# Towards Deeper Generative Architectures for GANs using Dense connections

Source: [Towards Deeper Generative Architectures for GANs using Dense connections](<https://www.sota2.com/research/paper/68fa65151e209131cea08220>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T21:17:53.140Z

Authors: Samarth Tripathi, Renbo Tu

Published: 2018-04-30T02:45:12.000Z

## Abstract

In this paper, we present the result of adopting skip connections and dense layers, previously used in image classification tasks, in the Fisher GAN implementation. We have experimented with different numbers of layers and inserting these connections in different sections of the network. Our findings suggests that networks implemented with the connections produce better images than the baseline, and the number of connections added has only slight effect on the result.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1804.11031>)

[PDF](<https://arxiv.org/pdf/1804.11031.pdf>)