Make Your Training Flexible: Towards Deployment-Efficient Video Models

• URL: http://arxiv.org/abs/2503.14237v1
• Date: Tue, 18 Mar 2025 13:15:58 GMT
• Title: Make Your Training Flexible: Towards Deployment-Efficient Video Models
• Authors: Chenting Wang, Kunchang Li, Tianxiang Jiang, Xiangyu Zeng, Yi Wang, Limin Wang,
• Abstract summary: We propose a new test setting, Token Optimization, for maximized input information across budgets.<n>By making the sampling grid flexible and leveraging token selection, it is easily adopted in most popular video training frameworks.<n>We integrate Flux in large-scale video pre-training, and the resulting FluxViT establishes new state-of-the-art results across extensive tasks at standard costs.
• Score: 22.727848052298427
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Popular video training methods mainly operate on a fixed number of tokens sampled from a predetermined spatiotemporal grid, resulting in sub-optimal accuracy-computation trade-offs due to inherent video redundancy. They also lack adaptability to varying computational budgets for downstream tasks, hindering applications of the most competitive model in real-world scenes. We thus propose a new test setting, Token Optimization, for maximized input information across budgets, which optimizes the size-limited set of input tokens through token selection from more suitably sampled videos. To this end, we propose a novel augmentation tool termed Flux. By making the sampling grid flexible and leveraging token selection, it is easily adopted in most popular video training frameworks, boosting model robustness with nearly no additional cost. We integrate Flux in large-scale video pre-training, and the resulting FluxViT establishes new state-of-the-art results across extensive tasks at standard costs. Notably, with 1/4 tokens only, it can still match the performance of previous state-of-the-art models with Token Optimization, yielding nearly 90\% savings. All models and data are available at https://github.com/OpenGVLab/FluxViT.

Related papers

• Temporal In-Context Fine-Tuning for Versatile Control of Video Diffusion Models [34.131515004434846]
  We introduce Temporal In-Context Fine-Tuning (TIC-FT), an efficient approach for adapting pretrained video diffusion models to conditional generation tasks.<n>TIC-FT requires no architectural changes and achieves strong performance with as few as 10-30 training samples.<n>We validate our method across a range of tasks, including image-to-video and video-to-video generation, using large-scale base models such as CogVideoX-5B and Wan-14B.
  arXiv  Detail & Related papers  (2025-06-01T12:57:43Z)
• Learning Adaptive and Temporally Causal Video Tokenization in a 1D Latent Space [84.22182151122598]
  AdapTok is an adaptive temporal causal video tokenizer that can flexibly allocate tokens for different frames based on video content.<n>AdapTok consistently improves reconstruction quality and generation performance under different token budgets.
  arXiv  Detail & Related papers  (2025-05-22T17:59:02Z)
• Learning from Streaming Video with Orthogonal Gradients [62.51504086522027]
  We address the challenge of representation learning from a continuous stream of video as input, in a self-supervised manner. This differs from the standard approaches to video learning where videos are chopped and shuffled during training in order to create a non-redundant batch. We demonstrate the drop in performance when moving from shuffled to sequential learning on three tasks.
  arXiv  Detail & Related papers  (2025-04-02T17:59:57Z)
• Stable Virtual Camera: Generative View Synthesis with Diffusion Models [67.33643698669209]
  We present Stable Virtual Camera (Seva), a generalist diffusion model that creates novel views of a scene.<n>Our approach overcomes these limitations through simple model design, optimized training recipe, and flexible sampling strategy.<n>Our method can generate high-quality videos lasting up to half a minute with seamless loop closure.
  arXiv  Detail & Related papers  (2025-03-18T17:57:22Z)
• Free Video-LLM: Prompt-guided Visual Perception for Efficient Training-free Video LLMs [56.040198387038025]
  We present a novel prompt-guided visual perception framework (abbreviated as Free Video-LLM) for efficient inference of training-free video LLMs. Our method effectively reduces the number of visual tokens while maintaining high performance across multiple video question-answering benchmarks.
  arXiv  Detail & Related papers  (2024-10-14T12:35:12Z)
• Get more for less: Principled Data Selection for Warming Up Fine-Tuning in LLMs [18.242110417706]
  This work focuses on leveraging and selecting from vast, unlabeled, open data to pre-fine-tune a pre-trained language model. We show the optimality of this approach for fine-tuning tasks under certain conditions. Our proposed method is significantly faster than existing techniques, scaling to millions of samples within a single GPU hour.
  arXiv  Detail & Related papers  (2024-05-05T00:08:00Z)
• Getting the most out of your tokenizer for pre-training and domain adaptation [26.427537023771844]
  We show that the size, pre-tokenization regular expression, and training data of a tokenizer can significantly impact the model's generation speed. We specialize the tokenizer of a pre-trained LLM to obtain large gains in generation speed and effective context size.
  arXiv  Detail & Related papers  (2024-02-01T21:49:34Z)
• Towards Free Data Selection with General-Purpose Models [71.92151210413374]
  A desirable data selection algorithm can efficiently choose the most informative samples to maximize the utility of limited annotation budgets. Current approaches, represented by active learning methods, typically follow a cumbersome pipeline that iterates the time-consuming model training and batch data selection repeatedly. FreeSel bypasses the heavy batch selection process, achieving a significant improvement in efficiency and being 530x faster than existing active learning methods.
  arXiv  Detail & Related papers  (2023-09-29T15:50:14Z)
• eP-ALM: Efficient Perceptual Augmentation of Language Models [70.47962271121389]
  We propose to direct effort to efficient adaptations of existing models, and propose to augment Language Models with perception. Existing approaches for adapting pretrained models for vision-language tasks still rely on several key components that hinder their efficiency. We show that by freezing more than 99% of total parameters, training only one linear projection layer, and prepending only one trainable token, our approach (dubbed eP-ALM) significantly outperforms other baselines on VQA and Captioning.
  arXiv  Detail & Related papers  (2023-03-20T19:20:34Z)
• Efficient Meta-Tuning for Content-aware Neural Video Delivery [40.3731358963689]
  We present Efficient Meta-Tuning (EMT) to reduce the computational cost. EMT adapts a meta-learned model to the first chunk of the input video. We propose a novel sampling strategy to extract the most challenging patches from video frames.
  arXiv  Detail & Related papers  (2022-07-20T06:47:10Z)
• ViViT: A Video Vision Transformer [75.74690759089529]
  We present pure-transformer based models for video classification. Our model extracts-temporal tokens from the input video, which are then encoded by a series of transformer layers. We show how we can effectively regularise the model during training and leverage pretrained image models to be able to train on comparatively small datasets.
  arXiv  Detail & Related papers  (2021-03-29T15:27:17Z)
• Scene-Adaptive Video Frame Interpolation via Meta-Learning [54.87696619177496]
  We propose to adapt the model to each video by making use of additional information that is readily available at test time. We obtain significant performance gains with only a single gradient update without any additional parameters.
  arXiv  Detail & Related papers  (2020-04-02T02:46:44Z)

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.