different trackers less straightforward. We propose the use of the negative log-likelihood (NLL) of the multi-object posterior given the set of groundtruth objects as a performance measure. This measure takes into account all available uncertainty information in a sound mathematical manner without hyperparameters. We provide efficient algorithms for approximating the computation of the NLL for several common MOT algorithms, show that in some cases it decomposes and approximates the widely-used GOSPA metric, and provide several illustrative examples highlighting the advantages of the NLL in comparison to other MOT performance measures.

Fiber tracking is a technique that, based on a diffusion tensor magnetic resonance imaging dataset, locates the fiber bundles in the human brain. Because it is a computationally expensive process, the interactivity of current fiber tracking tools is limited. We propose a new approach, which we termed real-time interactive fiber tracking, which aims at providing a rich and intuitive environment for the neuroradiologist. In this approach, fiber tracking is executed automatically every time the user acts upon the application. Particularly, when the volume of interest from which fiber trajectories are calculated is moved on the screen, fiber tracking is executed, even while it is being moved. We present our fiber tracking tool, which implements the real-time fiber tracking concept by using the video card's graphics processing units to execute the fiber tracking algorithm. Results show that real-time interactive fiber tracking is feasible on computers equipped with common, low-cost video cards.