Search Results for author:
Found 13 papers, 9 papers with code
Unlearning Backdoor Attacks through Gradient-Based Model Pruning
In the era of increasing concerns over cybersecurity threats, defending against backdoor attacks is paramount in ensuring the integrity and reliability of machine learning models.
Open-Set Recognition in the Age of Vision-Language Models
Are vision-language models (VLMs) for open-vocabulary perception inherently open-set models because they are trained on internet-scale datasets?
Addressing the Challenges of Open-World Object Detection
We address the challenging problem of open world object detection (OWOD), where object detectors must identify objects from known classes while also identifying and continually learning to detect novel objects.
Uncertainty-Aware Lidar Place Recognition in Novel Environments
State-of-the-art lidar place recognition models exhibit unreliable performance when tested on environments different from their training dataset, which limits their use in complex and evolving environments.
Density-aware NeRF Ensembles: Quantifying Predictive Uncertainty in Neural Radiance Fields
We show that ensembling effectively quantifies model uncertainty in Neural Radiance Fields (NeRFs) if a density-aware epistemic uncertainty term is considered.
SAFE: Sensitivity-Aware Features for Out-of-Distribution Object Detection
We address the problem of out-of-distribution (OOD) detection for the task of object detection.
Never mind the metrics -- what about the uncertainty? Visualising confusion matrix metric distributions
There are strong incentives to build models that demonstrate outstanding predictive performance on various datasets and benchmarks.
What's in the Black Box? The False Negative Mechanisms Inside Object Detectors
Using this framework, we investigate why Faster R-CNN and RetinaNet fail to detect objects in benchmark vision datasets and robotics datasets.
Uncertainty for Identifying Open-Set Errors in Visual Object Detection
We also introduce a methodology for converting existing object detection datasets into specific open-set datasets to evaluate open-set performance in object detection.
Class Anchor Clustering: a Loss for Distance-based Open Set Recognition
We also show that our anchored class centres achieve higher open set performance than learnt class centres, particularly on object-based datasets and large numbers of training classes.
Probabilistic Object Detection: Definition and Evaluation
We introduce Probabilistic Object Detection, the task of detecting objects in images and accurately quantifying the spatial and semantic uncertainties of the detections.
Evaluating Merging Strategies for Sampling-based Uncertainty Techniques in Object Detection
There has been a recent emergence of sampling-based techniques for estimating epistemic uncertainty in deep neural networks.
Dropout Sampling for Robust Object Detection in Open-Set Conditions
Dropout Variational Inference, or Dropout Sampling, has been recently proposed as an approximation technique for Bayesian Deep Learning and evaluated for image classification and regression tasks.
