Continual Test-Time Adaptation (CTTA) aims to adapt the source model to
...
Despite remarkable efforts been made, the classification of gigapixels
w...
Few-shot class-incremental learning(FSCIL) focuses on designing learning...
Real-world visual search systems involve deployments on multiple platfor...
Visual retrieval system faces frequent model update and deployment. It i...
Existing public person Re-Identification (ReID) datasets are small in mo...
Unsupervised domain adaptive (UDA) person re-identification (re-ID) is a...
Data augmentation in feature space is effective to increase data diversi...
Knowledge distillation(KD) aims to improve the performance of a student
...
Object detection aims to identify instances of semantic objects of a cer...
Fine-grained visual recognition aims to capture discriminative
character...