Related papers: Binary Neural Networks for Memory-Efficient and Ef…

Convolutional neural networks (CNNs) are one of the most successful computer vision systems to solve object recognition. Furthermore, CNNs have major applications in understanding the nature of visual representations in the human brain. Yet…

Visual Place Recognition (VPR) systems often have imperfect performance, affecting the `integrity' of position estimates and subsequent robot navigation decisions. Previously, SVM classifiers have been used to monitor VPR integrity. This…

Surface inspection systems are an important application domain for computer vision, as they are used for defect detection and classification in the manufacturing industry. Existing systems use hand-crafted features which require extensive…

Significant advances have been made recently in Visual Place Recognition (VPR), feature correspondence, and localization due to the proliferation of deep-learning-based methods. However, existing approaches tend to address, partially or…

Geo-localization from a single image at planet scale (essentially an advanced or extreme version of the kidnapped robot problem) is a fundamental and challenging task in applications such as navigation, autonomous driving and disaster…

CNNs have excelled at performing place recognition over time, particularly when the neural network is optimized for localization in the current environmental conditions. In this paper we investigate the concept of feature map filtering,…

Most Vision-and-Language Navigation (VLN) algorithms are prone to making inaccurate decisions due to their lack of visual common sense and limited reasoning capabilities. To address this issue, we propose a Hierarchical Spatial Proximity…

Vision-transformers (ViTs) and large-scale convolution-neural-networks (CNNs) have reshaped computer vision through pretrained feature representations that enable strong transfer learning for diverse tasks. However, their efficiency as…

Visual Place Recognition (VPR) refers to the process of using computer vision to recognize the position of the current query image. Due to the significant changes in appearance caused by season, lighting, and time spans between query images…

Visual Place Recognition (VPR) enables robust localization through image retrieval based on learned descriptors. However, drastic appearance variations of images at the same place caused by viewpoint changes can lead to inconsistent…

We present a simple and effective architecture for fine-grained visual recognition called Bilinear Convolutional Neural Networks (B-CNNs). These networks represent an image as a pooled outer product of features derived from two CNNs and…

We address multi-reference visual place recognition (VPR), where reference sets captured under varying conditions are used to improve localisation performance. While deep learning with large-scale training improves robustness, increasing…

We propose methods to train convolutional neural networks (CNNs) with both binarized weights and activations, leading to quantized models that are specifically friendly to mobile devices with limited power capacity and computation…

Convolutional neural networks have achieved astonishing results in different application areas. Various methods that allow us to use these models on mobile and embedded devices have been proposed. Especially binary neural networks are a…

Missions to small celestial bodies rely heavily on optical feature tracking for characterization of and relative navigation around the target body. While techniques for feature tracking based on deep learning are a promising alternative to…

Our goal is to design architectures that retain the groundbreaking performance of Convolutional Neural Networks (CNNs) for landmark localization and at the same time are lightweight, compact and suitable for applications with limited…

Visual Place Recognition (VPR) estimates the location of query images by matching them with images in a reference database. Conventional methods generally adopt aggregated CNN features for global retrieval and RANSAC-based geometric…

Ensuring accurate localization of robots in environments without GPS capability is a challenging task. Visual Place Recognition (VPR) techniques can potentially achieve this goal, but existing RGB-based methods are sensitive to changes in…

Existing Binary Neural Networks (BNNs) mainly operate on local convolutions with binarization function. However, such simple bit operations lack the ability of modeling contextual dependencies, which is critical for learning discriminative…

Visual place recognition is a challenging task for autonomous driving and robotics, which is usually considered as an image retrieval problem. A commonly used two-stage strategy involves global retrieval followed by re-ranking using…