ALIP: Adaptive Language-Image Pre-training with Synthetic Caption
Authors:
- 1 October 2023
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 2910-2919
Abstract
Contrastive Language-Image Pre-training (CLIP) has significantly boosted the performance of various vision-language tasks by scaling up the dataset with image-text pairs collected from the web. However, the presence of intrinsic noise and unmatched image-text pairs in web data can potentially affect the performance of representation learning. To address this issue, we first utilize the OFA model to generate synthetic captions that focus on the image content. The generated captions contain complementary information that is beneficial for pre-training. Then, we propose an Adaptive Language-Image Pre-training (ALIP), a bi-path model that integrates supervision from both raw text and synthetic caption. As the core components of ALIP, the Language Consistency Gate (LCG) and Description Consistency Gate (DCG) dynamically adjust the weights of samples and image-text/caption pairs during the training process. Meanwhile, the adaptive contrastive loss can effectively reduce the impact of noise data and enhances the efficiency of pre-training data. We validate ALIP with experiments on different scales of models and pre-training datasets. Experiments results show that ALIP achieves state-of-the-art performance on multiple downstream tasks including zero-shot image-text retrieval and linear probe. To facilitate future research, the code and pre-trained models are released at https://github.com/deepglint/ALIP.Keywords
All Related Versions
This publication has 21 references indexed in Scilit:
- SLIP: Self-supervision Meets Language-Image Pre-training2022
- Contrastive Multiview Coding2020
- Connecting Vision and Language with Localized Narratives2020
- Deep Multimodal Representation Learning: A SurveyIEEE Access, 2019
- 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 categoriesComputer Vision and Image Understanding, 2007
- Learning a Similarity Metric Discriminatively, with Application to Face Verification2005