53 citations · 73 across the 10 of their papers we have counts for
12 papers
Open-Set Recognition in the Age of Vision-Language Models
Dimity Miller, Niko Sünderhauf, Alex Kenna +1
Are vision-language models (VLMs) for open-vocabulary perception inherently open-set models because they are trained on internet-scale datasets? We answer this question with a clea…
Addressing the Challenges of Open-World Object Detection
David Pershouse, Feras Dayoub, Dimity Miller +1
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 lea…
Uncertainty-Aware Lidar Place Recognition in Novel Environments
Keita Mason, Joshua Knights, Milad Ramezani +2
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…
Density-aware NeRF Ensembles: Quantifying Predictive Uncertainty in Neural Radiance Fields
Niko Sünderhauf, Jad Abou-Chakra, Dimity Miller
We show that ensembling effectively quantifies model uncertainty in Neural Radiance Fields (NeRFs) if a density-aware epistemic uncertainty term is considered. The naive ensembles…
SAFE: Sensitivity-Aware Features for Out-of-Distribution Object Detection
Samuel Wilson, Tobias Fischer, Feras Dayoub +2
We address the problem of out-of-distribution (OOD) detection for the task of object detection. We show that residual convolutional layers with batch normalisation produce Sensitiv…
Never mind the metrics -- what about the uncertainty? Visualising confusion matrix metric distributions
David Lovell, Dimity Miller, Jaiden Capra +1
There are strong incentives to build models that demonstrate outstanding predictive performance on various datasets and benchmarks. We believe these incentives risk a narrow focus…
What's in the Black Box? The False Negative Mechanisms Inside Object Detectors
Dimity Miller, Peyman Moghadam, Mark Cox +2
In object detection, false negatives arise when a detector fails to detect a target object. To understand why object detectors produce false negatives, we identify five 'false nega…
Uncertainty for Identifying Open-Set Errors in Visual Object Detection
Dimity Miller, Niko Sünderhauf, Michael Milford +1
Deployed into an open world, object detectors are prone to open-set errors, false positive detections of object classes not present in the training dataset. We propose GMM-Det, a r…
Class Anchor Clustering: a Loss for Distance-based Open Set Recognition
Dimity Miller, Niko Sünderhauf, Michael Milford +1
In open set recognition, deep neural networks encounter object classes that were unknown during training. Existing open set classifiers distinguish between known and unknown classe…
Probabilistic Object Detection: Definition and Evaluation
David Hall, Feras Dayoub, John Skinner +6
We introduce Probabilistic Object Detection, the task of detecting objects in images and accurately quantifying the spatial and semantic uncertainties of the detections. Given the…
Evaluating Merging Strategies for Sampling-based Uncertainty Techniques in Object Detection
Dimity Miller, Feras Dayoub, Michael Milford +1
There has been a recent emergence of sampling-based techniques for estimating epistemic uncertainty in deep neural networks. While these methods can be applied to classification or…
Dropout Sampling for Robust Object Detection in Open-Set Conditions
Dimity Miller, Lachlan Nicholson, Feras Dayoub +1
Dropout Variational Inference, or Dropout Sampling, has been recently proposed as an approximation technique for Bayesian Deep Learning and evaluated for image classification and r…