- open set object detection
- open world object detection
- open world tracking
- open set segmentation
- open set panoptic segmentation
- Dropout sampling for robust object detection in open-set conditions, Dimity Miller, Lachlan Nicholson, Feras Dayoub, Niko Sunderhauf
- The Overlooked Elephant of Object Detection: Open Set, Akshay Raj Dhamija, Manuel G ̈unther, Jonathan Ventura, and Terrance E. Boult
- Exemplar-Based Open-Set Panoptic Segmentation Network, Jaedong Hwang, Seoung Wug Oh, Joon-Young Lee, Bohyung Han [CVPR 2021]
- OW-DETR: Open-world Detection Transformer Akshita Gupta, Sanath Narayan, K. J. Joseph, S. Khan, F. Khan, M. Shah
- Towards open world object detection, K J Joseph, Salman Khan, Fahad Shahbaz Khan, Vineeth N Balasubramanian
- Deep Metric Learning for Open World Semantic Segmentation, Jun Cen Peng Yun Junhao Cai Michael Yu Wang Ming Liu
- Learning open-world object proposals without learning to classify, Dahun Kim, Tsung-Yi Lin, Anelia Angelova, In So Kweon, Weicheng Kuo
- Uncertainty for Identifying Open-Set Errors in Visual Object Detection Dimity Miller, N. Sunderhauf, Michael Milford, Feras Dayoub
- Learning to Detect Every Thing in an Open World, Kuniaki Saito, Ping Hu, Trevor Darrell, Kate Saenko
- Precision and Recall -
- Absolute Open Set Error - total number of observations that pass the Entropy test, fall on unknown objects (there are no overlapping groud truth objects with an IoU >= 0.5 )and do not have a winning class label of unknown. In the case all observations are known objects, open set error is 0. - definition from Miller et al
- Scene RGB-D
- QUT Campus Dataset