Related papers: Interpretable Visualizations with Differentiating …
Deep learning is increasingly used in decision-making tasks. However, understanding how neural networks produce final predictions remains a fundamental challenge. Existing work on interpreting neural network predictions for images often…
Although biometric facial recognition systems are fast becoming part of security applications, these systems are still vulnerable to morphing attacks, in which a facial reference image can be verified as two or more separate identities. In…
Numerous computer vision applications rely on local feature descriptors, such as SIFT, SURF or FREAK, for image matching. Although their local character makes image matching processes more robust to occlusions, it often leads to…
When presented with one or a few photos of a previously unseen object, humans can instantly recognize it in different scenes. Although the human brain mechanism behind this phenomenon is still not fully understood, this work introduces a…
Estimating the number of clusters and cluster structures in unlabeled, complex, and high-dimensional datasets (like images) is challenging for traditional clustering algorithms. In recent years, a matrix reordering-based algorithm called…
Deep learning has been successfully applied to human activity recognition. However, training deep neural networks requires explicitly labeled data which is difficult to acquire. In this paper, we present a model with multiple siamese…
We propose GAN-Supervised Learning, a framework for learning discriminative models and their GAN-generated training data jointly end-to-end. We apply our framework to the dense visual alignment problem. Inspired by the classic Congealing…
Deep metric learning algorithms have been utilized to learn discriminative and generalizable models which are effective for classifying unseen classes. In this paper, a novel noise tolerant deep metric learning algorithm is proposed. The…
Learning social media data embedding by deep models has attracted extensive research interest as well as boomed a lot of applications, such as link prediction, classification, and cross-modal search. However, for social images which contain…
How do the neural networks distinguish two images? It is of critical importance to understand the matching mechanism of deep models for developing reliable intelligent systems for many risky visual applications such as surveillance and…
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…
In this paper, we propose a novel supervised learning method that is called Deep Embedding Kernel (DEK). DEK combines the advantages of deep learning and kernel methods in a unified framework. More specifically, DEK is a learnable kernel…
Deep learning models heavily rely on large scale annotated datasets for training. Unfortunately, datasets cannot capture the infinite variability of the real world, thus neural networks are inherently limited by the restricted visual and…
Node representations, or embeddings, are low-dimensional vectors that capture node properties, typically learned through unsupervised structural similarity objectives or supervised tasks. While recent efforts have focused on explaining…
We propose a novel probabilistic dimensionality reduction framework that can naturally integrate the generative model and the locality information of data. Based on this framework, we present a new model, which is able to learn a smooth…
Visual tracking is one of the most challenging computer vision problems. In order to achieve high performance visual tracking in various negative scenarios, a novel cascaded Siamese network is proposed and developed based on two different…
Self-supervised learning (SSL) has delivered superior performance on a variety of downstream vision tasks. Two main-stream SSL frameworks have been proposed, i.e., Instance Discrimination (ID) and Masked Image Modeling (MIM). ID pulls…
Recently, there has been increasing interest to leverage the competence of neural networks to analyze data. In particular, new clustering methods that employ deep embeddings have been presented. In this paper, we depart from centroid-based…
Learning to compare two objects are essential in applications, such as digital forensics, face recognition, and brain network analysis, especially when labeled data is scarce and imbalanced. As these applications make high-stake decisions…
High-dimensional time series are common in many domains. Since human cognition is not optimized to work well in high-dimensional spaces, these areas could benefit from interpretable low-dimensional representations. However, most…