魔鬼在于一致性：探索Transformer中用于图像恢复的多样学习器
Devil is in the Uniformity: Exploring Diverse Learners within Transformer for Image Restoration
AI总结：
针对Transformer多头注意力的冗余问题，提出HINT模型，通过分层多头注意力和查询-键缓存更新探索多样学习器与头间交互，在5个图像恢复任务的12个基准上验证了优越性。
摘要：
基于Transformer的方法在图像恢复领域引起了广泛关注，其核心组件多头注意力（MHA）在捕获多样特征和恢复高质量结果方面发挥着关键作用。在MHA中，各个头从均匀分割的子空间中独立执行注意力计算，由此引发冗余问题，阻碍模型获得令人满意的输出。本文提出通过探索多样学习器并引入头之间的各种交互来改进MHA，由此产生一种用于图像恢复的分层多头注意力驱动的Transformer模型，称为HINT。HINT包含两个模块，即分层多头注意力（HMHA）和查询-键缓存更新（QKCU）模块，以解决源于原始MHA的冗余问题。具体而言，HMHA通过让各个头从大小不同且包含不同信息的子空间中学习来提取多样的上下文特征。此外，QKCU包含层内和层间方案，通过促进层内和层间注意力头之间增强的交互，进一步减少冗余问题。在5个图像恢复任务（包括低光增强、去雾、去雪、去噪和去雨）的12个基准上进行了大量实验，以证明HINT的优越性。源代码可在补充材料中获取。
英文摘要：
Transformer-based approaches have gained significant attention in image restoration, where the core component, i.e, Multi-Head Attention (MHA), plays a crucial role in capturing diverse features and recovering high-quality results. In MHA, heads perform attention calculation independently from uniform split subspaces, and a redundancy issue is triggered to hinder the model from achieving satisfactory outputs. In this paper, we propose to improve MHA by exploring diverse learners and introducing various interactions between heads, which results in a Hierarchical multI-head atteNtion driven Transformer model, termed HINT, for image restoration. HINT contains two modules, i.e., the Hierarchical Multi-Head Attention (HMHA) and the Query-Key Cache Updating (QKCU) module, to address the redundancy problem that is rooted in vanilla MHA. Specifically, HMHA extracts diverse contextual features by employing heads to learn from subspaces of varying sizes and containing different information. Moreover, QKCU, comprising intra- and inter-layer schemes, further reduces the redundancy problem by facilitating enhanced interactions between attention heads within and across layers. Extensive experiments are conducted on 12 benchmarks across 5 image restoration tasks, including low-light enhancement, dehazing, desnowing, denoising, and deraining, to demonstrate the superiority of HINT. The source code is available in the supplementary materials.
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。
