Papers › ACNet: Attention Based Network to Exploit Complementary Features for RGBD Semantic Segmentation

ACNet: Attention Based Network to Exploit Complementary Features for RGBD Semantic Segmentation

24 May 2019arXiv:1905.10089archive 2025-07-28

Xinxin Hu, Kailun Yang, Lei Fei, Kaiwei Wang

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.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

anheidelonghu/ACNet officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

SegmentationSemantic SegmentationThermal Image Segmentation

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Semantic Segmentation KITTI-360 ACNet (ResNet50) mIoU 61.57 #7 of 17 Archive leaderboard report
Semantic Segmentation NYU Depth v2 ACNet Mean IoU 48.3% #78 of 121 Archive leaderboard report
Semantic Segmentation SUN-RGBD CMX (B4) Mean IoU 48.1% #33 of 44 Archive leaderboard report
Semantic Segmentation THUD Robotic Dataset ACNet mIoU 74.83 #4 of 4 Archive leaderboard report
Thermal Image Segmentation MFN Dataset ACNet mIOU 46.3 #45 of 55 Archive leaderboard report
Thermal Image Segmentation PST900 ACNet mIoU 71.81 #17 of 22 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections