Publicaties
Gekozen filters:
Gekozen filters:
Processor Architecture Optimization for Spatially Dynamic Neural Networks KU Leuven
Spatially dynamic neural networks adjust network execution based on the input data, saving computations by skipping non-important image regions. Yet, GPU implementations fail to achieve speedups from these spatially dynamic execution patterns for most neural network architectures. This paper investigates hardware constraints preventing such speedup and proposes and compares novel processor architectures and dataflows enabling latency ...
More classifiers, less forgetting:A generic multi-classifier paradigm for incremental learning KU Leuven
HPatches: A benchmark and evaluation of handcrafted and learned local descriptors KU Leuven
In this paper, a novel benchmark is introduced for evaluating local image descriptors. We demonstrate limitations of the commonly used datasets and evaluation protocols, that lead to ambiguities and contradictory results in the literature. Furthermore, these benchmarks are nearly saturated due to the recent improvements in local descriptors obtained by learning from large annotated datasets. To address these issues, we introduce a new large ...
A deep multi-modal explanation model for zero-shot learning KU Leuven
Zero-shot learning (ZSL) has attracted significant attention due to its capabilities of classifying new images from unseen classes. To perform the classification task for ZSL, learning visual and semantic embeddings has been the main research approach in existing literature. At the same time, generating complementary explanations to justify the classification decision has remained largely unexplored. In this paper, we propose to address a new ...