GitHub

Simplified PyTorch Implementation of Improved Autoencoder Model With Memory Module for Anomaly Detection

Improved Autoencoder Model With Memory Module for Anomaly Detection (IAEMM) is an unsupervised anomaly detection algorithm that enhances traditional autoencoders with a memory module and a hypersphere ...
GitHub

How to .update() a GaussianConditional entropy model and properly call .compress() and .decompress()?

Hello! I'm trying to train my own custom autoencoder model while integrating EntropyBottleneck and GaussianConditional. Here's a snippet of my class: class AEWithEntropy(nn.Module): def __init__(self, ...
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 ...
IEEE

Cross-Modal Contrastive Masked AutoEncoder for Compressed Video Pre-Training

Abstract: In this paper, we propose a novel Transformer based approach, namely Cross-modal Contrastive Masked AutoEncoder (C2MAE), to Self-Supervised Learning (SSL) on compressed videos. A unified ...
IEEE

MMEVAE: A Time-Varying Rolling Bearing Data Enhancement Method Based on a Multimodal Mechanism Enhanced Variational Autoencoder and Self-Attention Module

Abstract: Variational autoencoder (VAE) is widely used as a data enhancement technique. However, it faces challenges with inaccurate potential spatial distribution and poor reconstruction quality when ...
marktechpost

This AI Paper Introduces a Short KL+MSE Fine-Tuning Strategy: A Low-Cost Alternative to End-to-End Sparse Autoencoder Training for Interpretability

Sparse autoencoders are central tools in analyzing how large language models function internally. Translating complex internal states into interpretable components allows researchers to break down ...
Europe PMC

Harnessing unlabeled data: Enhanced rare earth component content prediction based on BiLSTM-Deep autoencoder.

Traditional data-driven models for predicting rare earth component content are primarily developed by relying on supervised learning methods, which suffer from limitations such as a lack of labeled ...