arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.11494cs.CV
收藏

通过下一个标记预测实现任意比例特征压缩

Arbitrary Ratio Feature Compression via Next Token Prediction

State Key Laboratory of Multimodal Artificial Intelligence Systems, Institution of Automation, Chinese Academy of Sciences(多模态人工智能系统国家重点实验室,自动化研究所,中国科学院);School of Artificial Intelligence, University of Chinese Academy of Sciences(中国科学院大学人工智能学院);CAS Center for Excellence in Brain Science and Intelligence Technology(中国科学院脑科学与智能技术卓越创新中心);People AI, Inc.(People AI公司);School of Artificial Intelligence, Shanghai Jiao Tong University(上海交通大学人工智能学院);School of Computer Science and Mathematics, Birkbeck College, University of London(伦敦大学伯克贝克学院计算机科学与数学学院)

Yufan Liu, Daoyuan Ren, Zhipeng Zhang, Wenyang Luo, Bing Li, Weiming Hu, Stephen Maybank

AI总结:

本文提出了一种通过下一个标记预测实现任意比例特征压缩的框架,解决了传统方法在灵活性和通用性上的不足,通过引入混合解决方案和实体关系图约束模块,提升了压缩特征的质量和鲁棒性。

摘要:

特征压缩在提高下游任务效率方面变得越来越重要,尤其是在涉及大规模或多模态数据的应用中。虽然现有方法通常依赖于专用模型来实现特定的压缩比,但它们在灵活性和通用性方面往往受到限制。特别是,当适应新的压缩比时需要重新训练。为了解决这一限制,我们提出了一种新颖且灵活的任意比例特征压缩(ARFC)框架,该框架支持任何压缩比,只需一个模型,从而消除了对多个专用模型的需要。在核心部分,任意比例压缩器(ARC)是一种自回归模型,通过下一个标记预测进行压缩。这允许在推理时通过调整生成的标记数量来控制压缩比。为了提高压缩特征的质量,引入了两个关键模块。混合解决方案(MoS)模块通过利用多个压缩结果(解决方案)来优化压缩标记,减少不确定性和提高鲁棒性。实体关系图约束(ERGC)被整合到训练过程中,以在压缩过程中保留语义和结构关系。在跨模态检索、图像分类和图像检索任务中,对多个数据集的广泛实验表明,我们的方法在各种压缩比下均优于现有方法。值得注意的是,在某些情况下,它甚至超过了原始未压缩特征的性能。这些结果验证了ARFC在实际资源受限场景中的有效性和通用性。

英文摘要:

Feature compression is increasingly important for improving the efficiency of downstream tasks, especially in applications involving large-scale or multi-modal data. While existing methods typically rely on dedicated models for achieving specific compression ratios, they are often limited in flexibility and generalization. In particular, retraining is necessary when adapting to a new compression ratio. To address this limitation, we propose a novel and flexible Arbitrary Ratio Feature Compression (ARFC) framework, which supports any compression ratio with a single model, eliminating the need for multiple specialized models. At its core, the Arbitrary Ratio Compressor (ARC) is an auto-regressive model that performs compression via next-token prediction. This allows the compression ratio to be controlled at inference simply by adjusting the number of generated tokens. To enhance the quality of the compressed features, two key modules are introduced. The Mixture of Solutions (MoS) module refines the compressed tokens by utilizing multiple compression results (solutions), reducing uncertainty and improving robustness. The Entity Relation Graph Constraint (ERGC) is integrated into the training process to preserve semantic and structural relationships during compression. Extensive experiments on cross-modal retrieval, image classification, and image retrieval tasks across multiple datasets demonstrate that our method consistently outperforms existing approaches at various compression ratios. Notably, in some cases, it even surpasses the performance of the original, uncompressed features. These results validate the effectiveness and versatility of ARFC for practical, resource-constrained scenarios.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