… In this paper, we propose a novel deep active learning approach for object detection. Our
approach relies on mixture density networks that estimate a probabilistic distribution for each …

… We aim to address these limitations by taking a probabilistic view. Contributions: We propose
a formulation for learning to predict the conditional probability density p(y|x) of the target …

… We introduce Probabilistic Object Detection, the task of detecting objects in images and …
assessing such probabilistic object detections, we present the new Probability-based Detection …

… with coherent representations. Furthermore, we would like to learn representations that not
… supervised framework that ties representation learning with exploration through prototypical …

… of discrete visual word representations for self-supervised learning in the image domain. (2)
In this context, we propose a novel method for self-supervised representation learning (Fig. 1…

… Probabilistic Cross-Modal Embedding (PCME). We argue that probabilistic mapping is an
effective representation tool that does not require an explicit many-to-many representation as …

… deep learning, and then systematically survey existing methods and evaluation metrics …
probabilistic object detection. Next, we present a strict comparative study for probabilistic object …

… visual classification. We do not explore alternative settings such as supervised contrastive
learning [31], contrastive learning in non-vision … burden for representation learning such as …

… There are two main reasons we adopt a probabilistic approach. First, it is the optimal
approach to decision making under uncertainty, as we explain in Section 5.1. Second, …

… virtual images and real data (Sun & Saenko, 2014). Our goal is therefore to learn visual
representations … We address the challenging setting of robust visual representation learning from …