Hierarchical Semantic Contrast for Weakly Supervised Semantic Segmentation
Authors: Yuanchen Wu, Xiaoqiang Li, Songmin Dai, Jide Li, Tong Liu, Shaorong Xie
IJCAI 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive studies manifest that our plug-and-play learning paradigm, HSC, can significantly boost CAM quality on both nonsaliency-guided and saliency-guided baselines, and establish new state-of-the-art WSSS performance on PASCAL VOC 2012 dataset. |
| Researcher Affiliation | Academia | Yuanchen Wu , Xiaoqiang Li , Songmin Dai , Jide Li , Tong Liu and Shaorong Xie School of Computer Engineering and Science, Shanghai University, Shanghai, China {yuanchenwu, xqli, laodar, iavtvai, tong liu, srxie}@shu.edu.com |
| Pseudocode | No | The paper does not contain structured pseudocode or algorithm blocks clearly labeled as "Pseudocode" or "Algorithm". |
| Open Source Code | Yes | Code is available at https://github.com/Wu0409/HSC WSSS. |
| Open Datasets | Yes | We evaluate our approach on the standard WSSS benchmark, PASCAL VOC 2012 (20 object classes and one background class). Following the convention in semantic segmentation, we adopted its augmented training set (SBD) [Hariharan et al., 2011] that consists of 10582 images to train our classification model in step 1 and the segmentation model in step 2. |
| Dataset Splits | Yes | We evaluate our approach on the standard WSSS benchmark, PASCAL VOC 2012 (20 object classes and one background class). Following the convention in semantic segmentation, we adopted its augmented training set (SBD) [Hariharan et al., 2011] that consists of 10582 images to train our classification model in step 1 and the segmentation model in step 2. Mean intersection over union (m Io U) is used to evaluate initial seeds, pseudo-labels, and final segmentation performance. The m Io U of segmentation performance on the test set is evaluated from the official evaluation server. Table 2 provides the comparison of HSC against representative methods in terms of final segmentation results on PASCAL VOC 2012 val and test set. |
| Hardware Specification | No | The paper mentions "Shanghai Engineering Research Center of Intelligent Computing System for providing the computing resources" in the acknowledgements, but does not provide specific hardware details such as GPU or CPU models used for the experiments. |
| Software Dependencies | No | The paper mentions software components like "Deep Lab-ASPP" and "Res Net38" but does not provide specific version numbers for these or other software dependencies. |
| Experiment Setup | Yes | For the training images of View #1, they are first randomly rescaled with the range of [448, 768] by the longest edge and then randomly cropped by 448 448. Based on the images of View #1, they are downsampled to 128 128 for View #2. At the training stage, we set γ = 0.1 to balance the loss of Lhsc and their supervision loss. In this paper, we set λ = 0.9, kc = 16, and kp = 32 for the optimal performance. |