# Anchoring to Exemplars for Training Mixture-of-Expert Cell Embeddings

arXiv: https://arxiv.org/abs/2112.03208 · HTML: https://mlsanity.com/paper/2112.03208/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Medical and biomedical MoE, one of 12 directions in Mixture-of-experts.
- Builds on 22 of its 43 references that are in the map.
- First posted on arXiv 6 Dec 2021.

## Placed in

- Mixture-of-experts / [Medical and biomedical MoE](https://mlsanity.com/moe/medical-and-biomedical-moe/)

## Builds on (most cited first, 22 of 22)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [Maximum Classifier Discrepancy for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1712.02560/) (2017)
- [Self-Challenging Improves Cross-Domain Generalization](https://mlsanity.com/paper/2007.02454/) (2020)
- [Sampling Matters in Deep Embedding Learning](https://mlsanity.com/paper/1706.07567/) (2017)
- [Towards Fairness in Visual Recognition: Effective Strategies for Bias Mitigation](https://mlsanity.com/paper/1911.11834/) (2019)
- [No Fuss Distance Metric Learning using Proxies](https://mlsanity.com/paper/1703.07464/) (2017)
- [Learning Deep Structure-Preserving Image-Text Embeddings](https://mlsanity.com/paper/1511.06078/) (2015)
- [Cross-Batch Memory for Embedding Learning](https://mlsanity.com/paper/1912.06798/) (2019)
- [ProxyNCA++: Revisiting and Revitalizing Proxy Neighborhood Component Analysis](https://mlsanity.com/paper/2004.01113/) (2020)
- [Learning Type-Aware Embeddings for Fashion Compatibility](https://mlsanity.com/paper/1803.09196/) (2018)
- [Conditional Image-Text Embedding Networks](https://mlsanity.com/paper/1711.08389/) (2017)
- [Fashion Outfit Complementary Item Retrieval](https://mlsanity.com/paper/1912.08967/) (2019)
- [Learning Similarity Conditions Without Explicit Supervision](https://mlsanity.com/paper/1908.08589/) (2019)
- [MULE: Multimodal Universal Language Embedding](https://mlsanity.com/paper/1909.03493/) (2019)
- [Contrastive Learning of Single-Cell Phenotypic Representations for Treatment Classification](https://mlsanity.com/paper/2103.16670/) (2021)
- [Effectively Leveraging Attributes for Visual Similarity](https://mlsanity.com/paper/2105.01695/) (2021)
- [Give me a hint! Navigating Image Databases using Human-in-the-loop Feedback](https://mlsanity.com/paper/1809.08714/) (2018)
- [Phenotypic Profiling of High Throughput Imaging Screens with Generic Deep Convolutional Features](https://mlsanity.com/paper/1903.06516/) (2019)

## Built on by (most cited first, 2 of 2)

- [Class-Guided Image-to-Image Diffusion: Cell Painting from Brightfield Images with Class Labels](https://mlsanity.com/paper/2303.08863/) (2023)
- [Morphological Profiling for Drug Discovery in the Era of Deep Learning](https://mlsanity.com/paper/2312.07899/) (2023)

## Abstract (arXiv)

Analyzing the morphology of cells in microscopy images can provide insights into the mechanism of compounds or the function of genes. Addressing this task requires methods that can not only extract biological information from the images, but also ignore technical variations, ie, changes in experimental procedure or differences between equipments used to collect microscopy images. We propose Treatment ExemplArs with Mixture-of-experts (TEAMs), an embedding learning approach that learns a set of experts that are specialized in capturing technical variations in our training set and then aggregates specialist's predictions at test time. Thus, TEAMs can learn powerful embeddings with less technical variation bias by minimizing the noise from every expert. To train our model, we leverage Treatment Exemplars that enable our approach to capture the distribution of the entire dataset in every minibatch while still fitting into GPU memory. We evaluate our approach on three datasets for tasks like drug discovery, boosting performance on identifying the true mechanism of action of cell treatments by 5.5-11% over the state-of-the-art.