TMT-VIS: Taxonomy-aware Multi-dataset Joint Training for Video Instance Segmentation

arXiv:2312.06630v3 Announce Type: replace
Abstract: Training on large-scale datasets can boost the performance of video instance segmentation while the annotated datasets for VIS are hard to scale up due to the high labor cost. What we possess are numerous isolated filed-specific datasets, thus, it is appealing to jointly train models across the aggregation of datasets to enhance data volume and diversity. However, due to the heterogeneity in category space, as mask precision increases with the data volume, simply utilizing multiple …

arxiv cs.cv dataset instance segmentation taxonomy training type video video instance segmentation