-
Squared ℓ_2 Norm as Consistency Loss for Leveraging Augmented Data to Learn Robust and Invariant Representations
Data augmentation is one of the most popular techniques for improving th...
11/25/2020 ∙ by Haohan Wang, et al. ∙
0
∙
share
read it
-
Comprehensive Attention Self-Distillation for Weakly-Supervised Object Detection
Weakly Supervised Object Detection (WSOD) has emerged as an effective to...
10/22/2020 ∙ by Zeyi Huang, et al. ∙
0
∙
share
read it
-
Self-Challenging Improves Cross-Domain Generalization
Convolutional Neural Networks (CNN) conduct image classification by acti...
07/05/2020 ∙ by Zeyi Huang, et al. ∙
0
∙
share
read it
-
Multiple Anchor Learning for Visual Object Detection
Classification and localization are two pillars of visual object detecto...
12/04/2019 ∙ by Wei Ke, et al. ∙
0
∙
share
read it
-
Improving Object Detection with Inverted Attention
Improving object detectors against occlusion, blur and noise is a critic...
03/28/2019 ∙ by Zeyi Huang, et al. ∙
0
∙
share
read it
-
Large Margin Object Tracking with Circulant Feature Maps
Structured output support vector machine (SVM) based tracking algorithms...
03/15/2017 ∙ by Mengmeng Wang, et al. ∙
0
∙
share
read it
