# Unified Kernel-Segregated Transpose Convolution Operation

arXiv: https://arxiv.org/abs/2502.20493 · HTML: https://mlsanity.com/paper/2502.20493/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 26 references that are in the map.
- First posted on arXiv 27 Feb 2025.

## Builds on (most cited first, 15 of 15)

- [Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks](https://mlsanity.com/paper/1511.06434/) (2015)
- [Multi-Scale Context Aggregation by Dilated Convolutions](https://mlsanity.com/paper/1511.07122/) (2015)
- [Learning to Discover Cross-Domain Relations with Generative Adversarial Networks](https://mlsanity.com/paper/1703.05192/) (2017)
- [The Computational Limits of Deep Learning](https://mlsanity.com/paper/2007.05558/) (2020)
- [Efficient Deep Learning: A Survey on Making Deep Learning Models Smaller, Faster, and Better](https://mlsanity.com/paper/2106.08962/) (2021)
- [Energy-based Generative Adversarial Network](https://mlsanity.com/paper/1609.03126/) (2016)
- [GP-GAN: Towards Realistic High-Resolution Image Blending](https://mlsanity.com/paper/1703.07195/) (2017)
- [Parallel Multi Channel Convolution using General Matrix Multiplication](https://mlsanity.com/paper/1704.04428/) (2017)
- [A Comprehensive Survey on Data-Efficient GANs in Image Generation](https://mlsanity.com/paper/2204.08329/) (2022)
- [ArtGAN: Artwork Synthesis with Conditional Categorical GANs](https://mlsanity.com/paper/1702.03410/) (2017)
- [Universal Spam Detection using Transfer Learning of BERT Model](https://mlsanity.com/paper/2202.03480/) (2022)
- [GANAX: A Unified MIMD-SIMD Acceleration for Generative Adversarial Networks](https://mlsanity.com/paper/1806.01107/) (2018)
- [The Effects of Approximate Multiplication on Convolutional Neural Networks](https://mlsanity.com/paper/2007.10500/) (2020)
- [Privacy-Preserving Deep Learning Model for Covid-19 Disease Detection](https://mlsanity.com/paper/2209.04445/) (2022)
- [Kernel-Segregated Transpose Convolution Operation](https://mlsanity.com/paper/2209.03704/) (2022)

## Abstract (arXiv)

The optimization of the transpose convolution layer for deep learning applications is achieved with the kernel segregation mechanism. However, kernel segregation has disadvantages, such as computing extra elements to obtain the output feature map with odd dimensions while launching a thread. To mitigate this problem, we introduce a unified kernel segregation approach that limits the usage of memory and computational resources by employing one unified kernel to execute four sub-kernels. The findings reveal that the suggested approach achieves an average computational speedup of 2.03x (3.89x) when tested on specific datasets with an RTX 2070 GPU (Intel Xeon CPU). The ablation study shows an average computational speedup of 3.5x when evaluating the transpose convolution layers from well-known Generative Adversarial Networks (GANs). The implementation of the proposed method for the transpose convolution layers in the EB-GAN model demonstrates significant memory savings of up to 35 MB.