Simple Open-Vocabulary Object Detection with Vision Transformers
Paper
• 2205.06230 • Published
• 4
Open-vocabulary object detection (OVD).
-
google/owlvit-base-patch32
Zero-Shot Object Detection • 0.2B • Updated • 108k • 145Note OWL-VIT is the seminal paper on Open-set object detection. It take a pretrained CLIP model, upsamples the model and ads detection box heads. The model is fully-finetuned while training these box heads.
-
Region-Aware Pretraining for Open-Vocabulary Object Detection with Vision Transformers
Paper • 2305.07011 • Published • 6 -
Multi-Modal Classifiers for Open-Vocabulary Object Detection
Paper • 2306.05493 • Published • 6 -
Scaling Open-Vocabulary Object Detection
Paper • 2306.09683 • Published • 16 -
Open-Vocabulary Universal Image Segmentation with MaskCLIP
Paper • 2208.08984 • Published -
Contrastive Feature Masking Open-Vocabulary Vision Transformer
Paper • 2309.00775 • Published • 10 -
RegionCLIP: Region-based Language-Image Pretraining
Paper • 2112.09106 • Published -
Side Adapter Network for Open-Vocabulary Semantic Segmentation
Paper • 2302.12242 • Published -
Transferable and Principled Efficiency for Open-Vocabulary Segmentation
Paper • 2404.07448 • Published • 12