Detection of Co-salient Objects by Looking Deep and Wide

By Dingwen Zhang, Junwei Han, Chao Li, Jingdong Wang, Xuelong Li. 2016

323 citations recorded by the source corpus.

In this paper, we propose a unified co-salient object detection framework by introducing two novel insights: (1) looking deep to transfer higher-level representations by using the convolutional neural network with additional adaptive layers could better reflect the sematic properties of the co-salient objects; (2) looking wide to take advantage of the visually similar neighbors from other image groups could effectively suppress the influence of the common background regions. The wide and deep information are explored for the object proposal windows extracted in each image. The window-level co-saliency scores are calculated by integrating the intra-image contrast, the intra-group consistency, and the inter-group separability via a principled Bayesian formulation and are then converted to the superpixel-level co-saliency maps through a foreground region agreement strategy. Comprehensive experiments on two existing and one newly established datasets have demonstrated the consistent performance gain of the proposed approach.

Subfields: Computer Vision and Pattern Recognition, Sensory Systems

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Sensory Systems

Citations in the corpus

Video Salient Object Detection via Fully Convolutional Networks (2017, background): “been extend to capturing common saliency among related images/videos [41]–[43], [45], [48], inferring the salient”
Weakly Supervised Object Localization and Detection: A Survey (2021, unknown): “In addition, the co-occurring patterns mined in co-saliency detection [196], [201] and object co-localization [118], [171] approaches can also be used as informative priors to guide the deep multiple instance learning process in weakly supervised object localization and detection.”
Revealing Event Saliency in Unconstrained Video Collection (2017, unknown): “For example, Zhang et al. [24] addressed object co-segmentation in arbitrary videos via a Regulated Maximum Weight Clique (RMWC) extraction scheme, which integrated the components of sampling , tracking and matching object proposals.”
CNNs-Based RGB-D Saliency Detection via Cross-View Transfer and Multiview Fusion (2018, background): “, co-saliency detection [52], [53], [55], video saliency detection [54], and”
Salient Object Detection via Integrity Learning (2021, background): “[53] proposed a unified co-saliency detection framework by exploring both the wide (visually similar images) and deep (highlevel semantics) information.”
Review of Visual Saliency Detection With Comprehensive Information (2018, background): “constructed in [116], which consists of 2015 RGB images distributed in 50 image groups with pixel-wise ground truth.”
Saliency-Aware Video Object Segmentation (2018, background): “Top-down approaches [32], [33], [34], [35] are goal-directed and require an explicit understanding of the context of the image.”
JL-DCF: Joint Learning and Densely-Cooperative Fusion Framework for RGB-D Salient Object Detection (2020, background): “It has many useful applications, including object segmentation and recognition [27, 32, 39, 51, 70, 79], image/video compression [24], video detection/summarization [19, 41], content-based image editing [14, 23, 42, 57, 63], informative common object discovery [71, 72], and image retrieval [8, 22, 3”