Contrastive knowledge transfer from CLIP for open vocabulary object detection

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...

Full description

Bibliographic Details
Main Author: Zhang, Chuhan
Other Authors: Hanwang Zhang
Format: Thesis-Master by Research
Language:English
Published: Nanyang Technological University 2023
Subjects:
Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence
Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision
Online Access:https://hdl.handle.net/10356/172024

Internet

https://hdl.handle.net/10356/172024

Similar Items