3 papers
cs.CV2025
Learning Fine-grained Domain Generalization via Hyperbolic State Space Hallucination
Qi Bi, Jingjun Yi, Haolan Zhan +2
Fine-grained domain generalization (FGDG) aims to learn a fine-grained representation that can be well generalized to unseen target domains when only trained on the source domain d…
cs.CV2024
GOOD: Towards Domain Generalized Orientated Object Detection
Qi Bi, Beichen Zhou, Jingjun Yi +3
Oriented object detection has been rapidly developed in the past few years, but most of these methods assume the training and testing images are under the same statistical distribu…
cs.CV2024
Cross-Level Multi-Instance Distillation for Self-Supervised Fine-Grained Visual Categorization
Qi Bi, Wei Ji, Jingjun Yi +2
High-quality annotation of fine-grained visual categories demands great expert knowledge, which is taxing and time consuming. Alternatively, learning fine-grained visual representa…