Stochastic-YOLO: Efficient Probabilistic Object Detection under Dataset Shifts

09/07/2020
by   Tiago Azevedo, et al.
13

In image classification tasks, the evaluation of models' robustness to increased dataset shifts with a probabilistic framework is very well studied. However, Object Detection (OD) tasks pose other challenges for uncertainty estimation and evaluation. For example, one needs to evaluate both the quality of the label uncertainty (i.e., what?) and spatial uncertainty (i.e., where?) for a given bounding box, but that evaluation cannot be performed with more traditional average precision metrics (e.g., mAP). In this paper, we adapt the well-established YOLOv3 architecture to generate uncertainty estimations by introducing stochasticity in the form of Monte Carlo Dropout (MC-Drop), and evaluate it across different levels of dataset shift. We call this novel architecture Stochastic-YOLO, and provide an efficient implementation to effectively reduce the burden of the MC-Drop sampling mechanism at inference time. Finally, we provide some sensitivity analyses, while arguing that Stochastic-YOLO is a sound approach that improves different components of uncertainty estimations, in particular spatial uncertainties.

READ FULL TEXT

page 3

page 8

research
08/08/2021

Monte Carlo DropBlock for Modelling Uncertainty in Object Detection

With the advancements made in deep learning, computer vision problems li...
research
03/19/2019

The Probabilistic Object Detection Challenge

We introduce a new challenge for computer and robotic vision, the first ...
research
03/07/2020

Inferring Spatial Uncertainty in Object Detection

The availability of real-world datasets is the prerequisite to develop o...
research
12/23/2020

Exploring Instance-Level Uncertainty for Medical Detection

The ability of deep learning to predict with uncertainty is recognized a...
research
12/16/2021

Benchmarking Uncertainty Qualification on Biosignal Classification Tasks under Dataset Shift

A biosignal is a signal that can be continuously measured from human bod...
research
11/27/2018

Probability-based Detection Quality (PDQ): A Probabilistic Approach to Detection Evaluation

We propose a new visual object detector evaluation measure which not onl...
research
09/17/2018

Evaluating Merging Strategies for Sampling-based Uncertainty Techniques in Object Detection

There has been a recent emergence of sampling-based techniques for estim...

Please sign up or login with your details

Forgot password? Click here to reset