A Unified Multiple Graph Learning and Convolutional Network Model for Co-saliency Estimation

Jiang, Bo; Jiang, Xingyue; Zhou, Ajian; Tang, Jin; Luo, Bin

doi:10.1145/3343031.3350860

Cited by 47 publications

(22 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For dl-based model, motion encoding is achieved by optical flow [23], [8], [61], [35] or recurrent neural network [35], [61], [57]. In addition, co-saliency [24], [32] estimation searches for the common salient object regions contained in an image set.…”

Section: B Salient Object Detectionmentioning

confidence: 99%

Horizontal-to-Vertical Video Conversion

Zhu

Zhang

et al. 2021

Preprint

View full text Add to dashboard Cite

Section: B Salient Object Detectionmentioning

confidence: 99%

Horizontal-to-Vertical Video Conversion

Zhu

Zhang

et al. 2021

Preprint

View full text Add to dashboard Cite

“…Recently deep-based models simultaneously explore the intra-and inter-image consistency in a supervised manner with different approaches, such as graph convolution networks (GCN) [32,33,34], self-learning methods [15,35], inter-image co-attention with PCA projection [1] or recurrent units [36], correlation techniques [37], quality measurement [38], or co-clustering [39]. Some methods exploit multi-task learning to simultaneously optimize the co-saliency detection and co-segmentation [40] or co-peak search [6].…”

Section: Related Workmentioning

confidence: 99%

Group Collaborative Learning for Co-Salient Object Detection

Fan¹,

Fan²,

Fu³

et al. 2021

Preprint

View full text Add to dashboard Cite

We present a novel group collaborative learning framework (GCoNet) capable of detecting co-salient objects in real time (16ms), by simultaneously mining consensus representations at group level based on the two necessary criteria: 1) intra-group compactness to better formulate the consistency among co-salient objects by capturing their inherent shared attributes using our novel group affinity module; 2) inter-group separability to effectively suppress the influence of noisy objects on the output by introducing our new group collaborating module conditioning the inconsistent consensus. To learn a better embedding space without extra computational overhead, we explicitly employ auxiliary classification supervision. Extensive experiments on three challenging benchmarks, i.e., CoCA, CoSOD3k, and Cosal2015, demonstrate that our simple GCoNet outperforms 10 cutting-edge models and achieves the new state-ofthe-art. We demonstrate this paper's new technical contributions on a number of important downstream computer vision applications including content aware co-segmentation, co-localization based automatic thumbnails, etc.

show abstract

“…As aforementioned, the AGCN is to process features as Laplacian smoothing [33] that can benefit long-range intraand inter-image correspondence while preserving spatial consistency. Numerous graph based works for co-saliency detection [26,55,79,25,28,38] have been developed to better preserve spatial consistency, but they perform intrasaliency detection and inter-image correspondence independently, which cannot well capture the interactions between co-salient regions across images that are essential to cosaliency detection, thereby leading to sub-optimal performance. Differently, our AGCN constructs a dense graph that takes all input image features as the node representations.…”

Section: Adaptive Graph Convolution Networkmentioning

confidence: 99%

“…Meanwhile, each edge of the graph models the interactions between any pair-wise nodes regardless of their positional distance, thereby well capturing long-range dependencies. Hence, both intra-saliency detection and interimage correspondence can be jointly implemented via feature propagation on the graph under a unified framework without any poster-processing, leading to a more accurate co-saliency estimation than those individually processing each part [26,55,79,25,28,38].…”

Section: Adaptive Graph Convolution Networkmentioning

confidence: 99%

Adaptive Graph Convolutional Network with Attention Graph Clustering for Co-saliency Detection

Zhang

Shen

et al. 2020

Preprint

View full text Add to dashboard Cite

Co-saliency detection aims to discover the common and salient foregrounds from a group of relevant images. For this task, we present a novel adaptive graph convolutional network with attention graph clustering (GCAGC). Three major contributions have been made, and are experimentally shown to have substantial practical merits. First, we propose a graph convolutional network design to extract information cues to characterize the intra-and interimage correspondence. Second, we develop an attention graph clustering algorithm to discriminate the common objects from all the salient foreground objects in an unsupervised fashion. Third, we present a unified framework with encoder-decoder structure to jointly train and optimize the graph convolutional network, attention graph cluster, and co-saliency detection decoder in an end-to-end manner. We evaluate our proposed GCAGC method on three cosaliency detection benchmark datasets (iCoseg, Cosal2015 and COCO-SEG). Our GCAGC method obtains significant improvements over the state-of-the-arts on most of them.

show abstract

A Unified Multiple Graph Learning and Convolutional Network Model for Co-saliency Estimation

Cited by 47 publications

References 27 publications

Horizontal-to-Vertical Video Conversion

Horizontal-to-Vertical Video Conversion

Group Collaborative Learning for Co-Salient Object Detection

Adaptive Graph Convolutional Network with Attention Graph Clustering for Co-saliency Detection

Contact Info

Product

Resources

About