By extensive experiments on a wide range of architectures, including the most efficient ones, we demonstrate that delta distillation sets a new state of the art in terms of accuracy vs. efficiency trade-off for semantic segmentation and object detection in videos.
To the best of our knowledge, our proposals are the first solutions that integrate ROI-based capabilities into neural video compression models.
We reformulate standard convolution to be efficiently computed on residual frames: each layer is coupled with a binary gate deciding whether a residual is important to the model prediction,~\eg foreground regions, or it can be safely skipped, e. g. background regions.
Continual Learning has inspired a plethora of approaches and evaluation settings; however, the majority of them overlooks the properties of a practical scenario, where the data stream cannot be shaped as a sequence of tasks and offline training is not viable.
Ranked #12 on Continual Learning on ASC (19 tasks)
Therefore, we additionally introduce a task classifier that predicts the task label of each example, to deal with settings in which a task oracle is not available.
Ranked #3 on Continual Learning on ImageNet-50 (5 tasks)
We present a novel and hierarchical approach for supervised classification of signals spanning over a fixed graph, reflecting shared properties of the dataset.
Novelty detection is commonly referred to as the discrimination of observations that do not conform to a learned model of regularity.
Awareness of the road scene is an essential component for both autonomous vehicles and Advances Driver Assistance Systems and is gaining importance both for the academia and car companies.
We address unsupervised optical flow estimation for ego-centric motion.