Related papers: GLENet: Boosting 3D Object Detectors with Generati…
Monocular 3D object detection plays a crucial role in autonomous driving. However, existing monocular 3D detection algorithms depend on 3D labels derived from LiDAR measurements, which are costly to acquire for new datasets and challenging…
Rotation augmentations generally improve a model's invariance/equivariance to rotation - except in object detection. In object detection the shape is not known, therefore rotation creates a label ambiguity. We show that the de-facto method…
Existing LiDAR-based 3D object detectors typically rely on manually annotated labels for training to achieve good performance. However, obtaining high-quality 3D labels is time-consuming and labor-intensive. To address this issue, recent…
Deploying 3D detectors in unfamiliar domains has been demonstrated to result in a significant 70-90% drop in detection rate due to variations in lidar, geography, or weather from their training dataset. This domain gap leads to missing…
We propose a novel object localization methodology with the purpose of boosting the localization accuracy of state-of-the-art object detection systems. Our model, given a search region, aims at returning the bounding box of an object of…
Deep neural networks (DNNs) are powerful tools in computer vision tasks. However, in many realistic scenarios label noise is prevalent in the training images, and overfitting to these noisy labels can significantly harm the generalization…
Reliable uncertainty estimation is crucial for perception systems in safe autonomous driving. Recently, many methods have been proposed to model uncertainties in deep learning based object detectors. However, the estimated probabilities are…
Combining multiple object detection datasets offers a path to improved generalisation but is hindered by inconsistencies in class semantics and bounding box annotations. Some methods to address this assume shared label taxonomies and…
In this paper, we propose the first framework (UCNet) to employ uncertainty for RGB-D saliency detection by learning from the data labeling process. Existing RGB-D saliency detection methods treat the saliency detection task as a point…
Object detection has been applied in a wide variety of real world scenarios, so detection algorithms must provide confidence in the results to ensure that appropriate decisions can be made based on their results. Accordingly, several…
Accurate perception is critical for vehicle safety, with LiDAR as a key enabler in autonomous driving. To ensure robust performance across environments, sensor types, and weather conditions without costly re-annotation, domain…
Multi-modal 3D object detection has received growing attention as the information from different sensors like LiDAR and cameras are complementary. Most fusion methods for 3D detection rely on an accurate alignment and calibration between 3D…
Despite powering sensitive systems like autonomous vehicles, object detection remains fairly brittle in part due to annotation errors that plague most real-world training datasets. We propose ObjectLab, a straightforward algorithm to detect…
Detecting 3D objects from a single RGB image is intrinsically ambiguous, thus requiring appropriate prior knowledge and intermediate representations as constraints to reduce the uncertainties and improve the consistencies between the 2D…
The success of modern deep learning algorithms for image segmentation heavily depends on the availability of large datasets with clean pixel-level annotations (masks), where the objects of interest are accurately delineated. Lack of time…
We present a robust real-time LiDAR 3D object detector that leverages heteroscedastic aleatoric uncertainties to significantly improve its detection performance. A multi-loss function is designed to incorporate uncertainty estimations…
This paper focuses on camouflaged object detection (COD), which is a task to detect objects hidden in the background. Most of the current COD models aim to highlight the target object directly while outputting ambiguous camouflaged…
The study of model bias and variance with respect to decision boundaries is critically important in supervised classification. There is generally a tradeoff between the two, as fine-tuning of the decision boundary of a classification model…
Uncertainty quantification is one of the most crucial tasks to obtain trustworthy and reliable machine learning models for decision making. However, most research in this domain has only focused on problems with small label spaces and…
In many safety-critical applications such as autonomous driving and surgical robots, it is desirable to obtain prediction uncertainties from object detection modules to help support safe decision-making. Specifically, such modules need to…