This work introduces the RevSilo, the first reversible module for bidirectional multi-scale feature fusion. Like other reversible methods, RevSilo eliminates the need to store hidden activations by recomputing them. Existing reversible methods, however, do not apply to multi-scale feature fusion and are therefore not applicable to a large class of networks. Bidirectional multi-scale feature fusion promotes local and global coherence and has become a de facto design principle for networks targeting spatially sensitive tasks e.g. HRNet and EfficientDet. When paired with high-resolution inputs, these networks achieve state-of-the-art results across various computer vision tasks, but training them requires substantial accelerator memory for saving large, multi-resolution activations. These memory requirements cap network size and limit progress. Using reversible recomputation, the RevSilo alleviates memory issues while still operating across resolution scales. Stacking RevSilos, we create RevBiFPN, a fully reversible bidirectional feature pyramid network. For classification, RevBiFPN is competitive with networks such as EfficientNet while using up to 19.8x lesser training memory. When fine-tuned on COCO, RevBiFPN provides up to a 2.5% boost in AP over HRNet using fewer MACs and a 2.4x reduction in training-time memory.
翻译:这项工作引入了 RevSIlo, 这是用于双向多尺度特性聚合的第一个可逆模块 。 RevSIlo 与其他可逆的方法一样, RevSIlo 也消除了存储隐藏激活装置的需要。 但是, 现有的可逆方法并不适用于多尺度特性聚合, 因此不适用于大型网络。 双向多尺度特性聚合可以促进地方和全球的一致性, 并已成为针对空间敏感任务( 如, HRNet 和 高效 Det) 的网络的事实上设计原则。 当这些网络与高分辨率投入配对时, 这些网络可以在各种计算机视觉任务中实现最先进的结果, 但是培训它们需要大量的加速器存储器来保存大型、 多分辨率的激活。 这些存储器要求限制网络的大小并限制进步。 使用可逆的反向反馈, Revislo 减少记忆问题, 我们创建 RevBIFPN, 一个完全可逆双向双向的双向特征金字塔网络。 关于计算机不同计算机愿景的分类, ReviBIFN 需要大量的升级的网络, 使用智能培训, 将 IMFA