CARD: Semi-supervised Semantic Segmentation via Class-agnostic Relation based Denoising
Authors: Xiaoyang Wang, Jimin Xiao, Bingfeng Zhang, Limin Yu
IJCAI 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive experiments on PASCAL VOC and Cityscapes demonstrate the state-of-the-art performances of the proposed methods under various semi-supervised settings. |
| Researcher Affiliation | Collaboration | 1Xi an Jiaotong Liverpool University 2University of Liverpool 3Dinnar Automation Technology |
| Pseudocode | No | The paper does not contain any structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not provide any explicit statements about open-sourcing code or links to a code repository. |
| Open Datasets | Yes | PASCAL VOC 2012 [Everingham et al., 2010] with SBD annotations [Hariharan et al., 2011] are commonly used benchmark for semantic segmentation. ... Cityscapes [Cordts et al., 2016] is a dataset for urban scene understanding. ... COCO [Lin et al., 2014] pretrained weights. ... Image Net [Deng et al., 2009] pretrained weights |
| Dataset Splits | Yes | For PASCAL VOC, 1/100, 1/50, 1/20, and 1/8 data splits are created. For Cityscapes, 1/30, 1/8, 1/4 images are randomly sampled from the dataset. The selected images are used as labeled data, while the rest are as an unlabeled set. Three folds are created for each data partition, and the final performance is the average on the three folds on the validation set. ... The training set and validation set consist of 10,582 and 1,449 images. ... The training set and validation set contain 2,975 and 500 finely annotated images. |
| Hardware Specification | No | The paper does not provide specific details about the hardware used to run experiments (e.g., GPU/CPU models, memory). |
| Software Dependencies | No | The paper mentions 'Deep Labv2' and 'Res Net-101' as models and 'SGD optimizer' but does not specify software versions (e.g., TensorFlow/PyTorch version, Python version, specific library versions). |
| Experiment Setup | Yes | For both PASCAL VOC and Cityscapes datasets, we use the stochastic gradient descent (SGD) optimizer with learning rate 0.001, weight decay 0.0005 and momentum 0.9. Following the common practice, we use poly learning rate policy where the initial learning rate is scaled by (1 iter/max iter)0.9. Among all semi-supervised protocols, the warm-up training on labeled sets lasts 10k iterations. We conduct single-stage self-training and train the model on unlabeled images for 40 epochs. The batch size is set to 8 for both training stages. The weight for updating the EMA teacher model is 0.999. For data augmentation, only random horizontal flip is applied. Upper bound b in Eq. (7) for denoising region is set as 60th class-wise quantile. |