Search Results for author:
Found 10 papers, 6 papers with code
Unsupervised Change Detection Based on Image Reconstruction Loss
In this paper, we propose unsupervised change detection based on image reconstruction loss using only unlabeled single temporal single image.
PT4AL: Using Self-Supervised Pretext Tasks for Active Learning
Before the active learning iterations, the pretext task learner is trained on the unlabeled set, and the unlabeled data are sorted and split into batches by their pretext task losses.
Ranked #2 on
Active Learning
on CIFAR10 (10,000)
Studying the Effects of Self-Attention for Medical Image Analysis
The use of computer vision to automate the classification of medical images is widely studied.
Exploiting Features with Split-and-Share Module
Deep convolutional neural networks (CNNs) have shown state-of-the-art performances in various computer vision tasks.
Learning Visual Context by Comparison
Current methods for solving this task exploit various characteristics of the chest X-ray image, but one of the most important characteristics is still missing: the necessity of comparison between related regions in an image.
Sequential Feature Filtering Classifier
We propose Sequential Feature Filtering Classifier (FFC), a simple but effective classifier for convolutional neural networks (CNNs).
Reducing Domain Gap by Reducing Style Bias
Convolutional Neural Networks (CNNs) often fail to maintain their performance when they confront new test domains, which is known as the problem of domain shift.
Ranked #62 on
Domain Generalization
on PACS
CBAM: Convolutional Block Attention Module
We propose Convolutional Block Attention Module (CBAM), a simple yet effective attention module for feed-forward convolutional neural networks.
BAM: Bottleneck Attention Module
In this work, we focus on the effect of attention in general deep neural networks.
Distort-and-Recover: Color Enhancement using Deep Reinforcement Learning
In addition, we present a 'distort-and-recover' training scheme which only requires high-quality reference images for training instead of input and retouched image pairs.
