#CellSeg3D hits 85K downloads, and we’ve updated our preprint to add a few more key details and added new demo videos 🎥! Check out the demos from @AChRD4 and @SebHausmann 🔥 https://t.co/bErlPNrB8e https://t.co/RRSLiPTITF https://t.co/P12USdgQ9S

🎉 new preprint posted of potential interest, lead by talented masters student @AChRD4: 🔥fully unsupervised 3D cell segmentation that is as good (or better) than leading supervised methods, with @napari_imaging integration! 👏 https://t.co/ekFfgxcm46 ➕new 3D GT dataset ⬇️🧵

🦓🦓🦓 #CEBRA is out 🎉🎉🎉 Check out the @Nature paper ⬇️ & the gorgeous code & resources built by current members @stes_io @BenquetCelia @TrackingActions @EPFL_en @epflSV 📚 how to use: https://t.co/Hihxng6lzh 💻 install: https://t.co/sQ681FrdZa 📖 https://t.co/GqvIxgWL44

Image cropping is an efficient and yet often underestimated strategy against big-data problems 🍌🖥️🚀

🐁🐘🐿🔥SuperAnimals for #Pose -No human labeling - Video analysis on over 45 species with only 2 global classes of animal pose models -If SA needs fine-tuning, its 10× more data efficient & 2X outperforms prior transfer learning 📝@shaokaiyeah et al https://t.co/s3RdKKvcrn 🧵⬇️

Join us in celebrating #ImagingTheFuture Week! If you’re an imaging scientist, share your favorite picture from an imaging project you enjoyed working on👇🏽

👀 it’s an exciting day! We released the first release candidate for 2.3 🔥 - a whole new GUI awaits you, and we await your feedback! - Welcome to the world, our first full @napari_imaging + PySide2 product! https://t.co/SdRTkH1wBf

Fantastic day at @CampusBiotech to celebrate our new EPFL Neuro-X institute! Introduction by @MartinVetterli , followed by inspiring talks by J Rogers, T Denison, J Lee, R McIntosh, T Makin, @Jocelyne_Bloch & @gcourtine. @EPFL_en @EPFLEngineering @ICepfl @epflSV

🔥New #selfsupervised contrastive learning algorithm samples both discrete & continuous time series data, without any data augmentation needed, and leverages aux. variables — check out #cebra, which outperforms umap, tSNE, & piVAE on synthetic benchmarks.

Turns out loading models from the hub (or any other place) is ⚠️ NOT SAFE ⚠️ and opens you up to arbitrary code execution by an attacker🤯 Learn how to do it yourself (and how to protect against it) in this video: https://t.co/mbcXbHKMxJ

So many new labs starting this fall👏✨ #newPI pro tip: whatever time, money, and effort you invest in solid data management pipelines and git controlled code is worth it. When I started 5 years ago (today), it was a priority and it’s so, so worth it. #BetterCodeBetterResearch

🎉 #DLCAIResidencyWeek - @scientistjonas🦇 Jonas has been hard at work extending the @napari_imaging-DLC GUI to include multi-cam labeling, & testing how to make robust models with unbalanced data (🦇 flying left->right). 📚how he solves it: #DLCBlog 🔥 https://t.co/1SYunBI2Lb

🎉 #DLCAIResidency - @Nirelkadzo & #teamMegaDLC 🔥 The team hooked up 💚MegaDetector+DeepLabCut 💜 and deployed it on 🤗! 📚 Read about it in the #cookbook: https://t.co/G6cuRvBTRy 𐂐 And hey, it's live, go test it out! @huggingface App 🤗: https://t.co/72VCTwaevK

And, a new release is out too :) including: - layer inf. feature request from @haesleinhuepf ✅ - very powerful transformer model for 3D segmentation @vmaxmc2 ✅ https://t.co/0ghwZZLdyE