Shanghua Gao 6cb7fe0c51 Imagenet-s dataset for large-scale semantic segmentation (#2480) ... ## Motivation Based on the ImageNet dataset, we propose the ImageNet-S dataset has 1.2 million training images and 50k high-quality semantic segmentation annotations to support unsupervised/semi-supervised semantic segmentation on the ImageNet dataset. paper: Large-scale Unsupervised Semantic Segmentation (TPAMI 2022) [Paper link](https://arxiv.org/abs/2106.03149) ## Modification 1. Support imagenet-s dataset and its' configuration 2. Add the dataset preparation in the documentation		2023-01-16 16:42:19 +08:00
..
datasets	Imagenet-s dataset for large-scale semantic segmentation (#2480)	2023-01-16 16:42:19 +08:00
models	[FIX] fixing bug in `test_cfg` for U-Net _base_ script	2023-01-11 13:59:27 +08:00
schedules	support coco stuff-10k/164k (#625)	2021-09-22 20:48:08 +08:00
default_runtime.py	PAVI startup optimization (#1679)	2022-06-21 11:07:08 +08:00