公开(公告)号：US20210110178A1

公开(公告)日：2021-04-15

申请号：US17128492

申请日：2020-12-21

Applicant: NEC Laboratories America, Inc.

Inventor： Yi-Hsuan Tsai ,  Kihyuk Sohn ,  Buyu Liu ,  Manmohan Chandraker ,  Jong-Chyi Su

IPC: G06K9/00 ,  G06K9/62 ,  B60W30/095 ,  B60W30/09 ,  B60W10/18 ,  B60W10/20 ,  G08G1/16 ,  B60W50/00 ,  G06N3/08 ,  G06N3/04

Abstract: Systems and methods for obstacle detection are provided. The system aligns image level features between a source domain and a target domain based on an adversarial learning process while training a domain discriminator. The target domain includes one or more road scenes having obstacles. The system selects, using the domain discriminator, unlabeled samples from the target domain that are far away from existing annotated samples from the target domain. The system selects, based on a prediction score of each of the unlabeled samples, samples with lower prediction scores. The system annotates the samples with the lower prediction scores.

公开(公告)号：US20190354807A1

公开(公告)日：2019-11-21

申请号：US16400376

申请日：2019-05-01

Applicant: NEC Laboratories America, Inc.

Inventor： Yi-Hsuan Tsai ,  Samuel Schulter ,  Kihyuk Sohn ,  Manmohan Chandraker

IPC: G06K9/62 ,  G06N3/08

Abstract: Systems and methods for domain adaptation for structured output via disentangled representations are provided. The system receives a ground truth of a source domain. The ground truth is used in a task loss function for a first convolutional neural network that predicts at least one output based on inputs from the source domain and a target domain. The system clusters the ground truth of the source domain into a predetermined number of clusters, and predicts, via a second convolutional neural network, a structure of label patches. The structure includes an assignment of each of the at least one output of the first convolutional neural network to the predetermined number of clusters. A cluster loss is computed for the predicted structure of label patches, and an adversarial loss function is applied to the predicted structure of label patches to align the source domain and the target domain on a structural level.