Search Results for author:
Found 8 papers, 6 papers with code
LaFAM: Unsupervised Feature Attribution with Label-free Activation Maps
Convolutional Neural Networks (CNNs) are known for their ability to learn hierarchical structures, naturally developing detectors for objects, and semantic concepts within their deeper layers.
Cost-Sensitive Uncertainty-Based Failure Recognition for Object Detection
Therefore, a process that mitigates false detections is crucial for both safety and accuracy.
Overcoming the Limitations of Localization Uncertainty: Efficient & Exact Non-Linear Post-Processing and Calibration
We overcome these limitations by: (1) implementing loss attenuation in EfficientDet, and proposing two deterministic methods for the exact and fast propagation of the output distribution, (2) demonstrating on the KITTI and BDD100K datasets that the predicted uncertainty is miscalibrated, and adapting two calibration methods to the localization task, and (3) investigating the correlation between aleatoric uncertainty and task-relevant error sources.
Adaptive Stochastic Optimisation of Nonconvex Composite Objectives
In this paper, we propose and analyse a family of generalised stochastic composite mirror descent algorithms.
Adaptive Zeroth-Order Optimisation of Nonconvex Composite Objectives
In this paper, we propose and analyze algorithms for zeroth-order optimization of non-convex composite objectives, focusing on reducing the complexity dependence on dimensionality.
Optimistic Optimisation of Composite Objective with Exponentiated Update
Furthermore, the algorithms have efficient implementations for popular composite objectives and constraints and can be converted to stochastic optimisation algorithms with the optimal accelerated rate for smooth objectives.
Forecasting Daily Primary Three-Hour Net Load Ramps in the CAISO System
The deepening penetration of variable energy resources creates unprecedented challenges for system operators (SOs).
GerNED: A German Corpus for Named Entity Disambiguation
Determining the real-world referents for name mentions of persons, organizations and other named entities in texts has become an important task in many information retrieval scenarios and is referred to as Named Entity Disambiguation (NED).
