ILDAV21
* *Interactive Labeling and Data Augmentation for Vision
* All you need are a few pixels: semantic segmentation with PixelPick
* Bounding Box Dataset Augmentation for Long-range Object Distance Estimation
* Class-Agnostic Segmentation Loss and Its Application to Salient Object Detection and Segmentation
* Data Augmentation for Scene Text Recognition
* EdgeFlow: Achieving Practical Interactive Segmentation with Edge-Guided Flow
* InAugment: Improving Classifiers via Internal Augmentation
* Interactive Labeling for Human Pose Estimation in Surveillance Videos
* Learning to Localise and Count with Incomplete Dot-Annotations
* Localizing Human Keypoints beyond the Bounding Box
* Meta Self-Learning for Multi-Source Domain Adaptation: A Benchmark
* Multi-Domain Conditional Image Translation: Translating Driving Datasets from Clear-Weather to Adverse Conditions
* Nuisance-Label Supervision: Robustness Improvement by Free Labels
* Object-Based Augmentation for Building Semantic Segmentation: Ventura and Santa Rosa Case Study
* Reducing Label Effort: Self-Supervised meets Active Learning
* Self-improving classification performance through GAN distillation
* Using Synthetic Data Generation to Probe Multi-View Stereo Networks
* Weakly-Supervised Semantic Segmentation by Learning Label Uncertainty
18 for ILDAV21