RELO formulates visual object tracking localization as a Markov decision process solved by reinforcement learning with combined IoU and AUC rewards, augmented by layer-aligned temporal token propagation, and reports 57.5% AUC on LaSOText without template updates.
Random Erasing Data Augmentation
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
abstract
In this paper, we introduce Random Erasing, a new data augmentation method for training the convolutional neural network (CNN). In training, Random Erasing randomly selects a rectangle region in an image and erases its pixels with random values. In this process, training images with various levels of occlusion are generated, which reduces the risk of over-fitting and makes the model robust to occlusion. Random Erasing is parameter learning free, easy to implement, and can be integrated with most of the CNN-based recognition models. Albeit simple, Random Erasing is complementary to commonly used data augmentation techniques such as random cropping and flipping, and yields consistent improvement over strong baselines in image classification, object detection and person re-identification. Code is available at: https://github.com/zhunzhong07/Random-Erasing.
citation-role summary
background 1
method 1
citation-polarity summary
verdicts
UNVERDICTED 7representative citing papers
A teacher-student model with co-saliency network and growing-probability occlusion simulator outperforms prior methods on four occluded person re-identification benchmarks.
Learned data augmentation policies optimized for object detection improve COCO mAP by more than 2.3 and transfer to other datasets and models.
Rényi entropy of attention maps serves as a tunable criterion for pruning redundant patches in vision transformers, reducing compute with preserved accuracy on image recognition.
GNC convolves stochastic gradient noise to smooth sharp minima in large-batch SGD, outperforming isotropic noise for better generalization in distributed deep learning.
YOLOv4 achieves 43.5% AP (65.7% AP50) on MS COCO at ~65 FPS on Tesla V100 by integrating WRC, CSP, CmBN, SAT, Mish activation, Mosaic augmentation, DropBlock, and CIoU loss.
Combines NMAR with two U-Nets to segment hip and thigh muscles in metal-contaminated CT, reducing average ASD from 1.17 to 1.10 mm on simulated data from 20 patients.
citing papers explorer
-
RELO: Reinforcement Learning to Localize for Visual Object Tracking
RELO formulates visual object tracking localization as a Markov decision process solved by reinforcement learning with combined IoU and AUC rewards, augmented by layer-aligned temporal token propagation, and reports 57.5% AUC on LaSOText without template updates.
-
A Novel Teacher-Student Learning Framework For Occluded Person Re-Identification
A teacher-student model with co-saliency network and growing-probability occlusion simulator outperforms prior methods on four occluded person re-identification benchmarks.
-
Learning Data Augmentation Strategies for Object Detection
Learned data augmentation policies optimized for object detection improve COCO mAP by more than 2.3 and transfer to other datasets and models.
-
R\'enyi Attention Entropy for Patch Pruning
Rényi entropy of attention maps serves as a tunable criterion for pruning redundant patches in vision transformers, reducing compute with preserved accuracy on image recognition.
-
Gradient Noise Convolution (GNC): Smoothing Loss Function for Distributed Large-Batch SGD
GNC convolves stochastic gradient noise to smooth sharp minima in large-batch SGD, outperforming isotropic noise for better generalization in distributed deep learning.
-
YOLOv4: Optimal Speed and Accuracy of Object Detection
YOLOv4 achieves 43.5% AP (65.7% AP50) on MS COCO at ~65 FPS on Tesla V100 by integrating WRC, CSP, CmBN, SAT, Mish activation, Mosaic augmentation, DropBlock, and CIoU loss.
-
Automated Segmentation of Hip and Thigh Muscles in Metal Artifact-Contaminated CT using Convolutional Neural Network-Enhanced Normalized Metal Artifact Reduction
Combines NMAR with two U-Nets to segment hip and thigh muscles in metal-contaminated CT, reducing average ASD from 1.17 to 1.10 mm on simulated data from 20 patients.