返回
Learning From Box Annotations for Referring Image Segmentation
DOI:10.1109/TNNLS.2022.3201372.png)
摘要
En 中文
Referring image segmentation (RIS) has obtained an impressive achievement by fully convolutional networks (FCNs). However, previous RIS methods require a large number of pixel-level annotations. In this article, we present a weakly supervised RIS method by using bounding box (BB) annotations. In the first stage, we introduce an adversarial boundary loss to extract the object contour from the BB, which is then used to select appropriate region proposals for pseudoground-truth (PGT) generation. In the second stage, we design a co-training (Co-T) strategy to purify the pseudolabels. Specifically, we train two networks and interactively guide them to pick clean labels for each other's networks, which can weaken the effect of noisy labels on model training. Experiment results on four benchmark datasets demonstrate that the proposed method can produce high-quality masks with a speed of 63 frames/s.
Keyword:
Proposals
Annotations
Image segmentation
Visualization
Semantics
Training
Noise measurement
Adversarial boundary loss
bounding box (BB) annotation
co-training (Co-T) strategy
weakly supervised referring image segmentation (RIS)
期刊
IF:
8.9
论文数:
7.6K
被引数:
7.2W
机构
引用论文
LID, LEED, and Alternative Rating Systems—Integrating Low Impact Development Techniques with Green Building DesignLID,LEED和替代评级系统-将低影响开发技术与绿色建筑设计相结合
Substrate specificity and inhibitor analyses of human steroid 5β-reductase (AKR1D1)人类类固醇5 β-还原酶 (AKR1D1) 的底物特异性和抑制剂分析
Steroids
IF0
Communication and reproductive behaviour in North American Jerusalem crickets (
Stenopelmatus
) (Orthoptera: Stenopelmatidae).北美耶路撒冷蟋蟀的交流和生殖行为 (
Stenopelmatus
) (直翅目: Stenopelmatidae)。
Thermal comfort, perceived air quality, and cognitive performance when personally controlled air movement is used by tropically acclimatized persons当热带适应的人使用个人控制的空气运动时,热舒适性,感知的空气质量和认知表现
Indoor Air
IF0

