More Like this

1. NaQ: Leveraging Narrations as Queries to Supervise Episodic Memory

   Ramakrishnan, Santhosh; Al-Halah, Ziad; Grauman, Kristen (January 2023, IEEE Conference on Computer Vision and Pattern Recognition)
2. NaQ: Leveraging Narrations as Queries to Supervise Episodic Memory

   Santhosh Kumar Ramakrishnan, Ziad Al-Halah (January 2023, arXivorg)
3. A Correct-and-Certify Approach to Self-Supervise Object Pose Estimators via Ensemble Self-Training

   Shi, Jingnan; Talak, Rajat; Maggio, Dominic; Carlone, Luca (July 2023, Robotics: Science and Systems (RSS))
4. A correct-and-certify approach to self-supervise object pose estimators via ensemble self-training

   J. Shil; R. Talak; D. Maggio; L. Carlone (July 2023, Robotics: Science and Systems (RSS))

   Real-world robotics applications demand object pose estimation methods that work reliably across a variety of scenarios. Modern learning-based approaches require large labeled datasets and tend to perform poorly outside the training domain. Our first contribution is to develop a robust corrector module that corrects pose estimates using depth information, thus enabling existing methods to better generalize to new test domains; the corrector operates on semantic keypoints (but is also applicable to other pose estimators) and is fully differentiable. Our second contribution is an ensemble self-training approach that simultaneously trains multiple pose estimators in a self-supervised manner. Our ensemble self-training architecture uses the robust corrector to refine the output of each pose estimator; then, it evaluates the quality of the outputs using observable correctness certificates; finally, it uses the observably correct outputs for further training, without requiring external supervision. As an additional contribution, we propose small improvements to a regression-based keypoint detection architecture, to enhance its robustness to outliers; these improvements include a robust pooling scheme and a robust centroid computation. Experiments on the YCBV and TLESS datasets show the proposed ensemble self-training outperforms fully supervised baselines while not requiring 3D annotations on real data. 

   more » « less
5. A Correct-and-Certify Approach to Self-Supervise Object Pose Estimators via Ensemble Self-Training

   Shi, Jingnan; Talak, Rajat; Maggio, Dominic; Carlone, Luca (July 2023, Robotics: Science and Systems (RSS))