A method for incremental semantic class discovery that builds a segmented 3D map from RGBD frames and identifies new classes from unlabeled coherent regions, achieving 10.7 Hz updates on NYUDv2.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.CV 3years
2019 3verdicts
UNVERDICTED 3representative citing papers
Develops a multi-task learning based adversarial training approach to improve robustness of object detectors to adversarial attacks, with experiments on PASCAL-VOC and MS-COCO.
Deep face models trained on MS-Celeb-1M and fine-tuned on VGGFace2 achieve state-of-the-art accuracies on SCFace and ICB-RW low-resolution benchmarks without using any of their training data by leveraging appearance variety, resolution distribution, resolution matching, and probe information content
citing papers explorer
-
Incremental Class Discovery for Semantic Segmentation with RGBD Sensing
A method for incremental semantic class discovery that builds a segmented 3D map from RGBD frames and identifies new classes from unlabeled coherent regions, achieving 10.7 Hz updates on NYUDv2.
-
Towards Adversarially Robust Object Detection
Develops a multi-task learning based adversarial training approach to improve robustness of object detectors to adversarial attacks, with experiments on PASCAL-VOC and MS-COCO.
-
Exploring Factors for Improving Low Resolution Face Recognition
Deep face models trained on MS-Celeb-1M and fine-tuned on VGGFace2 achieve state-of-the-art accuracies on SCFace and ICB-RW low-resolution benchmarks without using any of their training data by leveraging appearance variety, resolution distribution, resolution matching, and probe information content