We present Meta Pseudo Labels, a semi-supervised learning method that achieves a new state-of-the-art top-1 accuracy of 90.2% on ImageNet, which is 1.6% better than the existing state-of-the-art [16]. Like Pseudo Labe...
详细信息
ISBN:
(纸本)9781665445092
We present Meta Pseudo Labels, a semi-supervised learning method that achieves a new state-of-the-art top-1 accuracy of 90.2% on ImageNet, which is 1.6% better than the existing state-of-the-art [16]. Like Pseudo Labels, Meta Pseudo Labels has a teacher network to generate pseudo labels on unlabeled data to teach a student network. However, unlike Pseudo Labels where the teacher is fixed, the teacher in Meta Pseudo Labels is constantly adapted by the feedback of the student's performance on the labeled dataset. As a result, the teacher generates better pseudo labels to teach the student.(1)
We present Deep Global Registration, a differentiable framework for pairwise registration of real-world 3D scans. Deep global registration is based on three modules: a 6-dimensional convolutional network for correspon...
详细信息
ISBN:
(纸本)9781728171685
We present Deep Global Registration, a differentiable framework for pairwise registration of real-world 3D scans. Deep global registration is based on three modules: a 6-dimensional convolutional network for correspondence confidence prediction, a differentiable Weighted Procrustes algorithm for closed-form pose estimation, and a robust gradient-based SE(3) optimizer for pose refinement. Experiments demonstrate that our approach outperforms state-of-the-art methods, both learning-based and classical, on real-world data.
Gestures are a common form of human communication and important for human computer interfaces (HCI). Recent approaches to gesture recognition use deep learning methods, including multi-channel methods. We show that wh...
详细信息
ISBN:
(纸本)9781538664209
Gestures are a common form of human communication and important for human computer interfaces (HCI). Recent approaches to gesture recognition use deep learning methods, including multi-channel methods. We show that when spatial channels are focused on the hands, gesture recognition improves significantly, particularly when the channels are fused using a sparse network. Using this technique, we improve performance on the ChaLearn IsoGD dataset from a previous best of 67.71% to 82.07%, and on the NVIDIA dataset from 83.8% to 91.28%.
Neural networks are used for many real world applications, but often they have problems estimating their own confidence. This is particularly problematic for computervision applications aimed at making high stakes de...
详细信息
ISBN:
(纸本)9781665448994
Neural networks are used for many real world applications, but often they have problems estimating their own confidence. This is particularly problematic for computervision applications aimed at making high stakes decisions with humans and their lives. In this paper we make a meta-analysis of the literature, showing that most if not all computervision applications do not use proper epistemic uncertainty quantification, which means that these models ignore their own limitations. We describe the consequences of using models without proper uncertainty quantification, and motivate the community to adopt versions of the models they use that have proper calibrated epistemic uncertainty, in order to enable out of distribution detection. We close the paper with a summary of challenges on estimating uncertainty for computervision applications and recommendations.
We show how shadows can be efficiently generated in differentiable rendering of triangle meshes. Our central observation is that pre-filtered shadow mapping, a technique for approximating shadows based on rendering fr...
详细信息
ISBN:
(纸本)9798350301298
We show how shadows can be efficiently generated in differentiable rendering of triangle meshes. Our central observation is that pre-filtered shadow mapping, a technique for approximating shadows based on rendering from the perspective of a light, can be combined with existing differentiable rasterizers to yield differentiable visibility information. We demonstrate at several inverse graphics problems that differentiable shadow maps are orders of magnitude faster than differentiable light transport simulation with similar accuracy - while differentiable rasterization without shadows often fails to converge.
Understanding the complex relationship between emotions and facial expressions is important for both psychologists and computer scientists. A large body of research in psychology investigates facial expressions, emoti...
详细信息
ISBN:
(数字)9781665487399
ISBN:
(纸本)9781665487399
Understanding the complex relationship between emotions and facial expressions is important for both psychologists and computer scientists. A large body of research in psychology investigates facial expressions, emotions, and how emotions are perceived from facial expressions. As computer scientists look to incorporate this research into automatic emotion perception systems, it is important to understand the nature and limitations of human emotion perception. These principles of emotion science affect the way datasets are created, methods are implemented, and results are interpreted in automated emotion perception. This paper aims to distill and align prior work in automated and human facial emotion perception to facilitate future discussions and research at the intersection of the two disciplines.
Super-Fibonacci spirals are an extension of Fibonacci spirals, enabling fast generation of an arbitrary but fixed number of 3D orientations. The algorithm is simple and fast. A comprehensive evaluation comparing to ot...
详细信息
ISBN:
(数字)9781665469463
ISBN:
(纸本)9781665469463
Super-Fibonacci spirals are an extension of Fibonacci spirals, enabling fast generation of an arbitrary but fixed number of 3D orientations. The algorithm is simple and fast. A comprehensive evaluation comparing to other methods shows that the generated sets of orientations have low discrepancy, minimal spurious components in the power spectrum, and almost identical Voronoi volumes. This makes them useful for a variety of applications, in particular Monte Carlo sampling.
The NTIRE 2021 workshop features a Multi-modal Aerial View Object Classification Challenge. Its focus is on multi-sensor imagery classification in order to improve the performance of automatic target recognition (ATR)...
详细信息
ISBN:
(纸本)9781665448994
The NTIRE 2021 workshop features a Multi-modal Aerial View Object Classification Challenge. Its focus is on multi-sensor imagery classification in order to improve the performance of automatic target recognition (ATR) systems. In this paper we describe our entry in this challenge, a method focused on efficiency and low computational time, while maintaining a high level of accuracy. The method is a convolutional neural network with 11 convolutions, 1 max pooling layers and 3 residual blocks which has a total of 373.130 parameters. The method ranks 3rd in the Track 2 (SAR+EO) of the challenge.
Traditional empirical risk minimization (ERM) for semantic segmentation can disproportionately advantage or disadvantage certain target classes in favor of an (unfair but) improved overall performance. Inspired by the...
详细信息
ISBN:
(纸本)9781665448994
Traditional empirical risk minimization (ERM) for semantic segmentation can disproportionately advantage or disadvantage certain target classes in favor of an (unfair but) improved overall performance. Inspired by the recently introduced tilted ERM (TERM), we propose tilted cross-entropy (TCE) loss and adapt it to the semantic segmentation setting to minimize performance disparity among target classes and promote fairness. Through quantitative and qualitative performance analyses, we demonstrate that the proposed Stochastic TCE for semantic segmentation can offer improved overall fairness by efficiently minimizing the performance disparity among the target classes of Cityscapes.
暂无评论