OOWL500: Overcoming Dataset Collection Bias in the Wild

no code implementations • 24 Aug 2021 • Brandon Leung, Chih-Hui Ho, Amir Persekian, David Orozco, Yen Chang, Erik Sandstrom, Bo Liu, Nuno Vasconcelos

Second, it is used to show that the augmentation of in the wild datasets, such as ImageNet, with in the lab data, such as OOWL500, can significantly decrease these biases, leading to object recognizers of improved generalization.

Adversarial Attack Data Augmentation +2

Domain Adaptation for Real-World Single View 3D Reconstruction

no code implementations • 24 Aug 2021 • Brandon Leung, Siddharth Singh, Arik Horodniceanu

Results are performed with ShapeNet as the source domain and domains within the Object Dataset Domain Suite (ODDS) dataset as the target, which is a real world multiview, multidomain image dataset.

3D Reconstruction Object Reconstruction +2

Black-Box Test-Time Shape REFINEment for Single View 3D Reconstruction

no code implementations • 23 Aug 2021 • Brandon Leung, Chih-Hui Ho, Nuno Vasconcelos

Much recent progress has been made in reconstructing the 3D shape of an object from an image of it, i. e. single view 3D reconstruction.

3D Reconstruction Single-View 3D Reconstruction