Enhancing Multimodal LLM for Detailed and Accurate Video Captioning using Multi-Round Preference Optimization

• URL: http://arxiv.org/abs/2410.06682v2
• Date: Fri, 11 Oct 2024 02:09:30 GMT
• Title: Enhancing Multimodal LLM for Detailed and Accurate Video Captioning using Multi-Round Preference Optimization
• Authors: Changli Tang, Yixuan Li, Yudong Yang, Jimin Zhuang, Guangzhi Sun, Wei Li, Zujun Ma, Chao Zhang,
• Abstract summary: We present video-SALMONN 2, an advanced audio-visual large language model (LLM) with low-rank adaptation (LoRA) We propose new metrics to evaluate the completeness and accuracy of video descriptions, which are optimized using directed preference optimization (DPO) Experiments show that mrDPO significantly enhances video-SALMONN 2's captioning accuracy, reducing global and local error rates by 40% and 20%, respectively.
• Score: 19.327911862822262
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Videos contain a wealth of information, and generating detailed and accurate descriptions in natural language is a key aspect of video understanding. In this paper, we present video-SALMONN 2, an advanced audio-visual large language model (LLM) with low-rank adaptation (LoRA) designed for enhanced video (with paired audio) captioning through directed preference optimization (DPO). We propose new metrics to evaluate the completeness and accuracy of video descriptions, which are optimized using DPO. To further improve training, we introduce a novel multi-round DPO (mrDPO) approach, which involves periodically updating the DPO reference model, merging and re-initializing the LoRA module as a proxy for parameter updates after each training round (1,000 steps), and incorporating guidance from ground-truth video captions to stabilize the process. To address potential catastrophic forgetting of non-captioning abilities due to mrDPO, we propose rebirth tuning, which finetunes the pre-DPO LLM by using the captions generated by the mrDPO-trained model as supervised labels. Experiments show that mrDPO significantly enhances video-SALMONN 2's captioning accuracy, reducing global and local error rates by 40\% and 20\%, respectively, while decreasing the repetition rate by 35\%. The final video-SALMONN 2 model, with just 7 billion parameters, surpasses leading models such as GPT-4o and Gemini-1.5-Pro in video captioning tasks, while maintaining competitive performance to the state-of-the-art on widely used video question-answering benchmark among models of similar size. Upon acceptance, we will release the code, model checkpoints, and training and test data. Demos are available at \href{https://video-salmonn-2.github.io}{https://video-salmonn-2.github.io}.

