Related papers: Long-Term Ensemble Learning of Visual Place Classi…

Visual place recognition is a fundamental capability for the localization of mobile robots. It places image retrieval in the practical context of physical agents operating in a physical world. It is an active field of research and many…

Visual place recognition (VPR) is a fundamental task of computer vision for visual localization. Existing methods are trained using image pairs that either depict the same place or not. Such a binary indication does not consider continuous…

Recently the deep learning has shown its advantage in representation learning and clustering for time series data. Despite the considerable progress, the existing deep time series clustering approaches mostly seek to train the deep neural…

Systems involving human-robot collaboration necessarily require that steps be taken to ensure safety of the participating human. This is usually achievable if accurate, reliable estimates of the human's pose are available. In this paper, we…

Land Cover (LC) mapping using satellite imagery is critical for environmental monitoring and management. Deep Learning (DL), particularly Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs), have revolutionized this field by…

In this paper, we propose a novel unsupervised domain adaptation algorithm based on deep learning for visual object recognition. Specifically, we design a new model called Deep Reconstruction-Classification Network (DRCN), which jointly…

In the last few years, Deep Convolutional Neural Networks (D-CNNs) have shown state-of-the-art (SOTA) performance for Visual Place Recognition (VPR), a pivotal component of long-term intelligent robotic vision (vision-aware localization and…

Computer vision tasks are traditionally defined and evaluated using semantic categories. However, it is known to the field that semantic classes do not necessarily correspond to a unique visual class (e.g. inside and outside of a car).…

Recent years have witnessed a growing interest in using machine learning to predict and identify phase transitions in various systems. Here we adopt convolutional neural networks (CNNs) to study the phase transitions of Vicsek model,…

This paper studies the problem of semi-supervised video object segmentation(VOS). Multiple works have shown that memory-based approaches can be effective for video object segmentation. They are mostly based on pixel-level matching, both…

Multi-label classification (MLC) is an important class of machine learning problems that come with a wide spectrum of applications, each demanding a possibly different evaluation criterion. When solving the MLC problems, we generally expect…

Making accurate motion prediction of surrounding agents such as pedestrians and vehicles is a critical task when robots are trying to perform autonomous navigation tasks. Recent research on multi-modal trajectory prediction, including…

State-of-the-art rehearsal-free continual learning methods exploit the peculiarities of Vision Transformers to learn task-specific prompts, drastically reducing catastrophic forgetting. However, there is a tradeoff between the number of…

Our work focuses on training RL agents on multiple visually diverse environments to improve observational generalization performance. In prior methods, policy and value networks are separately optimized using a disjoint network architecture…

Deep Reinforcement Learning has enabled the learning of policies for complex tasks in partially observable environments, without explicitly learning the underlying model of the tasks. While such model-free methods achieve considerable…

Visual place recognition (VPR) is a robot's ability to determine whether a place was visited before using visual data. While conventional hand-crafted methods for VPR fail under extreme environmental appearance changes, those based on…

Transfer learning is a machine learning technique that uses previously acquired knowledge from a source domain to enhance learning in a target domain by reusing learned weights. This technique is ubiquitous because of its great advantages…

Performing data augmentation for learning deep neural networks is known to be important for training visual recognition systems. By artificially increasing the number of training examples, it helps reducing overfitting and improves…

Continual learning aims to enable machine learning models to continually learn from a shifting data distribution without forgetting what has already been learned. Such shifting distributions can be broken into disjoint subsets of related…

Multitask learning is a common approach in machine learning, which allows to train multiple objectives with a shared architecture. It has been shown that by training multiple tasks together inference time and compute resources can be saved,…