search
HomeTechnology peripheralsAIAdd fast and slow eyes to the video model, Apple's new training-free method surpasses everything SOTA in seconds

Since the release of Sora, the field of AI video generation has become more "busy". In the past few months, we have witnessed Jimeng, Runway Gen-3, Luma AI, and Kuaishou Keling taking turns to explode.

Unlike the past models that can be identified as AI-generated at a glance, this batch of large video models may be the "best" we have ever seen.

However, behind the amazing performance of the video large language model (LLM) is a huge and finely annotated video data set, which requires a very high cost. Recently, a number of innovative methods have emerged in the research field that do not require additional training: using trained image large language models to directly process video tasks, thus bypassing the "expensive" training process.

In addition, most existing video LLMs suffer from two major disadvantages: (1) they can only handle video input with a limited number of frames, which makes it difficult for the model to capture the subtle spatial and temporal content in the video; (2) they It lacks temporal modeling design, but simply inputs video features into LLM, completely relying on LLM's ability to model motion.

In response to the above problems, Apple researchers proposed SlowFast-LLaVA (SF-LLaVA for short). This model is based on the LLaVA-NeXT architecture developed by the Byte team. It requires no additional fine-tuning and can be used out of the box. Inspired by the successful two-stream network in the field of action recognition, the research team designed a novel SlowFast input mechanism for video LLM.

Simply put, SF-LLaVA will understand the details and motion in the video through two different observation speeds (Slow and Fast).

  • Slow path: extract features at low frame rates while retaining as much spatial detail as possible (e.g. retain 24×24 tokens every 8 frames)
  • Fast path: run at high frame rates, but Use a larger spatial pooling step size to reduce the resolution of the video to simulate a larger temporal context and focus more on understanding the coherence of actions

This is equivalent to the model having two "eyes": one Just look slowly and pay attention to the details; the other one is to look quickly and pay attention to the movements. This solves the pain points of most existing video LLMs and can capture both detailed spatial semantics and longer temporal context.

Add fast and slow eyes to the video model, Apples new training-free method surpasses everything SOTA in seconds

Paper link: https://arxiv.org/pdf/2407.15841

Experimental results show that SF-LLaVA surpasses existing training-free methods by significant advantages in all benchmark tests. Compared with carefully fine-tuned SFT models, SF-LLaVA achieves the same performance or even better.

Add fast and slow eyes to the video model, Apples new training-free method surpasses everything SOTA in seconds

Model architecture

As shown in the figure below, SF-LLaVA follows the standard training-free video LLM process. It takes a video V and a question Q as input and outputs the corresponding answer A.

Add fast and slow eyes to the video model, Apples new training-free method surpasses everything SOTA in seconds

對於輸入,要從每個視訊任意大小和長度中均勻取樣 N 幀,I = {I_1, I_2, ..., I_N},不需要對選取的視訊幀進行特別的組合或排列。以幀為單位視獨立提取頻特徵為 F_v ∈ R^N×H×W,其中 H 和 W 分別為幀特徵的高度和寬度。

下一步需要在慢速和快速兩個路徑中進一步處理 F_v,並將它們結合起來作為有效的視頻表示。慢速路徑從 F_v 中均勻取樣Add fast and slow eyes to the video model, Apples new training-free method surpasses everything SOTA in seconds的幀特徵,其中Add fast and slow eyes to the video model, Apples new training-free method surpasses everything SOTA in seconds

先前有研究發現,在空間維度上適當池化可以提高影片產生的效率和穩健性。因此,研究團隊在 F_v 上應用步長為 σ_h×σ_w 的池化過程,得到最終特徵:Add fast and slow eyes to the video model, Apples new training-free method surpasses everything SOTA in seconds,其中Add fast and slow eyes to the video model, Apples new training-free method surpasses everything SOTA in secondsAdd fast and slow eyes to the video model, Apples new training-free method surpasses everything SOTA in seconds。慢速路徑的整個過程如公式 2 所示。

Add fast and slow eyes to the video model, Apples new training-free method surpasses everything SOTA in seconds

