Ensemble CLIPs: Effective Zero-shot Classification with Hundreds of Multi-modal CLIPs
Open Access
- 30 June 2025
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 407-415
Abstract
No abstract availableFunding Information
- National Key R&D Program of China (2024YFB4710900)
- National Natural Science Foundation of China (62202087)
- Guangdong Basic and Applied Basic Research Foundation (2024A1515010244)
- Fundamental Research Funds for the Central Universities (N2404011, N2404008)
This publication has 21 references indexed in Scilit:
- PromptDet: Towards Open-Vocabulary Detection Using Uncurated Images2022
- Tip-Adapter: Training-Free Adaption of CLIP for Few-Shot Classification2022
- High-Resolution Image Synthesis with Latent Diffusion Models2022
- Learning to Prompt for Open-Vocabulary Object Detection with Vision-Language Model2022
- Describing Textures in the Wild2014
- Food-101 – Mining Discriminative Components with Random Forests2014
- Cats and dogs2012
- SUN database: Large-scale scene recognition from abbey to zoo2010
- ImageNet: A large-scale hierarchical image database2009
- Learning Generative Visual Models from Few Training Examples: An Incremental Bayesian Approach Tested on 101 Object Categories2005