[ICLR 2025] Mixture Compressor for Mixture-of-Experts LLMs Gains More

[CVPR 2024] Seeing and Hearing: Open-domain Visual-Audio Generation with Diffusion Latent Aligners

Refine high-quality datasets and visual AI models

Open-source and strong foundation image recognition models.

Official PyTorch implementation of ODISE: Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Models [CVPR 2023 Highlight]

Is synthetic data from generative models ready for image recognition?

CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

(CVPR 2022) Video Demoireing with Relation-Based Temporal Consistency

(NeurlPS 2022) Spatial Pruned Sparse Convolution for Efficient 3D Object Detection

(NeurlPS 2022) Towards Efficient 3D Object Detection with Knowledge Distillation

[NeurIPS 2022] Official implementation of the paper "Rethinking Resolution in the Context of Efficient Video Recognition".

(ECCV2022) This is the official PyTorch implementation of ECCV2022 paper: Towards Efficient and Scale-Robust Ultra-High-Definition Image Demoireing

(CVPR 2021 & T-PAMI 2022) ST3D: Self-training for Unsupervised Domain Adaptation on 3D Object Detection & ST3D++: Denoised Self-training for Unsupervised Domain Adaptation on 3D Object Detection

(CVPR 2021) PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Clouds

(NeurIPS 2022) Self-Supervised Visual Representation Learning with Semantic Grouping

(CVPR2022) Official PyTorch Implementation of KDEP. Knowledge Distillation as Efficient Pre-training: Faster Convergence, Higher Data-efficiency, and Better Transferability

(ICCV 2021 Oral) Re-distributing Biased Pseudo Labels for Semi-supervised Semantic Segmentation: A Baseline Investigation.

VISSL is FAIR's library of extensible, modular and scalable components for SOTA Self-Supervised Learning with images.

The official PyTorch implementation of the paper "Learning by Analogy: Reliable Supervision from Transformations for Unsupervised Optical Flow Estimation".