Related papers: Global Proxy-based Hard Mining for Visual Place Re…

Visual localization is one of the most important components for robotics and autonomous driving. Recently, inspiring results have been shown with CNN-based methods which provide a direct formulation to end-to-end regress 6-DoF absolute…

With increasing scale in model and dataset size, the training of deep neural networks becomes a massive computational burden. One approach to speed up the training process is Selective Backprop. For this approach, we perform a forward pass…

The success of deep learning in computer vision is rooted in the ability of deep networks to scale up model complexity as demanded by challenging visual tasks. As complexity is increased, so is the need for large amounts of labeled data to…

Deep embedding learning becomes more attractive for discriminative feature learning, but many methods still require hard-class mining, which is computationally complex and performance-sensitive. To this end, we propose Adaptive Large Margin…

Modern deep learning-based 3D pose estimation approaches require plenty of 3D pose annotations. However, existing 3D datasets lack diversity, which limits the performance of current methods and their generalization ability. Although…

Empirical researchers increasingly use upstream machine-learning (ML) methods to construct proxies for latent target variables from complex, unstructured data. A naive plug-in use of such proxies in downstream econometric models, however,…

Despite the growing prevalence of black-box pre-trained models (PTMs) such as prediction API services, there remains a significant challenge in directly applying general models to real-world scenarios due to the data distribution gap.…

While image-text representation learning has become very popular in recent years, existing models tend to lack spatial awareness and have limited direct applicability for dense understanding tasks. For this reason, self-supervised…

For deep ordinal classification, learning a well-structured feature space specific to ordinal classification is helpful to properly capture the ordinal nature among classes. Intuitively, when Euclidean distance metric is used, an ideal…

Contrastive learning is a representational learning paradigm in which a neural network maps data elements to feature vectors. It improves the feature space by forming lots with an anchor and examples that are either positive or negative…

Histopathology whole slide images (WSIs) play a very important role in clinical studies and serve as the gold standard for many cancer diagnoses. However, generating automatic tools for processing WSIs is challenging due to their enormous…

This paper introduces a new method for semi-supervised learning on high dimensional nonlinear manifolds, which includes a phase of unsupervised basis learning and a phase of supervised function learning. The learned bases provide a set of…

Visual relationship detection, as a challenging task used to find and distinguish the interactions between object pairs in one image, has received much attention recently. In this work, we propose a novel visual relationship detection…

Global localization in 3D point clouds is a challenging problem of estimating the pose of vehicles without any prior knowledge. In this paper, a solution to this problem is presented by achieving place recognition and metric pose estimation…

Image based localization is one of the important problems in computer vision due to its wide applicability in robotics, augmented reality, and autonomous systems. There is a rich set of methods described in the literature how to…

X-ray ptychography is a data-intensive imaging technique expected to become ubiquitous at next-generation light sources delivering many-fold increases in coherent flux. The need for real-time feedback under accelerated acquisition rates…

In this work a novel approach for weakly supervised object detection that incorporates pointwise mutual information is presented. A fully convolutional neural network architecture is applied in which the network learns one filter per object…

Undersampling is a common method in Magnetic Resonance Imaging (MRI) to subsample the number of data points in k-space, reducing acquisition times at the cost of decreased image quality. A popular approach is to employ undersampling…

Logo recognition is the task of identifying and classifying logos. Logo recognition is a challenging problem as there is no clear definition of a logo and there are huge variations of logos, brands and re-training to cover every variation…

Deep learning models have achieved significant success in various image related tasks. However, they often encounter challenges related to computational complexity and overfitting. In this paper, we propose an efficient approach that…