Search Results for author:
Found 12 papers, 6 papers with code
Training Over a Distribution of Hyperparameters for Enhanced Performance and Adaptability on Imbalanced Classification
Although binary classification is a well-studied problem, training reliable classifiers under severe class imbalance remains a challenge.
Optimizing for ROC Curves on Class-Imbalanced Data by Training over a Family of Loss Functions
Although binary classification is a well-studied problem in computer vision, training reliable classifiers under severe class imbalance remains a challenging problem.
RandMSAugment: A Mixed-Sample Augmentation for Limited-Data Scenarios
We show that low-level feature transforms play a pivotal role in this performance difference, postulate a new property of augmentations related to their data efficiency, and propose new ways to measure the diversity and realism of augmentations.
UFD-PRiME: Unsupervised Joint Learning of Optical Flow and Stereo Depth through Pixel-Level Rigid Motion Estimation
A second network, trained with optical flow from the first as pseudo-labels, takes disparities from the first network, estimates 3D rigid motion at every pixel, and reconstructs optical flow again.
SemARFlow: Injecting Semantics into Unsupervised Optical Flow Estimation for Autonomous Driving
We show that additional information such as semantics and domain knowledge can help better constrain this problem.
Unsupervised Flow Refinement near Motion Boundaries
Unsupervised optical flow estimators based on deep learning have attracted increasing attention due to the cost and difficulty of annotating for ground truth.
Cross-Attention Transformer for Video Interpolation
We propose TAIN (Transformers and Attention for video INterpolation), a residual neural network for video interpolation, which aims to interpolate an intermediate frame given two consecutive image frames around it.
Optical Flow Training under Limited Label Budget via Active Learning
Supervised training of optical flow predictors generally yields better accuracy than unsupervised training.
Joint Detection of Motion Boundaries and Occlusions
Since appearance mismatches between frames often signal vicinity to MBs or Occs, we construct a cost block that for each feature in one frame records the lowest discrepancy with matching features in a search range.
Identity Connections in Residual Nets Improve Noise Stability
Residual Neural Networks (ResNets) achieve state-of-the-art performance in many computer vision problems.
Features for Multi-Target Multi-Camera Tracking and Re-Identification
We examine the correlation between good Re-ID and good MTMCT scores, and perform ablation studies to elucidate the contributions of the main components of our system.
Ranked #94 on
Person Re-Identification
on Market-1501
Performance Measures and a Data Set for Multi-Target, Multi-Camera Tracking
To help accelerate progress in multi-target, multi-camera tracking systems, we present (i) a new pair of precision-recall measures of performance that treats errors of all types uniformly and emphasizes correct identification over sources of error; (ii) the largest fully-annotated and calibrated data set to date with more than 2 million frames of 1080p, 60fps video taken by 8 cameras observing more than 2, 700 identities over 85 minutes; and (iii) a reference software system as a comparison baseline.
