mlsanityData to 7 Oct 2026

CHAMMI: A benchmark for channel-adaptive models in microscopy imaging

arXiv 2310.19224 ↗First posted 30 Oct 2023cs.CVcited by 18

Not on the map. Why?

Abstract (arXiv)

Most neural networks assume that input images have a fixed number of channels (three for RGB images). However, there are many settings where the number of channels may vary, such as microscopy images where the number of channels changes depending on instruments and experimental goals. Yet, there has not been a systemic attempt to create and evaluate neural networks that are invariant to the number and type of channels. As a result, trained models remain specific to individual studies and are hardly reusable for other microscopy settings. In this paper, we present a benchmark for investigating channel-adaptive models in microscopy imaging, which consists of 1) a dataset of varied-channel single-cell images, and 2) a biologically relevant evaluation framework. In addition, we adapted several existing techniques to create channel-adaptive models and compared their performance on this benchmark to fixed-channel, baseline models. We find that channel-adaptive models can generalize better to out-of-domain tasks and can be computationally efficient. We contribute a curated dataset (https://doi.org/10.5281/zenodo.7988357) and an evaluation API (https://github.com/broadinstitute/MorphEm.git) to facilitate objective comparisons in future research and applications.

Key facts. Cited by 18 papers in the map (data through 7 Oct 2026). Builds on 33 of its 77 references that are in the map. First posted on arXiv 30 Oct 2023.

Builds on

33 of 77 references.

References · 33

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  4. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  5. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  6. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  7. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  8. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  9. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  10. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,827
  11. 2022A ConvNet for the 2020scited by 3,545
  12. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,540
21 more
  1. 2017Deep Setscited by 1,394
  2. 2020Big Self-Supervised Models are Strong Semi-Supervised Learnerscited by 1,375
  3. 2018Datasheets for Datasetscited by 1,371
  4. 2014Two-Stream Convolutional Networks for Action Recognition in Videoscited by 1,067
  5. 2019Unsupervised Data Augmentation for Consistency Trainingcited by 1,057
  6. 2016HyperNetworkscited by 1,003
  7. 2021Generalizing to Unseen Domains: A Survey on Domain Generalizationcited by 762
  8. 2021Domain Generalization: A Surveycited by 760
  9. 2021SWAD: Domain Generalization by Seeking Flat Minimacited by 431
  10. 2023Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistlescited by 287
  11. 2019PointNetLK: Robust & Efficient Point Cloud Registration using PointNetcited by 231
  12. 2022All in One: Exploring Unified Video-Language Pre-trainingcited by 171
  13. 2022Domain Generalization by Mutual-Information Regularization with Pre-trained Modelscited by 133
  14. 2020ProxyNCA++: Revisiting and Revitalizing Proxy Neighborhood Component Analysiscited by 107
  15. 2023HNeRV: A Hybrid Neural Representation for Videoscited by 100
  16. 2022Harnessing Out-Of-Distribution Examples via Augmenting Content and Stylecited by 43
  17. 2019Learning Implicitly Recurrent CNNs Through Parameter Sharingcited by 27
  18. 2020Neural Parameter Allocation Searchcited by 15
  19. 2023Hierarchical discriminative learning improves visual representations of biomedical microscopycited by 12
  20. 2021CytoImageNet: A large-scale pretraining dataset for bioimage transfer learningcited by 7
  21. 2023Out of Distribution Generalization via Interventional Style Transfer in Single-Cell Microscopycited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 1; 2025: 7; 2026: 9.

18 papers.

Sort:

By area:

  1. 2024Enhancing Feature Diversity Boosts Channel-Adaptive Vision Transformerscited by 10
  2. 2025ChA-MAEViT: Unifying Channel-Aware Masked Autoencoders and Multi-Channel Vision Transformers for Improved Cross-Channel Learningcited by 6
  3. 2025Isolated Channel Vision Transformers: From Single-Channel Pretraining to Multi-Channel Finetuningcited by 5
  4. 2025Unsupervised Detection of Distribution Shift in Inverse Problems using Diffusion Modelscited by 4
  5. 2025Noise-Aware Generalization: Robustness to In-Domain Noise and Out-of-Domain Generalizationcited by 2
  6. 2025Integrating chemical structures as treatments improves representations of microscopy images for morphological profilingcited by 2
  7. 2025C3R: Channel Conditioned Cell Representations for unified evaluation in microscopy imagingcited by 2
  8. 2025CHAMMI-75: Pre-training multi-channel models with heterogeneous microscopy imagescited by 1
  9. 2026Generalization of Self-Supervised Vision Transformers for Protein Localization Across Microscopy Domainscited by 1
  10. 2026DC-ViT: Modulating Spatial and Channel Interactions for Multi-Channel Imagescited by 1
  11. 2026Spectral Property-Driven Data Augmentation for Hyperspectral Single-Source Domain Generalizationcited by 1
  12. 2023A Unified Framework for Connecting Noise Modeling to Boost Noise Detectioncited by 0
6 more
  1. 2026Channel-Aware Probing for Multi-Channel Imagingcited by 0
  2. 2026Deep Learning for BioImaging: What Are We Really Learning?cited by 0
  3. 2026Using Deep Learning Models Pretrained by Self-Supervised Learning for Protein Localizationcited by 0
  4. 2026MorphoHELM: A Comprehensive Benchmark for Evaluating Representations for Microscopy-Based Morphology Assayscited by 0
  5. 2026JUMP-lite: Compact, reproducible benchmarking of cell representationscited by 0
  6. 2026Extending Decoupled Attention to Dense Prediction and Masked Training for Multi-Channel Imagescited by 0