arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2407.03243cs.CV
收藏

基于注意力驱动约束平衡的视觉定位

Visual Grounding with Attention-Driven Constraint Balancing

Illinois Institute of Technology(伊利诺伊理工学院);Microsoft(微软公司);Google DeepMind(谷歌DeepMind)

Weitai Kang, Luowei Zhou, Junyi Wu, Changchang Sun, Yan Yan

AI总结:

本文针对视觉定位任务中现有Transformer模型损失函数仅约束边界框回归而无法充分优化视觉-语言特征对齐的问题,提出注意力驱动约束平衡框架AttBalance,并在多个模型和基准上取得持续提升及新的最先进性能。

摘要:

与目标检测不同,视觉定位任务需要检测由复杂的自由形式语言所描述的对象。为了同时建模这种复杂的语义和视觉表示,最近的最先进研究采用基于Transformer的模型来融合来自两种模态的特征,并进一步引入各种模块来调制视觉特征,使其与语言表达对齐并消除不相关的冗余信息。然而,它们的损失函数仍然采用常见的目标检测损失,仅约束边界框回归输出,未能充分优化上述目标。为了解决这一问题,本文首先分析了基于Transformer模型的注意力机制。在此基础上,我们进一步提出了一种名为注意力驱动约束平衡(AttBalance)的新框架,以优化语言相关区域内视觉特征的行为。大量实验结果表明,我们的方法带来了显著的改进。具体而言,我们在四个不同基准上评估的五种不同模型上均取得了持续提升。此外,通过将我们的方法集成到QRNet中,我们获得了新的最先进性能。

英文摘要:

Unlike Object Detection, Visual Grounding task necessitates the detection of an object described by complex free-form language. To simultaneously model such complex semantic and visual representations, recent state-of-the-art studies adopt transformer-based models to fuse features from both modalities, further introducing various modules that modulate visual features to align with the language expressions and eliminate the irrelevant redundant information. However, their loss function, still adopting common Object Detection losses, solely governs the bounding box regression output, failing to fully optimize for the above objectives. To tackle this problem, in this paper, we first analyze the attention mechanisms of transformer-based models. Building upon this, we further propose a novel framework named Attention-Driven Constraint Balancing (AttBalance) to optimize the behavior of visual features within language-relevant regions. Extensive experimental results show that our method brings impressive improvements. Specifically, we achieve constant improvements over five different models evaluated on four different benchmarks. Moreover, we attain a new state-of-the-art performance by integrating our method into QRNet.

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。

↑