快速路徑保留 F_v 中的所有幀特徵,以盡可能多地捕捉視訊的長程時間上下文。具體來說,研究團隊使用空間池化步長Add fast and slow eyes to the video model, Apples new training-free method surpasses everything SOTA in seconds對 F_v 進行激進的下取樣,得到最終特徵Add fast and slow eyes to the video model, Apples new training-free method surpasses everything SOTA in seconds。研究團隊設定Add fast and slow eyes to the video model, Apples new training-free method surpasses everything SOTA in secondsAdd fast and slow eyes to the video model, Apples new training-free method surpasses everything SOTA in seconds,讓快速路徑能專注於模擬時間脈絡和運動線索。慢速路徑的整個過程如公式 3 所示。

Add fast and slow eyes to the video model, Apples new training-free method surpasses everything SOTA in seconds

最後,得到聚合的視訊特徵:Add fast and slow eyes to the video model, Apples new training-free method surpasses everything SOTA in seconds,其中 flat 和 [, ] 分別表示展平和連接操作。如表達式所示,Add fast and slow eyes to the video model, Apples new training-free method surpasses everything SOTA in seconds不需要任何特殊的 token 來分隔慢速和快速路徑。 SF-LLaVA 總共使用Add fast and slow eyes to the video model, Apples new training-free method surpasses everything SOTA in seconds個影片 token。影片的視覺特徵Add fast and slow eyes to the video model, Apples new training-free method surpasses everything SOTA in seconds將和文字訊息(例如使用者提出的問題)將被組合在一起,作為輸入資料送入大型語言模型(LLM)進行處理。

SlowFast 流程如公式 4 所示。

Add fast and slow eyes to the video model, Apples new training-free method surpasses everything SOTA in seconds

實驗結果

研究團隊對 SF-LLaVA 進行了全面的性能評估,將其與當前 SOTA 免訓練模型(如 IG-VLM 和 LLoVi)在多個視訊問答任務中進行了對比。此外,他們還將其與經過視訊資料集監督微調(SFT)的視訊 LLM,例如 VideoLLaVA 和 PLLaVA 進行了比較。

開放式視訊問答

如下表所示,在開放式視訊問答任務中,SF-LLaVA 在所有基準測試中都比現有的免訓練方法表現得更好。具體來說,分別搭載7B 和34B 參數規模的LLM 時,SF-LLaVA 分別在MSRVTT-QA 上比IGVLM 高出2.1% 和5.0%,在TGIF-QA 上高出5.7% 和1.5%,在ActivityNet -QA 上高出2.0% 和0.8%。

即使與經過微調的SFT 方法相比,SF-LLaVA 在大多數基準測試中也展現了可比的性能,只有在ActivityNet-QA 這一基准上,PLLaVA 和LLaVA-NeXT-VideoDPO 略勝一籌。

Add fast and slow eyes to the video model, Apples new training-free method surpasses everything SOTA in seconds

多項選擇視訊問答

從下表中可見,在所有基準測試中,SF-LLaVA 在多項選擇視訊問答的表現都優於其他免費訓練方法。在要求複雜長時序推理的 EgoSchema 資料集中,SF-LLaVA7B 和 34B 的版本相較 IG-VLM 模型的得分分別高出 11.4% 和 2.2%。

雖然 VideoTree 在基準測試中領先,因為它是基於 GPT-4 的專有模型,因而性能遠高於開源 LLM。與 SFT 方法相比,SF-LLaVA 34B 模型在 EgoSchema 上也取得了更好的結果,這證實了 SlowFast 設計處理長影片的強大能力。
Text Generation 

Add fast and slow eyes to the video model, Apples new training-free method surpasses everything SOTA in seconds

文生影片

如表 3 所示,對於文字產生影片的任務,SF-LLaVA 也顯示出了一些優勢。 SF-LLaVA-34B 在整體表現上超越了所有免訓練的基準。儘管在細節取向方面,SF-LLaVA 略遜於 LLaVA-NeXT-Image。基於 SlowFast 設計,SF-LLaVA 可以用更少的視覺 token 覆蓋更長的時間上下文,因此在時間理解任務中表現得格外出色。

此外,在文生影片的表現上,SF-LLaVA-34B 也優於大多數 SFT 方法。

Add fast and slow eyes to the video model, Apples new training-free method surpasses everything SOTA in seconds

更多細節,請參考原論文。

The above is the detailed content of Add fast and slow eyes to the video model, Apple's new training-free method surpasses everything SOTA in seconds. For more information, please follow other related articles on the PHP Chinese website!

Statement
The content of this article is voluntarily contributed by netizens, and the copyright belongs to the original author. This site does not assume corresponding legal responsibility. If you find any content suspected of plagiarism or infringement, please contact admin@php.cn
4090生成器:与A100平台相比,token生成速度仅低于18%,上交推理引擎赢得热议4090生成器:与A100平台相比,token生成速度仅低于18%,上交推理引擎赢得热议Dec 21, 2023 pm 03:25 PM

PowerInfer提高了在消费级硬件上运行AI的效率上海交大团队最新推出了超强CPU/GPULLM高速推理引擎PowerInfer。PowerInfer和llama.cpp都在相同的硬件上运行,并充分利用了RTX4090上的VRAM。这个推理引擎速度有多快?在单个NVIDIARTX4090GPU上运行LLM,PowerInfer的平均token生成速率为13.20tokens/s,峰值为29.08tokens/s,仅比顶级服务器A100GPU低18%,可适用于各种LLM。PowerInfer与

思维链CoT进化成思维图GoT,比思维树更优秀的提示工程技术诞生了思维链CoT进化成思维图GoT,比思维树更优秀的提示工程技术诞生了Sep 05, 2023 pm 05:53 PM

要让大型语言模型(LLM)充分发挥其能力,有效的prompt设计方案是必不可少的,为此甚至出现了promptengineering(提示工程)这一新兴领域。在各种prompt设计方案中,思维链(CoT)凭借其强大的推理能力吸引了许多研究者和用户的眼球,基于其改进的CoT-SC以及更进一步的思维树(ToT)也收获了大量关注。近日,苏黎世联邦理工学院、Cledar和华沙理工大学的一个研究团队提出了更进一步的想法:思维图(GoT)。让思维从链到树到图,为LLM构建推理过程的能力不断得到提升,研究者也通

复旦NLP团队发布80页大模型Agent综述,一文纵览AI智能体的现状与未来复旦NLP团队发布80页大模型Agent综述,一文纵览AI智能体的现状与未来Sep 23, 2023 am 09:01 AM

近期,复旦大学自然语言处理团队(FudanNLP)推出LLM-basedAgents综述论文,全文长达86页,共有600余篇参考文献!作者们从AIAgent的历史出发,全面梳理了基于大型语言模型的智能代理现状,包括:LLM-basedAgent的背景、构成、应用场景、以及备受关注的代理社会。同时,作者们探讨了Agent相关的前瞻开放问题,对于相关领域的未来发展趋势具有重要价值。论文链接:https://arxiv.org/pdf/2309.07864.pdfLLM-basedAgent论文列表:

吞吐量提升5倍,联合设计后端系统和前端语言的LLM接口来了吞吐量提升5倍,联合设计后端系统和前端语言的LLM接口来了Mar 01, 2024 pm 10:55 PM

大型语言模型(LLM)被广泛应用于需要多个链式生成调用、高级提示技术、控制流以及与外部环境交互的复杂任务。尽管如此,目前用于编程和执行这些应用程序的高效系统却存在明显的不足之处。研究人员最近提出了一种新的结构化生成语言(StructuredGenerationLanguage),称为SGLang,旨在改进与LLM的交互性。通过整合后端运行时系统和前端语言的设计,SGLang使得LLM的性能更高、更易控制。这项研究也获得了机器学习领域的知名学者、CMU助理教授陈天奇的转发。总的来说,SGLang的

FATE 2.0发布:实现异构联邦学习系统互联FATE 2.0发布:实现异构联邦学习系统互联Jan 16, 2024 am 11:48 AM

FATE2.0全面升级,推动隐私计算联邦学习规模化应用FATE开源平台宣布发布FATE2.0版本,作为全球领先的联邦学习工业级开源框架。此次更新实现了联邦异构系统之间的互联互通,持续增强了隐私计算平台的互联互通能力。这一进展进一步推动了联邦学习与隐私计算规模化应用的发展。FATE2.0以全面互通为设计理念,采用开源方式对应用层、调度、通信、异构计算(算法)四个层面进行改造,实现了系统与系统、系统与算法、算法与算法之间异构互通的能力。FATE2.0的设计兼容了北京金融科技产业联盟的《金融业隐私计算

220亿晶体管,IBM机器学习专用处理器NorthPole,能效25倍提升220亿晶体管,IBM机器学习专用处理器NorthPole,能效25倍提升Oct 23, 2023 pm 03:13 PM

