Align-KD: Distilling Cross-Modal Alignment Knowledge for Mobile Vision-Language Model

• URL: http://arxiv.org/abs/2412.01282v1
• Date: Mon, 02 Dec 2024 08:55:19 GMT
• Title: Align-KD: Distilling Cross-Modal Alignment Knowledge for Mobile Vision-Language Model
• Authors: Qianhan Feng, Wenshuo Li, Tong Lin, Xinghao Chen,
• Abstract summary: Vision-Language Models (VLMs) bring powerful understanding and reasoning capabilities to multimodal tasks. We propose a method called Align-KD to guide the student model to learn the cross-modal matching that occurs at the shallow layer. Under the guidance of Align-KD, the 1.7B MobileVLM V2 model can learn rich knowledge from the 7B teacher model with light design of training loss.
• Score: 11.010846827099936
• License:
• Abstract: Vision-Language Models (VLMs) bring powerful understanding and reasoning capabilities to multimodal tasks. Meanwhile, the great need for capable aritificial intelligence on mobile devices also arises, such as the AI assistant software. Some efforts try to migrate VLMs to edge devices to expand their application scope. Simplifying the model structure is a common method, but as the model shrinks, the trade-off between performance and size becomes more and more difficult. Knowledge distillation (KD) can help models improve comprehensive capabilities without increasing size or data volume. However, most of the existing large model distillation techniques only consider applications on single-modal LLMs, or only use teachers to create new data environments for students. None of these methods take into account the distillation of the most important cross-modal alignment knowledge in VLMs. We propose a method called Align-KD to guide the student model to learn the cross-modal matching that occurs at the shallow layer. The teacher also helps student learn the projection of vision token into text embedding space based on the focus of text. Under the guidance of Align-KD, the 1.7B MobileVLM V2 model can learn rich knowledge from the 7B teacher model with light design of training loss, and achieve an average score improvement of 2.0 across 6 benchmarks under two training subsets respectively. Code is available at: https://github.com/fqhank/Align-KD.

Related papers

• Multi-Stage Knowledge Integration of Vision-Language Models for Continual Learning [79.46570165281084]
  We propose a Multi-Stage Knowledge Integration network (MulKI) to emulate the human learning process in distillation methods. MulKI achieves this through four stages, including Eliciting Ideas, Adding New Ideas, Distinguishing Ideas, and Making Connections. Our method demonstrates significant improvements in maintaining zero-shot capabilities while supporting continual learning across diverse downstream tasks.
  arXiv  Detail & Related papers  (2024-11-11T07:36:19Z)
• VLM2Vec: Training Vision-Language Models for Massive Multimodal Embedding Tasks [60.5257456681402]
  We study the potential for building universal embeddings capable of handling a wide range of downstream tasks. We build a series of VLM2Vec models on SoTA VLMs like Phi-3.5-V, LLaVA-1.6 and evaluate them on MMEB's evaluation split. Our results show that VLM2Vec achieves an absolute average improvement of 10% to 20% over existing multimodal embedding models.
  arXiv  Detail & Related papers  (2024-10-07T16:14:05Z)
• TinyVLA: Towards Fast, Data-Efficient Vision-Language-Action Models for Robotic Manipulation [32.406783380729024]
  Vision-Language-Action (VLA) models have shown remarkable potential in visuomotor control and instruction comprehension through end-to-end learning processes. Current VLA models face significant challenges: they are slow during inference and require extensive pre-training on large amounts of robotic data. We introduce a new family of compact vision-language-action models, called TinyVLA, which offers two key advantages over existing VLA models.
  arXiv  Detail & Related papers  (2024-09-19T07:10:18Z)
• NVLM: Open Frontier-Class Multimodal LLMs [64.00053046838225]
  We introduce NVLM 1.0, a family of frontier-class multimodal large language models (LLMs) that achieve state-of-the-art results on vision-language tasks. We propose a novel architecture that enhances both training efficiency and multimodal reasoning capabilities. We develop production-grade multimodality for the NVLM-1.0 models, enabling them to excel in vision-language tasks.
  arXiv  Detail & Related papers  (2024-09-17T17:59:06Z)
• Interactive DualChecker for Mitigating Hallucinations in Distilling Large Language Models [7.632217365130212]
  Large Language Models (LLMs) have demonstrated exceptional capabilities across various machine learning (ML) tasks. These models can produce hallucinations, particularly in domains with incomplete knowledge. We introduce DualChecker, an innovative framework designed to mitigate hallucinations and improve the performance of both teacher and student models.
  arXiv  Detail & Related papers  (2024-08-22T12:04:04Z)
• LLAVADI: What Matters For Multimodal Large Language Models Distillation [77.73964744238519]
  In this work, we do not propose a new efficient model structure or train small-scale MLLMs from scratch. Our studies involve training strategies, model choices, and distillation algorithms in the knowledge distillation process. By evaluating different benchmarks and proper strategy, even a 2.7B small-scale model can perform on par with larger models with 7B or 13B parameters.
  arXiv  Detail & Related papers  (2024-07-28T06:10:47Z)
• Leveraging Foundation Models via Knowledge Distillation in Multi-Object Tracking: Distilling DINOv2 Features to FairMOT [0.5999777817331317]
  This work tries to leverage one such foundation model, called DINOv2, through using knowledge distillation. The results imply that although the proposed method shows improvements in certain scenarios, it does not consistently outperform the original FairMOT model.
  arXiv  Detail & Related papers  (2024-07-25T14:21:35Z)
• Learning without Forgetting for Vision-Language Models [86.53237963364754]
  Class-Incremental Learning (CIL) or continual learning is a desired capability in the real world. Recent advances in Vision-Language Models (VLM) have shown promising capabilities in learning generalizable representations. We propose PROjectiOn Fusion (PROOF) that enables VLMs to learn without forgetting.
  arXiv  Detail & Related papers  (2023-05-30T17:59:32Z)
• Enabling Multimodal Generation on CLIP via Vision-Language Knowledge Distillation [79.72299298976525]
  We propose to augment a vision-language pre-training model with a textual pre-trained language model (PLM) via vision-language knowledge distillation (VLKD) Experiments show that the resulting model has strong zero-shot performance on multimodal generation tasks, such as open-ended visual question answering and image captioning. The original textual language understanding and generation ability of the PLM is maintained after VLKD, which makes our model versatile for both multimodal and unimodal tasks.
  arXiv  Detail & Related papers  (2022-03-12T09:33:37Z)

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.