All-in-one training for vision models (YOLO, ViTs, RT-DETR, DINOv3): pretraining, fine-tuning, distillation.

The officieal implementation of the paper: CoWS: Self-Supervised Representation Pre-Training for Cross-Machine Fault Diagnosis

[ECCV2024] Video Foundation Models & Data for Multimodal Understanding

This is the implementation of DCMVC: Dual Contrastive Multi-view Clustering, published in Neurocomputing 2025.

[MICCAI'23] Foundation Model for Endoscopy Video Analysis via Large-scale Self-supervised Pre-train

Official implementation of "Augmentation-aware Self-supervised Learning with Conditioned Projector"

[AISY] Self-Supervised Learning-Based Framework for Speckle Reduction of Optical Coherence Tomography Images Using Frame Interpolation

[ICCV 2025] Official PyTorch Implementation of "Learning Self-supervised Part-aware 3D Hybrid Representations of 2D Gaussians and Superquadrics"

TomoSelfDEQ: Self-Supervised Deep Equilibrium Learning for Sparse-Angle CT Reconstruction (2025)

Self-supervised models for encoding protein localization patterns from microscopy images

[TIP 2025] DCPI-Depth: Explicitly Infusing Dense Correspondence Prior to Unsupervised Monocular Depth Estimation

[RA-L 25] Self-Supervised Diffusion-Based Scene Flow Estimation and Motion Segmentation with 4D Radar

🏠 [JBHI 2024] Pytorch implementation of 'MonoLoT: Self-Supervised Monocular Depth Estimation in Low-Texture Scenes for Automatic Robotic Endoscopy'

[ECCV 2024] Mono-ViFI: A Unified Learning Framework for Self-supervised Single- and Multi-frame Monocular Depth Estimation

Wav2vec 2.0 Self-Supervised Pretraining

A self-supervised network for image denoising and watermark removal (Neural Networks 2024)

Official PyTroch implementation for Learning from Memory: A Non-Parametric Memory Augmented Self-Supervised Learning of Visual Features

Library to perform image and video self-supervised learning.

[VUA@BMVC2024] Self-Supervised Contrastive Learning for Videos using Differentiable Local Alignment

Official implementation of the paper: Behind the Scenes: Density Fields for Single View Reconstruction (CVPR 2023)