A new framework improves open-vocabulary object detection on novel categories by using scene graphs for relational modeling and distilling knowledge from image captions.
Learning object-language alignments for open-vocabulary object detection
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.CV 3representative citing papers
DeCo-DETR builds hierarchical semantic prototypes offline and uses decoupled training streams to deliver competitive zero-shot open-vocabulary detection with improved inference speed.
citing papers explorer
-
Unveiling the Unknown: Open Vocabulary Object Detection with Scene Graphs
A new framework improves open-vocabulary object detection on novel categories by using scene graphs for relational modeling and distilling knowledge from image captions.
-
DeCo-DETR: Decoupled Cognition DETR for efficient Open-Vocabulary Object Detection
DeCo-DETR builds hierarchical semantic prototypes offline and uses decoupled training streams to deliver competitive zero-shot open-vocabulary detection with improved inference speed.
- Grad-ECLIP: Gradient-based Visual and Textual Explanations for CLIP