MISA: MIning Saliency-Aware Semantic Prior for Box Supervised Instance Segmentation
Authors: Hao Zhu, Yan Zhu, Jiayu Xiao, Yike Ma, Yucheng Zhang, Jintao Li, Feng Dai
IJCAI 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive experiments show that our proposed MISA consistently surpasses the existing state-of-the-art methods by a large margin in the BSIS scenario. |
| Researcher Affiliation | Academia | 1Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China 2University of Chinese Academy of Sciences, Beijing, China |
| Pseudocode | No | The paper describes its methods using equations and descriptive text, but it does not include any explicitly labeled pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not provide an explicit statement or a link to its source code. |
| Open Datasets | Yes | PASCAL VOC 2012 The PASCAL VOC 2012 dataset [Everingham et al., 2010] includes 20 object categories. This dataset is divided into training and validation subsets, with 10,582 images for training and 1,449 images for validation. COCO The COCO dataset [Lin et al., 2014] is widely used in image segmentation task. It comprises 80 different object categories and contains a training set of 110k images, a validation set of 5k images, and a testing set of 20k images. |
| Dataset Splits | Yes | PASCAL VOC 2012 ... This dataset is divided into training and validation subsets, with 10,582 images for training and 1,449 images for validation. COCO ... contains a training set of 110k images, a validation set of 5k images, and a testing set of 20k images. |
| Hardware Specification | No | We train our model on 8 GPUs with a batch size of 16. |
| Software Dependencies | No | Our proposed method is implemented in Pytorch [Paszke et al., 2017] with mmcv/mmdet [Chen et al., 2019b] repository. |
| Experiment Setup | Yes | We train our model on 8 GPUs with a batch size of 16, and adopt Adam W as the optimizer with the initial learning rate set to 1.2 10 4 and weight decay set to 0.05. ... We set θ = 0.2 and t = 10 in Equation 4. The affinity balanced coefficient in Equation 13 is set to 0.7. In the objective function of Equation 6, we set λbg = 6 and λfg = 10 by default. |