A
Aixuan Li
Researcher at Northwestern Polytechnical University
Publications - 15
Citations - 472
Aixuan Li is an academic researcher from Northwestern Polytechnical University. The author has contributed to research in topics: Object detection & Computer science. The author has an hindex of 5, co-authored 10 publications receiving 116 citations.
Papers
More filters
Proceedings ArticleDOI
Weakly-Supervised Salient Object Detection via Scribble Annotations
TL;DR: This paper proposes a weakly-supervised salient object detection model to learn saliency from scribble annotations, and presents a new metric, termed saliency structure measure, as a complementary metric to evaluate sharpness of the prediction.
Proceedings ArticleDOI
Simultaneously Localize, Segment and Rank the Camouflaged Objects
TL;DR: Zhang et al. as mentioned in this paper proposed a ranking-based COD network (Rank-Net) to simultaneously localize, segment and rank camouflaged objects, where the localization model is proposed to find the discriminative regions that make the camouflaged object obvious.
Proceedings ArticleDOI
Uncertainty-aware Joint Salient Object and Camouflaged Object Detection
TL;DR: Zhang et al. as discussed by the authors leveraged the contradictory information to enhance the detection ability of both salient object detection and camouflaged object detection, and proposed an adversarial learning network to achieve both higher order similarity measure and network confidence estimation.
Posted Content
Weakly-Supervised Salient Object Detection via Scribble Annotations
TL;DR: Li et al. as discussed by the authors proposed a weakly-supervised salient object detection model to learn saliency from scribbles, which first relabeled the S-DUTS dataset with scribbles and then employed them as supervision to learn high-quality saliency maps.
Journal ArticleDOI
Toward Deeper Understanding of Camouflaged Object Detection
TL;DR: This paper presents the first triple-task learning framework to simultaneously localize, segment and rank camouflaged objects, indicating the conspicuousness level of camou⬂age, and argues that the binary segmentation setting fails to fully understand the concept of camufi�age.