Contrastive knowledge transfer from CLIP for open vocabulary object detection
Object detection has made remarkable progress in recent years. While in real-world scenarios, a model is expected to generalize to novel objects that it never explicitly trained on. Though pre-trained vision language model has shown powerful results in zero-shot classification task, adapting it to d...
Saved in:
Main Author: | Zhang, Chuhan |
---|---|
Other Authors: | Hanwang Zhang |
Format: | Thesis-Master by Research |
Language: | English |
Published: |
Nanyang Technological University
2023
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/172024 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
Similar Items
-
Learning to recognize objects by adaptive knowledge transfer
by: Tao, Qingyi
Published: (2021) -
Real-world object detection
by: Zang, Yuhang
Published: (2023) -
Object detection from satellite imagery
by: Seah, Yi Xuan
Published: (2020) -
Fast OWDETR: transformer for open world object detection
by: Chen, Xuanying
Published: (2022) -
Embodied object hunt
by: Yeo, Zhi Hong
Published: (2020)