Compared to RGB semantic segmentation, RGBD semantic segmentation can achieve better performance by taking depth information into consideration. However, it is still problematic for contemporary segmenters to effectively exploit RGBD information since the feature distributions of RGB and depth (D) images vary significantly in different scenes. In this paper, we propose an Attention Complementary Network (ACNet) that selectively gathers features from RGB and depth branches. The main contributions lie in the Attention Complementary Module (ACM) and the architecture with three parallel branches. More precisely, ACM is a channel attention-based module that extracts weighted features from RGB and depth branches. The architecture preserves the inference of the original RGB and depth branches, and enables the fusion branch at the same time. Based on the above structures, ACNet is capable of exploiting more high-quality features from different channels. We evaluate our model on SUN-RGBD and NYUDv2 datasets, and prove that our model outperforms state-of-the-art methods. In particular, a mIoU score of 48.3% on NYUDv2 test set is achieved with ResNet50. We will release our source code based on PyTorch and the trained segmentation model at https://github.com/anheidelonghu/ACNet.

No abstract

Tumor-associated macrophages are a prominent component of lung cancer stroma and contribute to tumor progression. The protein V-set and Ig domain-containing 4 (VSIG4), a novel B7 family-related macrophage protein that has the capacity to inhibit T-cell activation, has a potential role in the development of lung cancer. In this study, 10 human non-small-cell lung cancer specimens were collected and immunohistochemically analyzed for VSIG4 expression. Results showed massive VSIG4 þ cell infiltration throughout the samples. Immunofluorescent double staining showed that VSIG4 was present on CD68 þ macrophages, but absent from CD3 þ T cells, CD31 þ endothelial cells, and CK-18 þ epithelial cells. Moreover, VSIG4 was coexpressed on B7-H1 þ and B7-H3 þ cells in these tumor specimens. Transfection of the VSIG4 gene into 293FT cells demonstrated that the VSIG4 signal could inhibit cocultured CD4 þ and CD8 þ T-cell proliferation and cytokine (IL-2 and IFN-g) production in vitro. Interestingly, in a murine tumor model induced by Lewis lung carcinoma cell line, we found that tumors grown in VSIG4-deficient (VSIG4 À / À ) mice were significantly smaller than those found in wildtype littermates. All of these results demonstrate that macrophage-associated VSIG4 is an activator that facilitates lung carcinoma development. Specific targeting of VSIG4 may prove to be a novel, efficacious strategy for the treatment of this carcinoma.

VSIG4 controls inflammation through MS4A6D-mediated transcriptional inhibition of Nlrp3 and Il-1β in macrophages.