Comic2k is a dataset used for cross-domain object detection which contains 2k comic images with image and instance-level annotations.
Image Source: https://naoto0804.github.io/cross_domain_detection/
Variants: Comic2k
This dataset is used in 2 benchmarks:
| Task | Model | Paper | Date |
|---|---|---|---|
| Domain Adaptation | DDT | Diffusion Domain Teacher: Diffusion Guided … | 2025-06-04 |
| Domain Adaptation | MILA | MILA: Memory-Based Instance-Level Adaptation for … | 2023-11-20 |
| Object Detection | CDDMSL | Semi-Supervised Domain Generalization for Object … | 2023-09-24 |
Recent papers with results on this dataset: