4 papers · 1 filter
Robust Instance Tracking via Uncertainty Flow
Jianing Qian, Junyu Nan, Siddharth Ancha +2
Current state-of-the-art trackers often fail due to distractorsand large object appearance changes. In this work, we explore the use ofdense optical flow to improve tracking robust…
Uncertainty-aware Self-supervised 3D Data Association
Jianren Wang, Siddharth Ancha, Yi-Ting Chen +1
3D object trackers usually require training on large amounts of annotated data that is expensive and time-consuming to collect. Instead, we propose leveraging vast unlabeled datase…
Combining Deep Learning and Verification for Precise Object Instance Detection
Siddharth Ancha, Junyu Nan, David Held
Deep learning object detectors often return false positives with very high confidence. Although they optimize generic detection performance, such as mean average precision (mAP), t…
Autofocus Layer for Semantic Segmentation
Yao Qin, Konstantinos Kamnitsas, Siddharth Ancha +4
We propose the autofocus convolutional layer for semantic segmentation with the objective of enhancing the capabilities of neural networks for multi-scale processing. Autofocus lay…