Performance Analysis
Spot the Difference: Detection of Topological Changes via Geometric Alignment
A recurring challenge is the alignment of domains whose topology is not the same; a problem that is routinely ignored, potentially introducing bias in downstream analysis.
Learning from Positive and Unlabeled Data with Arbitrary Positive Shift Supplemental Materials A Nomenclature
Boldface denotes the best performing algorithm according to mean misclassification rate.
Direct Multi-view Multi-person 3D Pose Estimation Tao Wang
Notably, it achieves 92.3% AP Multi-view multi-person 3D pose estimation aims to localize 3D skeleton joints for each person instance in a scene from multi-view camera inputs. Additionally, we mitigate the commonly faced generalization issue by a simple query adaptation strategy.
Appendix CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instances A Experimental details Training details
The learning rate starts at 0.1 and is dropped by a factor of 10 The detailed description of the augmentations are as follows: Inception crop. After the crop, cropped image are resized to the original image size. We apply color jitter with 80% of probability. Randomly apply a grayscale with 20% of probability. For unlabeled and labeled multi-class datasets, we train ResNet with CIFAR-10 and ImageNet-30.