This paper revives Densely Connected Convolutional Networks (DenseNets) and
reveals the underrated effectiveness over predominant ResNet-style
architectures. We believe DenseNets' potential was overlooked due to untouched
training methods and traditional design elements not fully revealing their
capabilities. Our pilot study shows dense connections through concatenation are
strong, demonstrating that DenseNets can be revitalized to compete with modern
architectures. We methodically refine suboptimal components - architectural
adjustments, block redesign, and improved training recipes towards widening
DenseNets and boosting memory efficiency while keeping concatenation shortcuts.
Our models, employing simple architectural elements, ultimately surpass Swin
Transformer, ConvNeXt, and DeiT-III - key architectures in the residual
learning lineage. Furthermore, our models exhibit near state-of-the-art
performance on ImageNet-1K, competing with the very recent models and
downstream tasks, ADE20k semantic segmentation, and COCO object
detection/instance segmentation. Finally, we provide empirical analyses that
uncover the merits of the concatenation over additive shortcuts, steering a
renewed preference towards DenseNet-style designs. Our code is available at
this https URL

在这篇论文中，我们研究了密集连接卷积网络（DenseNets）的效果，并发现其在流行的 ResNet 风格架构中被低估。我们通过串联密集连接的方式展示了 DenseNets 的优势，并且进行了架构调整、块重设计和改进训练方法以提高 DenseNets 的性能和内存效率。我们的模型不仅超越了 Swin Transformer、ConvNeXt 和 DeiT-III 等关键架构，还在 ImageNet-1K 等领域展现了接近最新模型的性能，包括 ADE20k 语义分割和 COCO 目标检测 / 实例分割任务。最后，我们提供了以经验为基础的分析结果，揭示了串联连接胜过加法连接的优点，从而引导人们重新偏好 DenseNet 风格的设计。