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 https://github.com/naver-ai/rdnet.

翻译：本文重新审视了密集连接卷积网络（DenseNets），并揭示了其在主流ResNet类架构之上被低估的有效性。我们认为，由于未优化的训练方法和传统设计元素未能充分展现其潜力，DenseNets的优势长期被忽视。我们的初步研究表明，通过拼接实现的密集连接具有强大性能，证明DenseNets能够通过革新与当代架构竞争。我们系统性地改进了次优组件——包括结构调整、模块重新设计以及改进的训练方案，在保持拼接捷径的同时扩展DenseNets的宽度并提升内存效率。采用简洁架构元素的模型最终超越了残差学习谱系中的关键架构：Swin Transformer、ConvNeXt和DeiT-III。此外，我们的模型在ImageNet-1K上展现出接近最先进的性能，与最新模型及下游任务（包括ADE20k语义分割、COCO目标检测/实例分割）相竞争。最后，我们通过实证分析揭示了拼接机制相较于加性捷径的优势，从而引导学界重新关注DenseNet式设计。代码已开源：https://github.com/naver-ai/rdnet。