Hunting Sparsity: Density-Guided Contrastive Learning for Semi-Supervised Semantic Segmentation
Hunting Sparsity: Density-Guided Contrastive Learning for Semi-Supervised Semantic Segmentation
Xiaoyang Wang, Bingfeng Zhang, Limin Yu, and Jimin Xiao.
In CVPR 2023.
> **Abstract:** *Inspired by density-based unsupervised clustering, we propose to leverage feature density to locate sparse regions within feature clusters defined by label and pseudo labels. The hypothesis is that lower-density features tend to be under-trained compared with those densely gathered. Therefore, we propose to apply regularization on the structure of the cluster by tackling the sparsity to increase intra-class compactness in feature space. With this goal, we present a Density-Guided Contrastive Learning (DGCL) strategy to push anchor features in sparse regions toward cluster centers approximated by high-density positive keys. The heart of our method is to estimate feature density which is defined as neighbor compactness. We design a multi-scale density estimation module to obtain the density from multiple nearest-neighbor graphs for robust density modeling. Moreover, a unified training framework is proposed to combine label-guided self-training and densityguided geometry regularization to form complementary supervision on unlabeled data.* ## Getting Started ### Installation ```bash cd DGCL conda create -n dgcl python=3.10 conda activate dgcl pip install -r requirements.txt ``` ### Pretrained Weights Download pretrained wegiths [ResNet-101](https://drive.google.com/file/d/1p3d2EZMNgSu0v-fQHk3pPpOygwraqyFP/view?usp=sharing) ``` ├── DGCL/ └── resnet101.pth ``` ### Data Preparation ``` ├── Path_to_Pascal ├── JPEGImages └── SegmentationClassAug ├── Path_to_Cityscapes ├── leftImg8bit └── gtFine ``` ## Training Navigate into `experiments/pascal/732` and modify `config.yaml` and `train.sh`. ``` sh train.sh