Related papers: Reducing Geographic Performance Differential for F…

Good local features improve the robustness of many 3D re-localization and multi-view reconstruction pipelines. The problem is that viewing angle and distance severely impact the recognizability of a local feature. Attempts to improve…

Face recognition research is one of the most active topics in computer vision (CV), and deep neural networks (DNN) are now filling the gap between human-level and computer-driven performance levels in face verification algorithms. However,…

In the last five years, deep learning methods, in particular CNN, have attracted considerable attention in the field of face-based recognition, achieving impressive results. Despite this progress, it is not yet clear precisely to what…

Face recognition (FR) models are vulnerable to performance variations across demographic groups. The causes for these performance differences are unclear due to the highly complex deep learning-based structure of face recognition models.…

The performance of deep neural networks for image recognition tasks such as predicting a smiling face is known to degrade with under-represented classes of sensitive attributes. We address this problem by introducing fairness-aware…

A key for person re-identification is achieving consistent local details for discriminative representation across variable environments. Current stripe-based feature learning approaches have delivered impressive accuracy, but do not make a…

The accuracy of face recognition systems has improved significantly in the past few years, thanks to the large amount of data collected and advancements in neural network architectures. However, these large-scale datasets are often…

Though having achieved some progresses, the hand-crafted texture features, e.g., LBP [23], LBP-TOP [11] are still unable to capture the most discriminative cues between genuine and fake faces. In this paper, instead of designing feature by…

The softmax-based loss functions and its variants (e.g., cosface, sphereface, and arcface) significantly improve the face recognition performance in wild unconstrained scenes. A common practice of these algorithms is to perform…

Face images captured in heterogeneous environments, e.g., sketches generated by the artists or composite-generation software, photos taken by common cameras and infrared images captured by corresponding infrared imaging devices, usually…

Climate models often require post-processing in order to make accurate estimates of local climate risk. The most common post-processing applied is bias-correction and spatial resolution enhancement. However, the statistical methods…

It is unknown what kind of biases modern in the wild face datasets have because of their lack of annotation. A direct consequence of this is that total recognition rates alone only provide limited insight about the generalization ability of…

In this paper we investigate the feasibility of using synthetic data to augment face datasets. In particular, we propose a novel generative adversarial network (GAN) that can disentangle identity-related attributes from non-identity-related…

Medical image registration is an important task in automated analysis of multi-modal images and temporal data involving multiple patient visits. Conventional approaches, although useful for different image types, are time consuming. Of…

Deep learning-based person identification and verification systems have remarkably improved in terms of accuracy in recent years; however, such systems, including widely popular cloud-based solutions, have been found to exhibit significant…

Despite the rapid progress in deep visual recognition, modern computer vision datasets significantly overrepresent the developed world and models trained on such datasets underperform on images from unseen geographies. We investigate the…

The use of synthetic data as an alternative to authentic datasets in face recognition (FR) development has gained significant attention, addressing privacy, ethical, and practical concerns associated with collecting and using authentic…

Graph Neural Networks (GNNs) have been successful in modeling graph-structured data. However, similar to other machine learning models, GNNs can exhibit bias in predictions based on attributes like race and gender. Moreover, bias in GNNs…

Person re-identification (re-ID) aims at matching images of the same identity across camera views. Due to varying distances between cameras and persons of interest, resolution mismatch can be expected, which would degrade person re-ID…

Heatmap regression with a deep network has become one of the mainstream approaches to localize facial landmarks. However, the loss function for heatmap regression is rarely studied. In this paper, we analyze the ideal loss function…