4 papers
Dynamic Cluster Data Sampling for Efficient and Long-Tail-Aware Vision-Language Pre-training
Mingliang Liang, Zhuoran Liu, Arjen P. de Vries +1
The computational cost of training a vision-language model (VLM) can be reduced by sampling the training data. Previous work on efficient VLM pre-training has pointed to the import…
Revealing the Impact of Visual Text Style on Attribute-based Descriptions Produced by Large Visual Language Models
Xiaomeng Wang, Martha Larson, Zhengyu Zhao
When the visual style of text is considered, a wide variety can be observed in font, color, and size. However, when a word is read, its meaning is independent of the style in which…
Frequency Is What You Need: Considering Word Frequency When Text Masking Benefits Vision-Language Model Pre-training
Mingliang Liang, Martha Larson
Vision Language Models (VLMs) can be trained more efficiently if training sets can be reduced in size. Recent work has shown the benefits of masking text during VLM training using…
Enhancing Vision-Language Model Pre-training with Image-text Pair Pruning Based on Word Frequency
Mingliang Liang, Martha Larson
We propose Word-Frequency-based Image-Text Pair Pruning (WFPP), a novel data pruning method that improves the efficiency of VLMs. Unlike MetaCLIP, our method does not need metadata…