iiinova — where your digital self keeps evolving

TimDarcet @timdarcet.bsky.social · 14/02/2025

Want strong SSL, but not the complexity of DINOv2? CAPI: Cluster and Predict Latents Patches for Improved Masked Image Modeling.

14910

Reposted by TimDarcet

Juliette Marrie @jlt-m.bsky.social · 31/01/2025

(3/3) LUDVIG uses a graph diffusion mechanism to refine 3D features, such as coarse segmentation masks, by leveraging 3D scene geometry and pairwise similarities induced by DINOv2.

2121

Reposted by TimDarcet

Juliette Marrie @jlt-m.bsky.social · 31/01/2025

(2/3) We propose a simple, parameter-free aggregation mechanism, based on alpha-weighted multi-view blending of 2D pixel features in the forward rendering process.

Illustration of the inverse and forward rendering of 2D visual features produced by DINOv2.

1101

Reposted by TimDarcet

Juliette Marrie @jlt-m.bsky.social · 31/01/2025

(1/3) Happy to share LUDVIG: Learning-free Uplifting of 2D Visual features to Gaussian Splatting scenes, that uplifts visual features from models such as DINOv2 (left) & CLIP (mid) to 3DGS scenes. Joint work w. @dlarlus.bsky.social @jmairal.bsky.social Webpage & code: juliettemarrie.github.io/ludvig

16516

TimDarcet @timdarcet.bsky.social · 07/01/2025

Hash functions are really useful to uniquely encode stuff without collision huh

150

TimDarcet @timdarcet.bsky.social · 27/12/2024

At least there's diversity of opinions

1121

Reposted by TimDarcet

Jacob Schreiber @jmschreiber91.bsky.social · 23/12/2024

"no one can match my artistic vision" i mutter to myself repeatedly as i leave critical analyses undone and focus on what shade of gray to use in a supplemental figure

1273

Reposted by TimDarcet

Shobhita Sundaram @shobsund.bsky.social · 23/12/2024

Personal vision tasks–like detecting *your mug*--are hard; they’re data scarce and fine-grained. In our new paper, we show you can adapt general-purpose vision models to these tasks from just three photos! 📝: arxiv.org/abs/2412.16156 💻: github.com/ssundaram21/... (1/n)

17213

Reposted by TimDarcet

David Picard @davidpicard.eurosky.social · 15/12/2024

Everything is a LAW when you have 4 points on a log-log plot 🤔

0101

Reposted by TimDarcet

Dhruv Batra @dhruvbatra.bsky.social · 14/12/2024

Brilliant talk by Ilya, but he's wrong on one point. We are NOT running out of data. We are running out of human-written text. We have more videos than we know what to do with. We just haven't solved pre-training in vision. Just go out and sense the world. Data is easy.

59916

Reposted by TimDarcet

Nicolas Dufour @nicolasdufour.bsky.social · 10/12/2024

🌍 Guessing where an image was taken is a hard, and often ambiguous problem. Introducing diffusion-based geolocation—we predict global locations by refining random guesses into trajectories across the Earth's surface! 🗺️ Paper, code, and demo: nicolas-dufour.github.io/plonk

89732

Reposted by TimDarcet

Clément Canonne @ccanonne.github.io · 08/12/2024

Web 1.0 is back, baby

0191

TimDarcet @timdarcet.bsky.social · 07/12/2024

Wake up babe new iNat just dropped

020

Reposted by TimDarcet

Sara Beery @sarameghanbeery.bsky.social · 06/12/2024

Along with INQUIRE, we introduce iNat24, a new dataset of 5 million research-grade images from @inaturalist with 10,000 species labels. This is one of the largest publicly available natural world image repositories!

1288

TimDarcet @timdarcet.bsky.social · 06/12/2024

The hardest thing in the world is to refrain from using superlatives

240

Reposted by TimDarcet

François Fleuret @francois.fleuret.org · 30/11/2024

I'd be fine calling this the "Milan Principle" and I'd extend it to "Most commercialized goods do not need new features."

