Related papers: Global Proxy-based Hard Mining for Visual Place Re…
We introduce a weakly supervised method for representation learning based on aligning temporal sequences (e.g., videos) of the same process (e.g., human action). The main idea is to use the global temporal ordering of latent correspondences…
Learning suitable Whole slide images (WSIs) representations for efficient retrieval systems is a non-trivial task. The WSI embeddings obtained from current methods are in Euclidean space not ideal for efficient WSI retrieval. Furthermore,…
Recent studies show that, both explicit deep feature matching as well as large-scale and diverse training data can significantly improve the generalization of person re-identification. However, the efficiency of learning deep matchers on…
Contrastive Learning has recently achieved state-of-the-art performance in a wide range of tasks. Many contrastive learning approaches use mined hard negatives to make batches more informative during training but these approaches are…
Traditional supervised learning with deep neural networks requires a tremendous amount of labelled data to converge to a good solution. For 3D medical images, it is often impractical to build a large homogeneous annotated dataset for a…
This paper adapts a general dataset representation technique to produce robust Visual Place Recognition (VPR) descriptors, crucial to enable real-world mobile robot localisation. Two parallel lines of work on VPR have shown, on one side,…
Visual Place Recognition is an essential component of systems for camera localization and loop closure detection, and it has attracted widespread interest in multiple domains such as computer vision, robotics and AR/VR. In this work, we…
We consider learning based methods for visual localization that do not require the construction of explicit maps in the form of point clouds or voxels. The goal is to learn an implicit representation of the environment at a higher, more…
In image retrieval, deep local features learned in a data-driven manner have been demonstrated effective to improve retrieval performance. To realize efficient retrieval on large image database, some approaches quantize deep local features…
In visual place recognition (VPR), filtering and sequence-based matching approaches can improve performance by integrating temporal information across image sequences, especially in challenging conditions. While these methods are commonly…
Visual Place Recognition (VPR) aims to estimate the location of an image by treating it as a retrieval problem. VPR uses a database of geo-tagged images and leverages deep neural networks to extract a global representation, called…
Deep metric learning maps visually similar images onto nearby locations and visually dissimilar images apart from each other in an embedding manifold. The learning process is mainly based on the supplied image negative and positive training…
Transformers with powerful global relation modeling abilities have been introduced to fundamental computer vision tasks recently. As a typical example, the Vision Transformer (ViT) directly applies a pure transformer architecture on image…
LiDAR-based place recognition serves as a crucial enabler for long-term autonomy in robotics and autonomous driving systems. Yet, prevailing methodologies relying on handcrafted feature extraction face dual challenges: (1) Inconsistent…
Diffusion has shown great success in improving accuracy of unsupervised image retrieval systems by utilizing high-order structures of image manifold. However, existing diffusion methods suffer from three major limitations: 1) they usually…
Most of the existing semantic segmentation approaches with image-level class labels as supervision, highly rely on the initial class activation map (CAM) generated from the standard classification network. In this paper, a novel…
Despite the rapid advancement in the field of image recognition, the processing of high-resolution imagery remains a computational challenge. However, this processing is pivotal for extracting detailed object insights in areas ranging from…
Recently, deep learning based 3D face reconstruction methods have shown promising results in both quality and efficiency.However, training deep neural networks typically requires a large volume of data, whereas face images with ground-truth…
Multimodal models often experience a significant performance drop when one or more modalities are missing during inference. To address this challenge, we propose a simple yet effective approach that enhances robustness to missing modalities…
Learning discriminative representations is a central goal of supervised deep learning. While cross-entropy (CE) remains the dominant objective for classification, it does not explicitly enforce desirable geometric properties in the…