Related papers

• VistaDPO: Video Hierarchical Spatial-Temporal Direct Preference Optimization for Large Video Models [80.92928946973026]
  We introduce VistaDPO, a framework for Video Hierarchical Spatial-Temporal Direct Preference Optimization. VistaDPO enhances text-video preference alignment across three hierarchical levels. Experiments on benchmarks such as Video Hallucination, Video QA, and Captioning performance tasks demonstrate that VistaDPO significantly improves the performance of existing LVMs.
  arXiv  Detail & Related papers  (2025-04-17T17:39:41Z)
• PaMi-VDPO: Mitigating Video Hallucinations by Prompt-Aware Multi-Instance Video Preference Learning [50.81779197183613]
  Direct Preference Optimization (DPO) helps reduce hallucinations in Video Multimodal Large Language Models (VLLMs) We propose Video Direct Preference Optimization (VDPO), an online preference learning framework that eliminates the need for preference annotation. We introduce Prompt-aware Multi-instance Learning VDPO, which selects augmentations based on prompt context.
  arXiv  Detail & Related papers  (2025-04-08T08:41:41Z)
• VPO: Aligning Text-to-Video Generation Models with Prompt Optimization [80.86205966195593]
  Video generation models are typically trained on text-to-video pairs with highly detailed and carefully crafted descriptions. We introduce VPO, a principled framework that optimize prompts based on three core principles: harmlessness, accuracy, and helpfulness. Our experiments demonstrate that VPO significantly improves safety, alignment, and video quality compared to baseline methods.
  arXiv  Detail & Related papers  (2025-03-26T12:28:20Z)
• Temporal Preference Optimization for Long-Form Video Understanding [28.623353303256653]
  Temporal Preference Optimization (TPO) is a novel post-training framework designed to enhance the temporal grounding capabilities of video-LMMs. TPO significantly enhances temporal understanding while reducing reliance on manually annotated data. LLaVA-Video-TPO establishes itself as the leading 7B model on the Video-MME benchmark.
  arXiv  Detail & Related papers  (2025-01-23T18:58:03Z)
• Prompt-A-Video: Prompt Your Video Diffusion Model via Preference-Aligned LLM [54.2320450886902]
  Text-to-video models have made remarkable advancements through optimization on high-quality text-video pairs. Current automatic methods for refining prompts encounter challenges such as Modality-Inconsistency, Cost-Discrepancy, and Model-Unaware. We introduce Prompt-A-Video, which excels in crafting Video-Centric, Labor-Free and Preference-Aligned prompts tailored to specific video diffusion model.
  arXiv  Detail & Related papers  (2024-12-19T18:32:21Z)
• Bootstrapping Language Models with DPO Implicit Rewards [45.68366127605774]
  Direct preference optimization (DPO) has greatly simplified the process from past work in reinforcement learning from human feedback. In this work, we make a novel observation that this implicit reward model can by itself be used in a bootstrapping fashion to further align the LLM. Our approach, named self-alignment with DPO ImpliCit rEwards (DICE), shows great improvements in alignment and achieves superior performance.
  arXiv  Detail & Related papers  (2024-06-14T06:57:18Z)
• Self-Play Preference Optimization for Language Model Alignment [75.83359213697854]
  Recent advancements suggest that directly working with preference probabilities can yield a more accurate reflection of human preferences. We propose a self-play-based method for language model alignment, which treats the problem as a constant-sum two-player game. Our approach, dubbed Self-Play Preference Optimization (SPPO), utilizes iterative policy updates to provably approximate the Nash equilibrium.
  arXiv  Detail & Related papers  (2024-05-01T17:59:20Z)
• PLLaVA : Parameter-free LLaVA Extension from Images to Videos for Video Dense Captioning [78.23573511641548]
  Vision-language pre-training has significantly elevated performance across a wide range of image-language applications. Yet, the pre-training process for video-related tasks demands exceptionally large computational and data resources. This paper investigates a straight-forward, highly efficient, and resource-light approach to adapting an existing image-language pre-trained model for video understanding.
  arXiv  Detail & Related papers  (2024-04-25T19:29:55Z)
• Direct Preference Optimization of Video Large Multimodal Models from Language Model Reward [118.65089648651308]
  This paper introduces a novel framework that utilizes detailed video captions as a proxy of video content. We show that applying this tailored reward through DPO significantly improves the performance of video LMMs on video Question Answering (QA) tasks.
  arXiv  Detail & Related papers  (2024-04-01T17:28:16Z)
• M2-RAAP: A Multi-Modal Recipe for Advancing Adaptation-based Pre-training towards Effective and Efficient Zero-shot Video-text Retrieval [13.418762442122723]
  We present a Multi-Modal Recipe for Advancing Adaptation-based Pre-training towards effective and efficient zero-shot video-text retrieval, dubbed M2-RAAP.
  arXiv  Detail & Related papers  (2024-01-31T12:45:44Z)
• READ: Recurrent Adapter with Partial Video-Language Alignment for Parameter-Efficient Transfer Learning in Low-Resource Video-Language Modeling [31.745255364708864]
  We introduce lightweight adapters to the pre-trained model and only update them at fine-tuning time. We propose a novel REcurrent ADapter (READ) that employs recurrent computation to enable temporal modeling capability. We validate our READ framework through extensive experiments where READ significantly outperforms all existing fine-tuning strategies.
  arXiv  Detail & Related papers  (2023-12-12T03:09:30Z)
• Video-Teller: Enhancing Cross-Modal Generation with Fusion and Decoupling [79.49128866877922]
  Video-Teller is a video-language foundation model that leverages multi-modal fusion and fine-grained modality alignment. Video-Teller boosts the training efficiency by utilizing frozen pretrained vision and language modules. It capitalizes on the robust linguistic capabilities of large language models, enabling the generation of both concise and elaborate video descriptions.
  arXiv  Detail & Related papers  (2023-10-08T03:35:27Z)
• VLAB: Enhancing Video Language Pre-training by Feature Adapting and Blending [78.1399386935455]
  Large-scale image-text contrastive pre-training models, such as CLIP, have been demonstrated to effectively learn high-quality multimodal representations. We propose a novel video-text pre-training method dubbed VLAB: Video Language pre-training by feature generativearity and Blending. VLAB transfers CLIP representations to video pre-training tasks and develops unified video multimodal models for a wide range of video-text tasks.
  arXiv  Detail & Related papers  (2023-05-22T15:54:22Z)
• LiteVL: Efficient Video-Language Learning with Enhanced Spatial-Temporal Modeling [48.283659682112926]
  We propose LiteVL, which adapts a pre-trained image-language model BLIP into a video-text model directly on downstream tasks. We also propose a non-parametric pooling mechanism to adaptively reweight the fine-grained video embedding conditioned on the text.
  arXiv  Detail & Related papers  (2022-10-21T13:03:49Z)

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.