281

Reposted by TimDarcet

Thomas Fel @thomasfel.bsky.social · 27/11/2024

A fun thesis experiment: ResNet, DETR, and CLIP tackle Saint-Bernards. 🐶 ResNet focused on **fur** patterns, DETR too but also use **paws** (possibly because it helps define bounding boxes), and CLIP **head** concept oddly included human heads — language shaping learned concepts?

An image showing how three model top concept look like to classify st bernard, resnet use head and fur, while detr also use paws (maybe it help him delimitate the boundary). Clip use the head of the st bernard, but oodly the head seems to also react to human head...

082

TimDarcet @timdarcet.bsky.social · 24/11/2024

Excellent writeup on GPU streams / CUDA memory dev-discuss.pytorch.org/t/fsdp-cudac... TLDR by default mem is proper to a stream, to share it:: - `Tensor.record_stream` -> automatic, but can be suboptimal and nondeterministic - `Stream.wait` -> manual, but precise control

2291

Reposted by TimDarcet

Eugene Vinitsky 🍒 @eugenevinitsky.bsky.social · 24/11/2024

I've been using Skybridge (chromewebstore.google.com/detail/sky-f...) to rebuild the graph periodically which I think helps

chromewebstore.google.com

Sky Follower Bridge - Chrome Web Store

Instantly find and follow the same users from your Twitter follows on Bluesky.

1212

Reposted by TimDarcet

Opinion Editor @ Bluesky @dly.bsky.social · 24/11/2024

please, remember our core values:

541455

Reposted by TimDarcet

Lionel @spiindoctor.bsky.social · 23/11/2024

These opportunities are mostly reserved for the rest of the world. We need similar Industry-Academia PhD programs in the US too! We need an american version of the CIFRE.

231

Reposted by TimDarcet

Johan Edstedt @parskatt.bsky.social · 22/11/2024

༼ つ ◕_◕ ༽つ GIVE DINOv3

1121

Reposted by TimDarcet

Alaa El-Nouby @alaaelnouby.bsky.social · 22/11/2024

𝗗𝗼𝗲𝘀 𝗮𝘂𝘁𝗼𝗿𝗲𝗴𝗿𝗲𝘀𝘀𝗶𝘃𝗲 𝗽𝗿𝗲-𝘁𝗿𝗮𝗶𝗻𝗶𝗻𝗴 𝘄𝗼𝗿𝗸 𝗳𝗼𝗿 𝘃𝗶𝘀𝗶𝗼𝗻? 🤔 Delighted to share AIMv2, a family of strong, scalable, and open vision encoders that excel at multimodal understanding, recognition, and grounding 🧵 paper: arxiv.org/abs/2411.14402 code: github.com/apple/ml-aim HF: huggingface.co/collections/...

35819

Reposted by TimDarcet

Kosta Derpanis @csprofkgd.bsky.social · 21/11/2024

Gotta put this app down. Discovered so much cool stuff without the rage.

0281

Reposted by TimDarcet

David Picard @davidpicard.eurosky.social · 21/11/2024

Sidenote: TMLR is such a pleasant journal. It's fast and reviews are (mostly) insightful, detailed and helpful. Kind of how conference reviews were before the big rush, for the youngsters who thought It's always been that way.

061

Reposted by TimDarcet

Raphael Pisoni @4rtemi5.bsky.social · 18/11/2024

DinoV2 is without a doubt one of the most important Self Supervised Learning (SSL) methods right now. But training it takes 32 80Gb GPUs which is not easy to come by for small labs. What if we could train a comparable high-res model on 24Gb of VRAM? That's what I hope to show you here soon!🤞🧵 #mlsky

4616

TimDarcet @timdarcet.bsky.social · 01/10/2023

Vision transformers need registers! Or at least, it seems they 𝘸𝘢𝘯𝘵 some… ViTs have artifacts in attention maps. It’s due to the model using these patches as “registers”. Just add new tokens (“[reg]”): - no artifacts - interpretable attention maps 🦖 - improved performances! arxiv.org/abs/2309.16588

0110