Loading [a11y]/accessibility-menu.js
Multi-level Feature Reweighting and Fusion for Instance Segmentation | IEEE Conference Publication | IEEE Xplore

Multi-level Feature Reweighting and Fusion for Instance Segmentation


Abstract:

Accurate instance segmentation requires high-resolution features for performing a dense pixel-wise prediction task. However, using high-resolution feature maps results in...Show More

Abstract:

Accurate instance segmentation requires high-resolution features for performing a dense pixel-wise prediction task. However, using high-resolution feature maps results in highly expensive model complexity and ineffective receptive fields. To overcome the problems of high-resolution features, conventional methods explore multi-level feature fusion that exchanges the information between low-level features at earlier layers and high-level features at top layers. Both low and high information is extracted by the hierarchical backbone network where high-level features contain more semantic cues and low-level features encompass more specific patterns. Thus, adopting these features to the training segmentation model is necessary, and designing a more efficient multi-level feature fusion is crucial. Existing methods balance such information by using top-down and bottom-up pathway connections with more inefficient convolution layers to produce richer multi-scale features. In this work, we contribute two folds: (1) a simple but effective multilevel feature reweighting layer is proposed to strengthen deep high-level features based on channel reweighting generated from multiple features of the backbone, and (2) an efficient fusion block is proposed to process low-resolution features in a depth-to-spatial manner and combine enhanced multi-level features together. These designs enable the segmentation models to predict instance kernels for mask generation on high-level feature maps. To verify the effectiveness of the proposed method, we conduct experiments on the challenging benchmark dataset MS-COCO. Surprisingly, our simple network outperforms the baseline in both accuracy and inference speed. More specifically, we achieve 35.4% APmask at 19.5 FPS on a GPU device, becoming a state-of-the-art instance segmentation method.
Date of Conference: 25-28 July 2022
Date Added to IEEE Xplore: 15 December 2022
ISBN Information:
Conference Location: Perth, Australia

Funding Agency:


Contact IEEE to Subscribe

References

References is not available for this document.