# RepMode: Learning to Re-parameterize Diverse Experts for Subcellular Structure Prediction

arXiv: https://arxiv.org/abs/2212.10066 · HTML: https://mlsanity.com/paper/2212.10066/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 44 of its 75 references that are in the map.
- First posted on arXiv 20 Dec 2022.

## Builds on (most cited first, 30 of 44)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [YOLOv3: An Incremental Improvement](https://mlsanity.com/paper/1804.02767/) (2018)
- [Pyramid Scene Parsing Network](https://mlsanity.com/paper/1612.01105/) (2016)
- [Rethinking Atrous Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1706.05587/) (2017)
- [Deep High-Resolution Representation Learning for Human Pose Estimation](https://mlsanity.com/paper/1902.09212/) (2019)
- [Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks](https://mlsanity.com/paper/1604.02878/) (2016)
- [Path Aggregation Network for Instance Segmentation](https://mlsanity.com/paper/1803.01534/) (2018)
- [Scaling Vision with Sparse Mixture of Experts](https://mlsanity.com/paper/2106.05974/) (2021)
- [Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition](https://mlsanity.com/paper/1406.4729/) (2014)
- [Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks](https://mlsanity.com/paper/1602.07868/) (2016)
- [RepVGG: Making VGG-style ConvNets Great Again](https://mlsanity.com/paper/2101.03697/) (2021)
- [Selective Kernel Networks](https://mlsanity.com/paper/1903.06586/) (2019)
- [Dynamic Convolution: Attention over Convolution Kernels](https://mlsanity.com/paper/1912.03458/) (2019)
- [nnU-Net: Self-adapting Framework for U-Net-Based Medical Image Segmentation](https://mlsanity.com/paper/1809.10486/) (2018)
- [CondConv: Conditionally Parameterized Convolutions for Efficient Inference](https://mlsanity.com/paper/1904.04971/) (2019)
- [Unified Scaling Laws for Routed Language Models](https://mlsanity.com/paper/2202.01169/) (2022)
- [ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blocks](https://mlsanity.com/paper/1908.03930/) (2019)
- [Scale-Aware Trident Networks for Object Detection](https://mlsanity.com/paper/1901.01892/) (2019)
- [DEMix Layers: Disentangling Domains for Modular Language Modeling](https://mlsanity.com/paper/2108.05036/) (2021)
- [DSelect-k: Differentiable Selection in the Mixture of Experts with Applications to Multi-Task Learning](https://mlsanity.com/paper/2106.03760/) (2021)
- [DoDNet: Learning to segment multi-organ and tumors from multiple partially labeled datasets](https://mlsanity.com/paper/2011.10217/) (2020)
- [Diverse Branch Block: Building a Convolution as an Inception-like Unit](https://mlsanity.com/paper/2103.13425/) (2021)
- [Implicit Reparameterization Gradients](https://mlsanity.com/paper/1805.08498/) (2018)
- [Generalizable Person Re-identification with Relevance-aware Mixture of Experts](https://mlsanity.com/paper/2105.09156/) (2021)

## Built on by (most cited first, 3 of 3)

- [FFNet: MetaMixer-based Efficient Convolutional Mixer Design](https://mlsanity.com/paper/2406.02021/) (2024)
- [SparseSSP: 3D Subcellular Structure Prediction from Sparse-View Transmitted Light Images](https://mlsanity.com/paper/2407.02159/) (2024)
- [Foreground-aware Virtual Staining for Accurate 3D Cell Morphological Profiling](https://mlsanity.com/paper/2507.05383/) (2025)

## Abstract (arXiv)

In biological research, fluorescence staining is a key technique to reveal the locations and morphology of subcellular structures. However, it is slow, expensive, and harmful to cells. In this paper, we model it as a deep learning task termed subcellular structure prediction (SSP), aiming to predict the 3D fluorescent images of multiple subcellular structures from a 3D transmitted-light image. Unfortunately, due to the limitations of current biotechnology, each image is partially labeled in SSP. Besides, naturally, subcellular structures vary considerably in size, which causes the multi-scale issue of SSP. To overcome these challenges, we propose Re-parameterizing Mixture-of-Diverse-Experts (RepMode), a network that dynamically organizes its parameters with task-aware priors to handle specified single-label prediction tasks. In RepMode, the Mixture-of-Diverse-Experts (MoDE) block is designed to learn the generalized parameters for all tasks, and gating re-parameterization (GatRep) is performed to generate the specialized parameters for each task, by which RepMode can maintain a compact practical topology exactly like a plain network, and meanwhile achieves a powerful theoretical topology. Comprehensive experiments show that RepMode can achieve state-of-the-art overall performance in SSP.