TY - GEN
T1 - Ground-truth or DAER
T2 - 18th IEEE/CVF International Conference on Computer Vision, ICCV 2021
AU - Lemmer, Stephan J.
AU - Corso, Jason J.
N1 - Publisher Copyright:
© 2021 IEEE
PY - 2021
Y1 - 2021
N2 - Many vision tasks use secondary information at inference time-a seed-to assist a computer vision model in solving a problem. For example, an initial bounding box is needed to initialize visual object tracking. To date, all such work makes the assumption that the seed is a good one. However, in practice, from crowdsourcing to noisy automated seeds, this is often not the case. We hence propose the problem of seed rejection-determining whether to reject a seed based on the expected performance degradation when it is provided in place of a gold-standard seed. We provide a formal definition to this problem, and focus on two meaningful subgoals: understanding causes of error and understanding the model's response to noisy seeds conditioned on the primary input. With these goals in mind, we propose a novel training method and evaluation metrics for the seed rejection problem. We then use seeded versions of the viewpoint estimation and fine-grained classification tasks to evaluate these contributions. In these experiments, we show our method can reduce the number of seeds that need to be reviewed for a target performance by over 23% compared to strong baselines.
AB - Many vision tasks use secondary information at inference time-a seed-to assist a computer vision model in solving a problem. For example, an initial bounding box is needed to initialize visual object tracking. To date, all such work makes the assumption that the seed is a good one. However, in practice, from crowdsourcing to noisy automated seeds, this is often not the case. We hence propose the problem of seed rejection-determining whether to reject a seed based on the expected performance degradation when it is provided in place of a gold-standard seed. We provide a formal definition to this problem, and focus on two meaningful subgoals: understanding causes of error and understanding the model's response to noisy seeds conditioned on the primary input. With these goals in mind, we propose a novel training method and evaluation metrics for the seed rejection problem. We then use seeded versions of the viewpoint estimation and fine-grained classification tasks to evaluate these contributions. In these experiments, we show our method can reduce the number of seeds that need to be reviewed for a target performance by over 23% compared to strong baselines.
UR - http://www.scopus.com/inward/record.url?scp=85127778480&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85127778480&partnerID=8YFLogxK
U2 - 10.1109/ICCV48922.2021.00074
DO - 10.1109/ICCV48922.2021.00074
M3 - Conference contribution
AN - SCOPUS:85127778480
T3 - Proceedings of the IEEE International Conference on Computer Vision
SP - 683
EP - 694
BT - Proceedings - 2021 IEEE/CVF International Conference on Computer Vision, ICCV 2021
Y2 - 11 October 2021 through 17 October 2021
ER -