# Convolutional Networks with Dense Connectivity

arXiv: https://arxiv.org/abs/2001.02394 · HTML: https://mlsanity.com/paper/2001.02394/

## Key facts

- Cited by 98 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Jan 2020.

## Built on by (most cited first, 30 of 98)

- [Target-aware Dual Adversarial Learning and a Multi-scenario Multi-Modality Benchmark to Fuse Infrared and Visible for Object Detection](https://mlsanity.com/paper/2203.16220/) (2022)
- [Vision Transformer with Deformable Attention](https://mlsanity.com/paper/2201.00520/) (2022)
- [Not All Images are Worth 16x16 Words: Dynamic Transformers for Efficient Image Recognition](https://mlsanity.com/paper/2105.15075/) (2021)
- [Domain Adaptation via Prompt Learning](https://mlsanity.com/paper/2202.06687/) (2022)
- [Vision-Language Models for Medical Report Generation and Visual Question Answering: A Review](https://mlsanity.com/paper/2403.02469/) (2024)
- [Federated Learning for Generalization, Robustness, Fairness: A Survey and Benchmark](https://mlsanity.com/paper/2311.06750/) (2023)
- [P2T: Pyramid Pooling Transformer for Scene Understanding](https://mlsanity.com/paper/2106.12011/) (2021)
- [Adaptive Focus for Efficient Video Recognition](https://mlsanity.com/paper/2105.03245/) (2021)
- [On the Integration of Self-Attention and Convolution](https://mlsanity.com/paper/2111.14556/) (2021)
- [Revisiting Locally Supervised Learning: an Alternative to End-to-end Training](https://mlsanity.com/paper/2101.10832/) (2021)
- [Multi-Scale VMamba: Hierarchy in Hierarchy Visual State Space Model](https://mlsanity.com/paper/2405.14174/) (2024)
- [Gradient Norm Aware Minimization Seeks First-Order Flatness and Improves Generalization](https://mlsanity.com/paper/2303.03108/) (2023)
- [EfficientTrain: Exploring Generalized Curriculum Learning for Training Visual Backbones](https://mlsanity.com/paper/2211.09703/) (2022)
- [Glance and Focus Networks for Dynamic Visual Recognition](https://mlsanity.com/paper/2201.03014/) (2022)
- [AdaFocus V2: End-to-End Training of Spatial Dynamic Networks for Video Recognition](https://mlsanity.com/paper/2112.14238/) (2021)
- [Single Image Depth Prediction with Wavelet Decomposition](https://mlsanity.com/paper/2106.02022/) (2021)
- [Sketching Curvature for Efficient Out-of-Distribution Detection for Deep Neural Networks](https://mlsanity.com/paper/2102.12567/) (2021)
- [AdvHaze: Adversarial Haze Attack](https://mlsanity.com/paper/2104.13673/) (2021)
- [VSSD: Vision Mamba with Non-Causal State Space Duality](https://mlsanity.com/paper/2407.18559/) (2024)
- [Latency-aware Unified Dynamic Networks for Efficient Image Recognition](https://mlsanity.com/paper/2308.15949/) (2023)
- [Monocular Depth Estimation through Virtual-world Supervision and Real-world SfM Self-Supervision](https://mlsanity.com/paper/2103.12209/) (2021)
- [Generalized Domain Conditioned Adaptation Network](https://mlsanity.com/paper/2103.12339/) (2021)
- [UDIS: Unsupervised Discovery of Bias in Deep Visual Recognition Models](https://mlsanity.com/paper/2110.15499/) (2021)
- [Out-of-Distribution Detection with Semantic Mismatch under Masking](https://mlsanity.com/paper/2208.00446/) (2022)
- [DAT++: Spatially Dynamic Vision Transformer with Deformable Attention](https://mlsanity.com/paper/2309.01430/) (2023)
- [Flexible Job Shop Scheduling via Dual Attention Network Based Reinforcement Learning](https://mlsanity.com/paper/2305.05119/) (2023)
- [EfficientTrain++: Generalized Curriculum Learning for Efficient Visual Backbone Training](https://mlsanity.com/paper/2405.08768/) (2024)
- [VDN-NeRF: Resolving Shape-Radiance Ambiguity via View-Dependence Normalization](https://mlsanity.com/paper/2303.17968/) (2023)
- [A Simple Interpretable Transformer for Fine-Grained Image Classification and Analysis](https://mlsanity.com/paper/2311.04157/) (2023)
- [Multi-domain semantic segmentation with overlapping labels](https://mlsanity.com/paper/2108.11224/) (2021)

## Abstract (arXiv)

Recent work has shown that convolutional networks can be substantially deeper, more accurate, and efficient to train if they contain shorter connections between layers close to the input and those close to the output. In this paper, we embrace this observation and introduce the Dense Convolutional Network (DenseNet), which connects each layer to every other layer in a feed-forward fashion.Whereas traditional convolutional networks with L layers have L connections - one between each layer and its subsequent layer - our network has L(L+1)/2 direct connections. For each layer, the feature-maps of all preceding layers are used as inputs, and its own feature-maps are used as inputs into all subsequent layers. DenseNets have several compelling advantages: they alleviate the vanishing-gradient problem, encourage feature reuse and substantially improve parameter efficiency. We evaluate our proposed architecture on four highly competitive object recognition benchmark tasks (CIFAR-10, CIFAR-100, SVHN, and ImageNet). DenseNets obtain significant improvements over the state-of-the-art on most of them, whilst requiring less parameters and computation to achieve high performance.