This paper studies the problem of sparse residual regression, i. e., learning a linear model using a norm that favors solutions in which the residuals are sparsely distributed.
Unsupervised anomaly detection on image data is notoriously unstable.
We use the model to develop a classification scheme which suppresses the impact of noise while preserving semantic cues.
This leads us to introduce Relation Preserving Triplet Mining (RPTM), a feature-matching guided triplet mining scheme, that ensures that triplets will respect the natural subgroupings within an object ID.
Ranked #2 on Vehicle Re-Identification on VeRi-776
The foundational assumption of machine learning is that the data under consideration is separable into classes; while intuitively reasonable, separability constraints have proven remarkably difficult to formulate mathematically.
Ranked #1 on Unsupervised Anomaly Detection with Specified Settings -- 30% anomaly on CIFAR-10 (using extra training data)
This paper proposes a novel method to detect anomalies in large datasets under a fully unsupervised setting.
As local pose estimation is ill-conditioned, local pose estimation failures happen regularly, making the overall SLAM system brittle.
To this end, we present a uniform benchmark with novel evaluation metrics and a large-scale dataset for evaluating the overall performance of image matching methods.
Incorporating smoothness constraints into feature matching is known to enable ultra-robust matching.
Training a generic objectness measure to produce a small set of candidate object windows, has been shown to speed up the classical sliding window object detection paradigm.
Fundamental challenges to such an image or scene alignment task are often multifold, which render many existing techniques fall short of producing dense correspondences robustly and efficiently.
This allows us to formulate the image parsing problem as one of jointly estimating per-pixel object and attribute labels from a set of training images.