Bilateral Reference for High-Resolution Dichotomous Image Segmentation
arXiv:2401.03407 · doi:10.26599/AIR.2024.9150038
Abstract
We introduce a novel bilateral reference framework (BiRefNet) for high-resolution dichotomous image segmentation (DIS). It comprises two essential components: the localization module (LM) and the reconstruction module (RM) with our proposed bilateral reference (BiRef). The LM aids in object localization using global semantic information. Within the RM, we utilize BiRef for the reconstruction process, where hierarchical patches of images provide the source reference and gradient maps serve as the target reference. These components collaborate to generate the final predicted maps. We also introduce auxiliary gradient supervision to enhance focus on regions with finer details. Furthermore, we outline practical training strategies tailored for DIS to improve map quality and training process. To validate the general applicability of our approach, we conduct extensive experiments on four tasks to evince that BiRefNet exhibits remarkable performance, outperforming task-specific cutting-edge methods across all benchmarks. Our codes are available at https://github.com/ZhengPeng7/BiRefNet.
Version 7, fix the A/B reverse problem in Fig. 9
References in corpus (11)
- U-Net: Going Deeper with Nested U-Structure for Salient Object Detection
- Salient Object Detection: A Benchmark
- Concealed Object Detection
- Anabranch Network for Camouflaged Object Segmentation
- Boundary-Guided Camouflaged Object Detection
- Deep Gradient Learning for Efficient Camouflaged Object Detection
- A Deep Learning based No-reference Quality Assessment Model for UGC Videos
- Blind Quality Assessment for in-the-Wild Images via Hierarchical Feature Fusion and Iterative Mixed Database Training
- Advances in Deep Concealed Scene Understanding
- Salient Objects in Clutter
- Deep Neural Network for Blind Visual Quality Assessment of 4K Content