Search Results for author:
Found 5 papers, 1 papers with code
Guiding Attention in End-to-End Driving Models
Vision-based end-to-end driving models trained by imitation learning can lead to affordable solutions for autonomous driving.
Co-Training for Unsupervised Domain Adaptation of Semantic Segmentation Models
In this paper, we propose a new co-training procedure for synth-to-real UDA of semantic segmentation models.
Co-training for Deep Object Detection: Comparing Single-modal and Multi-modal Approaches
This data labeling bottleneck may be intensified due to domain shifts among image sensors, which could force per-sensor data labeling.
Co-training for On-board Deep Object Detection
Providing ground truth supervision to train visual models has been a bottleneck over the years, exacerbated by domain shifts which degenerate the performance of such models.
Temporal Coherence for Active Learning in Videos
Our active learning criterion is based on the estimated number of errors in terms of false positives and false negatives.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
