GitHub

Time-Series Image Classifier

A production-ready deep learning project for time-series image classification using EfficientNet/NFNet with PyTorch Lightning. This project implements transfer learning for multi-class classification ...
GitHub

ResNet-50 Image Classification

This project implements ResNet-50, a deep convolutional neural network with 50 layers that uses residual connections to enable training of very deep networks. The architecture includes identity ...
VentureBeat

NYU’s new AI architecture makes high-quality image generation faster and cheaper

Researchers at New York University have developed a new architecture for diffusion models that improves the semantic representation of the images they generate. “Diffusion Transformer with ...
Scientific Research Publishing

Xu, J., Xiang, L., Liu, Q., Gilmore, H., Wu, J., Tang, J., et al. (2016) Stacked Sparse Autoencoder (SSAE) for Nuclei Detection on Breast Cancer Histopathology Images. IEEE ...

ABSTRACT: Liver cancer is one of the most prevalent and lethal forms of cancer, making early detection crucial for effective treatment. This paper introduces a novel approach for automated liver tumor ...
Frontiers

Thyroid nodule segmentation in ultrasound images using transformer models with masked autoencoder pre-training

Introduction: Thyroid nodule segmentation in ultrasound (US) images is a valuable yet challenging task, playing a critical role in diagnosing thyroid cancer. The difficulty arises from factors such as ...
Frontiers

Enhanced hyperspectral image classification for coastal wetlands using a hybrid CNN-transformer approach with cross-attention mechanism

1 State Key Laboratory of Resources and Environmental Information System, Institute of Geographic Sciences and Natural Resources Research (IGSNRR), Chinese Academy of Sciences (CAS), Beijing, China 2 ...
ArchDaily

Beyond the Image: Rethinking Architecture in the Age of AI

Artificial intelligence is becoming an undeniable presence in our daily lives. It teaches, generates content, and disrupts the fragile boundaries—both visual and imaginative—that once governed our ...
IEEE

PyTorch Re-implementation of Stable Diffusion: A Manual Implementation and Efficiency Analysis of Text-to-Image Synthesis

Abstract: This paper presents an in-depth exploration of the Stable Diffusion pipeline for text-to-image synthesis, emphasizing a comparative analysis between the Latent Diffusion Model (LDM) and the ...
IEEE

Spatial–Spectral Hierarchical Multiscale Transformer-Based Masked Autoencoder for Hyperspectral Image Classification

Abstract: Due to the excellent feature extraction capabilities, deep learning has become the mainstream method for hyperspectral image (HSI) classification. Transformer, with its powerful long-range ...
VentureBeat

Sakana introduces new AI architecture, ‘Continuous Thought Machines’ to make models reason with less guidance — like human brains

Want smarter insights in your inbox? Sign up for our weekly newsletters to get only what matters to enterprise AI, data, and security leaders. Subscribe Now Tokyo-based artificial intelligence startup ...