Related papers: Weakly supervised training of deep convolutional n…

Recently, deep learning has experienced rapid expansion, contributing significantly to the progress of supervised learning methodologies. However, acquiring labeled data in real-world settings can be costly, labor-intensive, and sometimes…

In this work, we introduce a Denser Feature Network (DenserNet) for visual localization. Our work provides three principal contributions. First, we develop a convolutional neural network (CNN) architecture which aggregates feature maps at…

Accurate Named Entity Recognition (NER) is crucial for various information retrieval tasks in industry. However, despite significant progress in traditional NER methods, the extraction of Complex Named Entities remains a relatively…

Scene Parsing is a crucial step to enable autonomous systems to understand and interact with their surroundings. Supervised deep learning methods have made great progress in solving scene parsing problems, however, come at the cost of…

Visual place recognition techniques based on deep learning, which have imposed themselves as the state-of-the-art in recent years, do not generalize well to environments visually different from the training set. Thus, to achieve top…

Most existing approaches to training object detectors rely on fully supervised learning, which requires the tedious manual annotation of object location in a training set. Recently there has been an increasing interest in developing weakly…

Semantic segmentation tasks based on weakly supervised condition have been put forward to achieve a lightweight labeling process. For simple images that only include a few categories, researches based on image-level annotations have…

Understanding human motion is crucial for accurate pedestrian trajectory prediction. Conventional methods typically rely on supervised learning, where ground-truth labels are directly optimized against predicted trajectories. This amplifies…

A significant issue in training deep neural networks to solve supervised learning tasks is the need for large numbers of labelled datapoints. The goal of semi-supervised learning is to leverage ubiquitous unlabelled data, together with…

3D semantic scene understanding tasks have achieved great success with the emergence of deep learning, but often require a huge amount of manually annotated training data. To alleviate the annotation cost, we propose the first…

Deep Learning (DL) has brought significant advances to robotics vision tasks. However, most existing DL methods have a major shortcoming, they rely on a static inference paradigm inherent in traditional computer vision pipelines. On the…

Pedestrian Attribute Recognition (PAR) focuses on identifying various attributes in pedestrian images, with key applications in person retrieval, suspect re-identification, and soft biometrics. However, Deep Neural Networks (DNNs) for PAR…

Fine-grained image classification has witnessed significant advancements with the advent of deep learning and computer vision technologies. However, the scarcity of detailed annotations remains a major challenge, especially in scenarios…

3D object detection is essential for autonomous driving and robotic perception, yet its reliance on large-scale manually annotated data limits scalability and adaptability. To reduce annotation dependency, unsupervised and…

Progress has been achieved recently in object detection given advancements in deep learning. Nevertheless, such tools typically require a large amount of training data and significant manual effort to label objects. This limits their…

Feature matching and finding correspondences between endoscopic images is a key step in many clinical applications such as patient follow-up and generation of panoramic image from clinical sequences for fast anomalies localization.…

Training convolutional networks (CNN's) that fit on a single GPU with minibatch stochastic gradient descent has become effective in practice. However, there is still no effective method for training large CNN's that do not fit in the memory…

Providing ground truth supervision to train visual models has been a bottleneck over the years, exacerbated by domain shifts which degenerate the performance of such models. This was the case when visual tasks relied on handcrafted features…

This work tackles Weakly Supervised Anomaly detection, in which a predictor is allowed to learn not only from normal examples but also from a few labeled anomalies made available during training. In particular, we deal with the localization…

This paper introduces a new architecture for human pose estimation using a multi- layer convolutional network architecture and a modified learning technique that learns low-level features and higher-level weak spatial models. Unconstrained…