---
title: "Densely Connected Convolutional Networks"
description: "DenseNet keeps earlier feature maps available by concatenating them and asks each layer to add a small new contribution. Follow channel growth and compressed transitions, then separate the paper’s parameter-efficiency evidence from the activation-memory cost of a naive implementation."
canonical_url: "https://fanout.sh/daily/2026-10-21-densenet-feature-reuse"
md_url: "https://fanout.sh/daily/2026-10-21-densenet-feature-reuse.md"
last_updated: "2026-10-21"
access: "public"
---

# Densely Connected Convolutional Networks

DenseNet keeps earlier feature maps available by concatenating them and asks each layer to add a small new contribution. Follow channel growth and compressed transitions, then separate the paper’s parameter-efficiency evidence from the activation-memory cost of a naive implementation.

## Paper details

- Authors: Gao Huang, Zhuang Liu, Laurens van der Maaten, and Kilian Q. Weinberger

- Venue: CVPR 2017

- Track: AI Research

- Difficulty: Easy

- Reading time: 11 min

- Original paper: https://arxiv.org/abs/1608.06993v5

## What you will learn

- How concatenation preserves earlier maps as separate channels while a growth rate limits each new contribution.

- Why fixed-resolution dense blocks need channel projections and pooling at their boundaries.

- What the parameter comparison establishes and why it does not guarantee low peak memory or latency.

## Continue exploring

[Start with residual connections](https://fanout.sh/daily/2026-07-09-resnet): Review residual addition before comparing it with DenseNet’s channel concatenation.

---
This representation contains public Fanout content only. Protected Pro lessons, account data, billing, checkout, and pricing are not included.

Browse the public content map: https://fanout.sh/sitemap.md