One of the main challenges in machine vision relates to the problem of obtaining robust
representation of visual features that remain unaffected by geometric transformations. This …

High-resolution representations are essential for position-sensitive vision problems, such as
human pose estimation, semantic segmentation, and object detection. Existing state-of-the …

In this paper, we are interested in the human pose estimation problem with a focus on
learning reliable high-resolution representations. Most existing methods recover high …

In this paper we challenge the common assumption that convolutional layers in modern
CNNs are translation invariant. We show that CNNs can and will exploit the absolute spatial …

Abstract Convolutional Neural Networks (CNNs) are commonly assumed to be invariant to
small image transformations: either because of the convolutional architecture or because …

High-quality HDRIs (High Dynamic Range Images), typically HDR panoramas, are one of
the most popular ways to create photorealistic lighting and 360-degree reflections of 3D …

Recently, contrastive learning has risen to be a promising approach for large-scale self-
supervised learning. However, theoretical understanding of how it works is still unclear. In …

Modern neural networks use building blocks such as convolutions that are equivariant to
arbitrary 2 D translations. However, these vanilla blocks are not equivariant to arbitrary 3 D …

In this paper, we consider the problem of pedestrian detection in natural scenes. Intuitively,
instances of pedestrians with different spatial scales may exhibit dramatically different …

Recently, non-recurrent architectures (convolutional, self-attentional) have outperformed
RNNs in neural machine translation. CNNs and self-attentional networks can connect distant …