Awesome Knowledge-Distillation. 分类整理的知识蒸馏paper(2014-2021)。
A curated list of Multimodal Related Research.
Paper bank for Self-Supervised Learning
Deep learning for video compression.
FAIR's research platform for object detection research, implementing popular algorithms like Mask R-CNN and RetinaNet.
Image augmentation for machine learning experiments.
A high performance semantic segmentation toolkit based on PaddlePaddle. (『飞桨』图像分割库）
:robot: PaddleViT: State-of-the-art Visual Transformer and MLP Models for PaddlePaddle 2.0+
PyTorch implementation of Contrastive Learning methods; List of awesome-contrastive-learning papers
novel deep learning research works with PaddlePaddle
[CVPR 2021] Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers
Examples of using sparse attention, as in "Generating Long Sequences with Sparse Transformers"
[NeurIPS-2020] Self-paced Contrastive Learning with Hybrid Memory for Domain Adaptive Object Re-ID.
A PyTorch-Based Framework for Deep Learning in Computer Vision
A paper list of some recent Transformer-based CV works.