IBM再度发力。随着AI系统的飞速发展,其能源需求也在不断增加。训练新系统需要大量的数据集和处理器时间,因此能耗极高。在某些情况下,执行一些训练好的系统,智能手机就能轻松胜任。但是,执行的次数太多,能耗也会增加。幸运的是,有很多方法可以降低后者的能耗。IBM和英特尔已经试验过模仿实际神经元行为设计的处理器。IBM还测试了在相变存储器中执行神经网络计算,以避免重复访问RAM。现在,IBM又推出了另一种方法。该公司的新型NorthPole处理器综合了上述方法的一些理念,并将其与一种非常精简的计算运行

大模型也有小偷?为保护你的参数,上交大给大模型制作「人类可读指纹」大模型也有小偷?为保护你的参数,上交大给大模型制作「人类可读指纹」Feb 02, 2024 pm 09:33 PM

将不同的基模型象征为不同品种的狗,其中相同的「狗形指纹」表明它们源自同一个基模型。大模型的预训练需要耗费大量的计算资源和数据,因此预训练模型的参数成为各大机构重点保护的核心竞争力和资产。然而,与传统软件知识产权保护不同,对预训练模型参数盗用的判断存在以下两个新问题:1)预训练模型的参数,尤其是千亿级别模型的参数,通常不会开源。预训练模型的输出和参数会受到后续处理步骤(如SFT、RLHF、continuepretraining等)的影响,这使得判断一个模型是否基于另一个现有模型微调得来变得困难。无

何恺明和谢赛宁团队成功跟随解构扩散模型探索,最终创造出备受赞誉的去噪自编码器何恺明和谢赛宁团队成功跟随解构扩散模型探索,最终创造出备受赞誉的去噪自编码器Jan 29, 2024 pm 02:15 PM

去噪扩散模型(DDM)是目前广泛应用于图像生成的一种方法。最近,XinleiChen、ZhuangLiu、谢赛宁和何恺明四人团队对DDM进行了解构研究。通过逐步剥离其组件,他们发现DDM的生成能力逐渐下降,但表征学习能力仍然保持一定水平。这说明DDM中的某些组件对于表征学习的作用可能并不重要。针对当前计算机视觉等领域的生成模型,去噪被认为是一种核心方法。这类方法通常被称为去噪扩散模型(DDM),通过学习一个去噪自动编码器(DAE),能够通过扩散过程有效地消除多个层级的噪声。这些方法实现了出色的图

See all articles

Hot AI Tools

Undresser.AI Undress

Undresser.AI Undress

AI-powered app for creating realistic nude photos

AI Clothes Remover

AI Clothes Remover

Online AI tool for removing clothes from photos.

Undress AI Tool

Undress AI Tool

Undress images for free

Clothoff.io

Clothoff.io

AI clothes remover

AI Hentai Generator

AI Hentai Generator

Generate AI Hentai for free.

Hot Article

R.E.P.O. Energy Crystals Explained and What They Do (Yellow Crystal)
2 weeks agoBy尊渡假赌尊渡假赌尊渡假赌
Repo: How To Revive Teammates
4 weeks agoBy尊渡假赌尊渡假赌尊渡假赌
Hello Kitty Island Adventure: How To Get Giant Seeds
4 weeks agoBy尊渡假赌尊渡假赌尊渡假赌

Hot Tools

DVWA

DVWA

Damn Vulnerable Web App (DVWA) is a PHP/MySQL web application that is very vulnerable. Its main goals are to be an aid for security professionals to test their skills and tools in a legal environment, to help web developers better understand the process of securing web applications, and to help teachers/students teach/learn in a classroom environment Web application security. The goal of DVWA is to practice some of the most common web vulnerabilities through a simple and straightforward interface, with varying degrees of difficulty. Please note that this software

PhpStorm Mac version

PhpStorm Mac version

The latest (2018.2.1) professional PHP integrated development tool

SublimeText3 Mac version

SublimeText3 Mac version

God-level code editing software (SublimeText3)

MinGW - Minimalist GNU for Windows

MinGW - Minimalist GNU for Windows

This project is in the process of being migrated to osdn.net/projects/mingw, you can continue to follow us there. MinGW: A native Windows port of the GNU Compiler Collection (GCC), freely distributable import libraries and header files for building native Windows applications; includes extensions to the MSVC runtime to support C99 functionality. All MinGW software can run on 64-bit Windows platforms.

ZendStudio 13.5.1 Mac

ZendStudio 13.5.1 Mac

Powerful PHP integrated development environment