Re-thinking Co-Salient Object Detection

Fan, Deng-Ping; Li, Tengpeng; Zheng, Lin; Ji, Ge-Peng; Zhang, Dingwen; Cheng, Ming–Ming; Fu, Huazhu; Shen, Jianbing

doi:10.1109/tpami.2021.3060412

Cited by 101 publications

(47 citation statements)

References 123 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…To more accurately locate camouflage objects in complex backgrounds, DDCN introduced the deep convolutional network to extract the semantic feature information. When the human eyes are performing some visual tasks (such as salient object detection [30], [31], pedestrian re-recognition, etc. ), the processes are usually carried out in two steps, namely, search and identification.…”

Section: A Camouflaged Object Detectionmentioning

confidence: 99%

D$^{2}$C-Net: A Dual-Branch, Dual-Guidance and Cross-Refine Network for Camouflaged Object Detection

Wang

Zhang

et al. 2022

IEEE Trans. Ind. Electron.

View full text Add to dashboard Cite

In this work, we propose a novel framework for camouflaged object detection (COD), named D 2 C-Net, which contains two new modules: dual-branch features extraction (DFE) and gradually refined cross fusion (GRCF). Specifically, the DFE simulates the two-stage detection process of human visual mechanisms in observing camouflage scenes. For the first stage, a dense concatenation is employed to aggregate multi-level features and expand the receptive field. The first stage feature maps are then utilized to extract two-direction guidance information, which benefits the second stage. The GRCF consists of a selfrefine attention unit and a cross-refinement unit, with the aim of combining the peer layer features and DFE features for an improved COD performance. The proposed framework outperforms 13 state-of-the-art deep learning-based methods upon three public datasets in terms of five widely used metrics. Finally, we show evidence for the successful applications of the proposed method in the fields of surface defect detection, medical image segmentation.

show abstract

Section: A Camouflaged Object Detectionmentioning

confidence: 99%

D$^{2}$C-Net: A Dual-Branch, Dual-Guidance and Cross-Refine Network for Camouflaged Object Detection

Wang

Zhang

et al. 2022

IEEE Trans. Ind. Electron.

View full text Add to dashboard Cite

show abstract

“…Jin et al [36] proposed that the weighted average each pairwise image was masked by the predicted saliency map as group semantics, and then used to compare the cosine similarity of each position of each image. Fan et al [38] learned common information using co-attentional projection strategy, and at the same time established a CoSOD3k dataset for the CoSOD task. Tang et al [39] regarded the CoSOD task as an end-toend sequence prediction problem and proposed the co-salient object detection transformer (CoSformer) network.…”

Section: Related Workmentioning

confidence: 99%

Global-and-Local Collaborative Learning for Co-Salient Object Detection

Cong¹,

Yang²,

Li³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

The goal of co-salient object detection (CoSOD) is to discover salient objects that commonly appear in a query group containing two or more relevant images. Therefore, how to effectively extract inter-image correspondence is crucial for the CoSOD task. In this paper, we propose a global-and-local collaborative learning architecture, which includes a global correspondence modeling (GCM) and a local correspondence modeling (LCM) to capture comprehensive inter-image corresponding relationship among different images from the global and local perspectives. Firstly, we treat different images as different time slices and use 3D convolution to integrate all intra features intuitively, which can more fully extract the global group semantics. Secondly, we design a pairwise correlation transformation (PCT) to explore similarity correspondence between pairwise images and combine the multiple local pairwise correspondences to generate the local inter-image relationship. Thirdly, the interimage relationships of the GCM and LCM are integrated through a global-and-local correspondence aggregation (GLA) module to explore more comprehensive inter-image collaboration cues. Finally, the intra-and inter-features are adaptively integrated by an intra-and-inter weighting fusion (AEWF) module to learn co-saliency features and predict the co-saliency map. The proposed GLNet is evaluated on three prevailing CoSOD benchmark datasets, demonstrating that our model trained on a small dataset (about 3k images) still outperforms eleven stateof-the-art competitors trained on some large datasets (about 8k˜200k images).

show abstract

“…

物体分割技术在计算机领域有着广泛的应用基础, 如图像分割 [1] 、显著目标分割 [2∼6] 、多模态显著物体分割 [7] 、协同显著目标分割 [8] 、前背景提取 [9] 、视频目标分割 [10] 以及目标检测与识别 [11,12] 等. 在这些应用当中, 为了评估模型算法的优劣, 将物体分割模型输出结果 (foreground map, FM) 与标准结果 (ground-truth, GT) 进行定量比较是必不可少的, 通常需要引入评价标准去衡量两者之间的相似度.

…”

unclassified