🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Reparameterizing #neuralnets with #tensors #CVPR2019 work by Jean Kossaifi Adrian Bulat @GeorgiosTzimiropoulos Maja Pantic @CVPR2019

Really enjoyed giving a talk Caltech on #tensor methods and #DeepLearning with Adrian Bulat

Some more work from our lab. This time 3D segmentation of roots in CT images. We use a multi-path network to capture both high resolution detail, and wider context. Fully automatic, no parameters or user interaction. Tool soon! biorxiv.org/content/10.110…

The #NeurIPS reviewer option “I will consider not reviewing for NeurIPS again if this submission is accepted.” is ridiculous. It encourages a toxic attitude towards reviewing, and when it is actually used, can be incredibly hurtful to our young scholars. NeurIPS Conference

Interested in automatic #emotion estimation from faces in natural conditions? 😁☹️😠😧😮 Checkout our Nature Machine Intelligence paper - we estimate discrete emotion, continuous valence & arousal levels and facial landmarks w/ very high accuracy! ⬇️ youtube.com/watch?v=J8Skph… Springer Nature

Excited to announce the Workshop on Binary Networks held in conjunction with #CVPR2021. Great place for learning about efficient deep learning models from our amazing invited speakers. Paper submission will open soon. For more details, please check: binarynetworks.io

In the past I've thought that having a comment system on arXiv would enable productive discussion and identification of errors in papers which were previously only known to a select few. Based on #ICLR2021's OpenReview, I think it would just be people saying "plz cite me"

Journal club today at 1: We'll read "Pre-training strategies and datasets for facial representation learning" by Adrian Bulat et al. Leif will be leading the discussion. KITE Trainees AGE-WELL Follow @KITE_UHN and @TorontoRehab cs.toronto.edu/~taati/journal…

Our work "Bit-Mixer: Mixed-precision networks with runtime bit-width selection" has being accepted at #ICCV2021 ICCV2021 ! Check it out if want to learn more about how you can quantize your model's blocks to different bit-widths at runtime. Preprint: arxiv.org/abs/2103.17267

📢📢📢📢Check our new Arxiv paper: Variational Prompt Tuning Improves Generalization of Vision-Language Models Link: arxiv.org/abs/2210.02390 w/ Enrique Sanchez, Adrian Bulat, Victor Turrisi, Cees Snoek, Georgios Tzimiropoulos, Brais Martinez at Samsung Research 🧵1/5

[Tech Blog] #CVPR2023 series ⑥ Introducing LASP, a text-to-text optimization method for vision language adaptation that sets a new state-of-the-art for #fewshot and #zeroshot image classification. #AI #VisionLanguage research.samsung.com/blog/LASP-Text…

Join us at #iccv2023 at the workshop on Low-Bit Quantized Neural Networks (LBQNN). Learn about the latest developments in the field, foster collaborations or share your work by submitting a paper by 1st of august. Call for papers: sites.google.com/view/lbqnn-icc…

Only a few days left (1st of august) to submit your papers to the Low-Bit Quantized Neural Networks (LBQNN) workshop #ICCV2025 ⌛️

Just a few days left (3rd of July) to submit your work on extreme quantization to the BiVision Workshop #ICCV2025 We look forward to hear about you interesting work in this area! #ICCV2025 Call for papers: binarynetworks.io