ProCLIP: Progressive Vision-Language Alignment via LLM-based Embedder

• URL: http://arxiv.org/abs/2510.18795v2
• Date: Wed, 22 Oct 2025 03:43:28 GMT
• Title: ProCLIP: Progressive Vision-Language Alignment via LLM-based Embedder
• Authors: Xiaoxing Hu, Kaicheng Yang, Ziyang Gong, Qi Ming, Zonghao Guo, Xiang An, Ziyong Feng, Junchi Yan, Xue Yang,
• Abstract summary: The CLIP text encoder is limited by a maximum input length of 77 tokens.<n>ProCLIP is a curriculum learning-based progressive vision-language alignment framework.
• Score: 50.25233123718465
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The original CLIP text encoder is limited by a maximum input length of 77 tokens, which hampers its ability to effectively process long texts and perform fine-grained semantic understanding. In addition, the CLIP text encoder lacks support for multilingual inputs. All these limitations significantly restrict its applicability across a broader range of tasks. Recent studies have attempted to replace the CLIP text encoder with an LLM-based embedder to enhance its ability in processing long texts, multilingual understanding, and fine-grained semantic comprehension. However, because the representation spaces of LLMs and the vision-language space of CLIP are pretrained independently without alignment priors, direct alignment using contrastive learning can disrupt the intrinsic vision-language alignment in the CLIP image encoder, leading to an underutilization of the knowledge acquired during pre-training. To address this challenge, we propose ProCLIP, a curriculum learning-based progressive vision-language alignment framework to effectively align the CLIP image encoder with an LLM-based embedder. Specifically, ProCLIP first distills knowledge from CLIP's text encoder into the LLM-based embedder to leverage CLIP's rich pretrained knowledge while establishing initial alignment between the LLM embedder and CLIP image encoder. Subsequently, ProCLIP further aligns the CLIP image encoder with the LLM-based embedder through image-text contrastive tuning, employing self-distillation regularization to avoid overfitting. To achieve a more effective alignment, instance semantic alignment loss and embedding structure alignment loss are employed during representation inheritance and contrastive tuning. The Code is available at https://github.com/VisionXLab/ProCLIP.

Related papers

• SuperCLIP: CLIP with Simple Classification Supervision [88.86549733903314]
  Contrastive Language-Image Pretraining achieves strong generalization in vision-language tasks by aligning images and texts in a shared embedding space.<n>Recent findings show that CLIP-like models still underutilize fine-grained semantic signals in text.<n>We propose SuperCLIP, a framework that augments contrastive learning with classification-based supervision.
  arXiv  Detail & Related papers  (2025-12-16T15:11:53Z)
• Language-Image Alignment with Fixed Text Encoders [28.898689028197005]
  Currently, the most dominant approach to establishing language-image alignment is to pre-train text and image encoders jointly.<n>In this work, we investigate if a pre-trained fixed large language model (LLM) offers a good enough text encoder to guide visual representation learning.
  arXiv  Detail & Related papers  (2025-06-04T17:51:56Z)
• FineLIP: Extending CLIP's Reach via Fine-Grained Alignment with Longer Text Inputs [0.351124620232225]
  FineLIP enhances cross-modal text-image mapping by incorporating textbfFine-grained alignment with textbfLonger text input.<n>FineLIP first extends the positional embeddings to handle longer text, followed by the dynamic aggregation of local image and text tokens.<n>We validate our model on datasets with long, detailed captions across two tasks: zero-shot cross-modal retrieval and text-to-image generation.
  arXiv  Detail & Related papers  (2025-04-02T17:19:59Z)
• Exploring CLIP's Dense Knowledge for Weakly Supervised Semantic Segmentation [19.26516470653798]
  Weakly Supervised Semantic (WSSS) with image-level labels aims to achieve pixel-level predictions using Class Maps (CAMs)<n>Recent methods primarily focus on image-text alignment for CAM generation, while CLIP's potential in patch-text alignment remains unexplored.<n>We propose ExCEL to explore CLIP's dense knowledge via a novel patchtext alignment paradigm for WSSS.
  arXiv  Detail & Related papers  (2025-03-26T02:00:49Z)
• LLM2CLIP: Powerful Language Model Unlocks Richer Visual Representation [72.02635550088546]
  This work explores how large language models (LLMs) can enhance CLIP's capability, especially for processing longer and more complex image captions.<n>We introduce a caption-to-caption contrastive fine-tuning framework, significantly enhancing the discriminative quality of LLM outputs.<n>Our approach outperforms LoRA-based methods, achieving nearly fourfold faster training with superior performance.
  arXiv  Detail & Related papers  (2024-11-07T18:59:16Z)
• Contrastive Localized Language-Image Pre-Training [60.4967533101887]
  Contrastive Language-Image Pre-training (CLIP) has been a celebrated method for training vision encoders to generate image/text representations.<n>We propose Contrastive Localized Language-Image Pre-training (CLOC) by complementing CLIP with region-text contrastive loss and modules.<n>CLOC enables high-quality regional embeddings for image region recognition and retrieval tasks.
  arXiv  Detail & Related papers  (2024-10-03T17:56:09Z)
• Symmetrical Linguistic Feature Distillation with CLIP for Scene Text Recognition [77.93678598476149]
  We establish a novel Symmetrical Linguistic Feature Distillation framework (named CLIP-OCR) By cascading the CLIP image encoder with the reversed CLIP text encoder, a symmetrical structure is built with an image-to-text feature flow. Extensive experiments demonstrate the effectiveness of CLIP-OCR with 93.8% average accuracy on six popular STR benchmarks.
  arXiv  Detail & Related papers  (2023-10-08T04:00:20Z)
• Open Vocabulary Semantic Segmentation with Patch Aligned Contrastive Learning [82.70453633641466]
  We introduce Patch Aligned Contrastive Learning (PACL), a modified compatibility function for CLIP's contrastive loss. We show that PACL is also applicable to image-level predictions and when used with a CLIP backbone, provides a general improvement in zero-shot classification accuracy.
  arXiv  Detail & Related papers  (2022-12-09T17:23:00Z)
• CLIP also Understands Text: Prompting CLIP for Phrase Understanding [65.59857372525664]
  Contrastive Language-Image Pretraining (CLIP) efficiently learns visual concepts by pre-training with natural language supervision. In this paper, we find that the text encoder of CLIP actually demonstrates strong ability for phrase understanding, and can even significantly outperform popular language models such as BERT with a properly designed prompt.
  arXiv  Detail & Related papers  (2022-10-11T23:35:18Z)

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.