Featured
Interpretable Medical Image Diagnosis with Explicd
Derm-T2IM: Harnessing Synthetic Skin Lesion Data via Stable Diffusion Models for Enhanced Skin Disease Classification using ViT and CNN
ViTPose : A simple yet powerful transformer baseline for Human Pose Estimation
FreqyWM:
The Skin Game: Setting New Standards for AI in Dermatology
Prompt Depth Anything
Uncertainty Quantification for skin cancer classification using Bayesian Deep Learning
Revolutionizing Cancer Diagnosis with the CHIEF Foundation Model
BiasPruner: Debiased Continual Learning for Medical Image Classification
StoryMaker
Wavelet Diffusion Models are fast and scalable Image Generators
S-SYNTH : Knowledge-based synthetic generation of skin images
Sapiens: Foundation for Human Vision Models
Exploring Kolmogorov-Arnold Networks (KANs)
MAXVIT-UNET: MULTI-AXIS ATTENTION FOR MEDICAL IMAGE SEGMENTATION
Ugly duckling detection using deep learning
MultiFacetEval
SuperYOLO: Super Resolution Assisted Object Detection in Multimodal Remote Sensing Imagery
ReNoise
Post-Hoc Concept Bottleneck Models
FeatUp: A Model-Agnostic Framework for Features at Any Resolution
Recently in AI | April 2024
High-Resolution Video Synthesis with Latent Diffusion Models
Catmull-Clark's algorithm
Face aging with Identity-preserved CGANs.
LRM : Large Reconstruction Model for Single Image to 3D
Depth Anything
Unveiling SAM: Revolutionizing Image Segmentation with the Segment Anything Model
Data Augmentation in Classification and Segmentation: A Survey and New Strategies
Understanding DLSS: A Dive into NVIDIA's Revolutionary Technology
“Vision Transformer Adapters for Generalizable Multitask Learning”
Can AI do Math Research ?
Unmasking Skin Lesions
Skeleton project with DWPose
Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation
Diffuse, Attend, and Segment: Unsupervised Zero-Shot Segmentation using Stable Diffusion
Computed tomography scan
A step into Machine Unlearning
"MAGVIT: Masked Generative Video Transformer"
Supercharge Your Python Code with a Comprehensive Testing Strategy
Mastering Generative AI with Large Language Models
Exploring Image Similarity Search and Deduplication
Dynamical Systems & machine Learning
Reconstructing Natural Scenes from fMRI Patters Using Deep Generative Networks
“Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture”, the latest paper from Yann Lecun’s team at Meta
DeepXplore: Unleashing the Power of Automated Whitebox Testing for Deep Learning Systems
EfficientNetV2: Smaller Models & Faster Training
Depth Map
Unsupervised Learning in Spiking Neural Networks
SkinGAN Project using LaMa-Fourier
Overview of Self Supervised Learning
SAM: Segment Anything Model by Meta AI
Introduction aux Graphes Neural Networks
AI Insights
-
Introduction aux Graphes Neural Networks
-
SAM: Segment Anything Model by Meta AI
-
Overview of Self Supervised Learning
-
SkinGAN Project using LaMa-Fourier
-
Unsupervised Learning in Spiking Neural Networks
AI Tasting Seminars
-
Reconstructing Natural Scenes from fMRI Patters Using Deep Generative Networks
-
From Dilated Convolution With Learnable Spacings to Gaussian Mixture Kernel Convolution
-
A Bayesian Framework for Multivariate Multifractal Analysis of Signals and Images
-
Functional Principal Component Analysis
-
Training Adaptive Reconstruction Networks for Blind Inverse Problems