Enhancing Vision-Language Model Pre-training with Image-text Pair Pruning Based on Word Frequency

• URL: http://arxiv.org/abs/2410.10879v1
• Date: Wed, 09 Oct 2024 11:54:41 GMT
• Title: Enhancing Vision-Language Model Pre-training with Image-text Pair Pruning Based on Word Frequency
• Authors: Mingliang Liang, Martha Larson,
• Abstract summary: We propose Word-Frequency-based Image-Text Pair Pruning (WFPP), a novel data pruning method. WFPP prunes text-image pairs containing high-frequency words across the entire training dataset. Our experiments demonstrate that applying WFPP when training a CLIP model improves performance on a wide range of downstream tasks.
• Score: 0.0
• License:
• Abstract: 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 for pruning, but selects text-image pairs to prune based on the content of the text. Specifically, WFPP prunes text-image pairs containing high-frequency words across the entire training dataset. The effect of WFPP is to reduce the dominance of frequent words. The result a better balanced word-frequency distribution in the dataset, which is known to improve the training of word embedding models. After pre-training on the pruned subset, we fine-tuned the model on the entire dataset for one additional epoch to achieve better performance. Our experiments demonstrate that applying WFPP when training a CLIP model improves performance on a wide range of downstream tasks. WFPP also provides the advantage of speeding up pre-training by using fewer samples. Additionally, we analyze the training data before and after pruning to visualize how WFPP changes the balance of word frequencies. We hope our work encourages researchers to consider the distribution of words in the training data when pre-training VLMs, not limited to CLIP.

Related papers

• Vision Model Pre-training on Interleaved Image-Text Data via Latent Compression Learning [78.19528555505961]
  We propose a novel vision model pre-training method called Latent Compression Learning (LCL) for interleaved image-text data. The training objective can be decomposed into two basic tasks: 1) contrastive learning between visual representation and preceding context, and 2) generating subsequent text based on visual representation. Our experiments demonstrate that our method not only matches the performance of CLIP on paired pre-training datasets, but can also leverage interleaved pre-training data.
  arXiv  Detail & Related papers  (2024-06-11T17:59:35Z)
• Make Prompts Adaptable: Bayesian Modeling for Vision-Language Prompt Learning with Data-Dependent Prior [14.232144691524528]
  Recent Vision-Language Pretrained models have become the backbone for many downstream tasks. MLE training can lead the context vector to over-fit dominant image features in the training data. This paper presents a Bayesian-based framework of prompt learning, which could alleviate the overfitting issues on few-shot learning application.
  arXiv  Detail & Related papers  (2024-01-09T10:15:59Z)
• Sieve: Multimodal Dataset Pruning Using Image Captioning Models [11.362835828985494]
  Vision-Language Models (VLMs) are pretrained on large, diverse, and noisy web-crawled datasets. We argue that this approach suffers from multiple limitations including false positives and negatives due to CLIP's pretraining on noisy labels. We propose a pruning signal, Sieve, that employs synthetic captions generated by image-captioning models pretrained on small, diverse, and well-aligned image-text pairs.
  arXiv  Detail & Related papers  (2023-10-03T14:53:53Z)
• ALIP: Adaptive Language-Image Pre-training with Synthetic Caption [78.93535202851278]
  Contrastive Language-Image Pre-training (CLIP) has significantly boosted the performance of various vision-language tasks. The presence of intrinsic noise and unmatched image-text pairs in web data can potentially affect the performance of representation learning. We propose an Adaptive Language-Image Pre-training (ALIP), a bi-path model that integrates supervision from both raw text and synthetic caption.
  arXiv  Detail & Related papers  (2023-08-16T15:19:52Z)
• Weakly Supervised Vision-and-Language Pre-training with Relative Representations [76.63610760577214]
  Weakly supervised vision-and-language pre-training has been shown to effectively reduce the data cost of pre-training. Current methods use only local descriptions of images, i.e., object tags, as cross-modal anchors to construct weakly-aligned image-text pairs for pre-training.
  arXiv  Detail & Related papers  (2023-05-24T18:10:24Z)
• Scaling Language-Image Pre-training via Masking [63.36988191660858]
  Fast Language-Image Pre-training (FLIP) is a simple and more efficient method for training CLIP. Masking allows us to learn from more image-text pairs given the same wall-clock time. FLIP dominantly outperforms CLIP counterparts trained on the same data.
  arXiv  Detail & Related papers  (2022-12-01T18:59:57Z)
• Generative Negative Text Replay for Continual Vision-Language Pretraining [95.2784858069843]
  Vision-language pre-training has attracted increasing attention recently. Massive data are usually collected in a streaming fashion. We propose a multi-modal knowledge distillation between images and texts to align the instance-wise prediction between old and new models.
  arXiv  Detail & Related papers  (2022-10-31T13:42:21Z)
• Coarse-to-Fine Vision-Language Pre-training with Fusion in the Backbone [170.85076677740292]
  We present FIBER (Fusion-In-the-Backbone-basedER), a new model architecture for vision-language (VL) pre-training. Instead of having dedicated transformer layers for fusion after the uni-modal backbones, FIBER pushes multimodal fusion deep into the model. We conduct comprehensive experiments on a wide range of VL tasks, ranging from VQA, image captioning, and retrieval, to phrase grounding, referring expression comprehension, and object detection.
  arXiv  Detail & Related papers  (2022-06-15T16:41:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.