FOR fine-tunes a CLIP encoder with a learnable-query decoder head and a pseudo-label loss, improving open-vocabulary object-level retrieval by up to 8 mAP@50 points over prior art.
Zero-shot object detection
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
FOR: Finetuning for Object Level Open Vocabulary Image Retrieval
FOR fine-tunes a CLIP encoder with a learnable-query decoder head and a pseudo-label loss, improving open-vocabulary object-level retrieval by up to 8 mAP@50 points over prior art.