Year | Title | Author | Publication | Code | Tags | Notes | Datasets |
---|---|---|---|---|---|---|---|
2022 | Shattering Distribution for Active Learning | Cao and Tsang | IEEE TNNLS | code | New AL method |
||
2022 | Active Learning With Multiple Kernels | Hong and Chae | IEEE TNNLS | - | stream-based AL framework |
||
2022 | Multiview Multi-Instance Multilabel Active Learning | Yu et al. | IEEE TNNLS | Important, code | multiview multi-instance multilabel active learning |
||
2022 | Active Learning for Deep Visual Tracking | Yuan et al. | IEEE TNNLS | - | CNNs , Target Tracking , Representitive Sampling |
More specifically, to ensure the diversity of selected samples, we propose an active learning method based on multi-frame collaboration to select those training samples that should be and need to be annotated. Meanwhile, considering the representativeness of these selected samples, we adopt a nearest neighbor discrimination method based on the average nearest neighbor distance to screen isolated samples and low- quality samples. | OTB100 [1], UAV123 [2], TrackingNet [15], LaSOT [16], GOT10k [17], VOT2019 [41] and VOT2020 |