Multi-Source Weak Supervision for Saliency Detection

Zeng, Yu; Zhuge, Yunzhi; Lu, Huchuan; Zhang, Lihe; Qian, Mingyang; Yu, Yizhou

doi:10.1109/cvpr.2019.00623

Cited by 152 publications

(119 citation statements)

References 35 publications

Supporting

Mentioning

119

Contrasting

Order By: Relevance

“…In greater detail, visual information is grouped into multi-cues vectors to discard the non-salient regions and highlight the salient area. Zeng et al [80] proposed a unified framework to train saliency detection models with diverse weak supervision sources to overcome issues characterizing saliency maps achieved with a single weak supervision source. Other very popular methods in [81], [82] and [83] are based on unsupervised approaches.…”

Section: ) Deep Neural Network Based Saliency Techniquesmentioning

confidence: 99%

A Multi-Scale Colour and Keypoint Density-Based Approach for Visual Saliency Detection

et al. 2020

View full text Add to dashboard Cite

In the first seconds of observation of an image, several visual attention processes are involved in the identification of the visual targets that pop-out from the scene to our eyes. Saliency is the quality that makes certain regions of an image stand out from the visual field and grab our attention. Saliency detection models, inspired by visual cortex mechanisms, employ both colour and luminance features. Furthermore, both locations of pixels and presence of objects influence the Visual Attention processes. In this paper, we propose a new saliency method based on the combination of the distribution of interest points in the image with multiscale analysis, a centre bias module and a machine learning approach. We use perceptually uniform colour spaces to study how colour impacts on the extraction of saliency. To investigate eye-movements and assess the performances of saliency methods over object-based images, we conduct experimental sessions on our dataset ETTO (Eye Tracking Through Objects). Experiments show our approach to be accurate in the detection of saliency concerning state-of-the-art methods and accessible eye-movement datasets. The performances over object-based images are excellent and consistent on generic pictures. Besides, our work reveals interesting findings on some relationships between saliency and perceptually uniform colour spaces.

show abstract

Section: ) Deep Neural Network Based Saliency Techniquesmentioning

confidence: 99%

A Multi-Scale Colour and Keypoint Density-Based Approach for Visual Saliency Detection

et al. 2020

View full text Add to dashboard Cite

show abstract

“…To alleviate this issue, there has been increasing interest in weakly and semi-supervised learning, which have been applied to salient object detection [185][186][187][188][189]. Semi-and weak supervision could also be introduced into RGB-D salient object detection, by leveraging image-level tags [185] and pseudo pixel-wise annotations [188,190], to improve detection performance. Furthermore, several studies [191,192] have suggested that models pretrained using self-supervision can effectively be used to achieve better performance.…”

Section: Different Supervision Strategiesmentioning

confidence: 99%

RGB-D salient object detection: A survey

et al. 2021

View full text Add to dashboard Cite

Salient object detection, which simulates human visual perception in locating the most significant object(s) in a scene, has been widely applied to various computer vision tasks. Now, the advent of depth sensors means that depth maps can easily be captured; this additional spatial information can boost the performance of salient object detection. Although various RGB-D based salient object detection models with promising performance have been proposed over the past several years, an in-depth understanding of these models and the challenges in this field remains lacking. In this paper, we provide a comprehensive survey of RGB-D based salient object detection models from various perspectives, and review related benchmark datasets in detail. Further, as light fields can also provide depth maps, we review salient object detection models and popular benchmark datasets from this domain too. Moreover, to investigate the ability of existing models to detect salient objects, we have carried out a comprehensive attribute-based evaluation of several representative RGB-D based salient object detection models. Finally, we discuss several challenges and open directions of RGB-D based salient object detection for future research. All collected models, benchmark datasets, datasets constructed for attribute-based evaluation, and related code are publicly available at https://github.com/taozh2017/RGBD-SODsurvey.

show abstract

“…l , Ac h and Ac l ) and the scaling factor r in Equation (8). To determine these hyperparameters, we conduct several sets of experiments in Section 6.4.3.…”

Section: Ip H Ipmentioning

confidence: 99%

“…The PASCAL-S dataset contains 850 images with cluttered scenes and is one of the most challenging salient object FIGURE 8 Qualitative comparisons between our salient object detection approach and other state-of-the-art methods. From left to right (columns): input image, ground truth, Amulet [10], UCF [11], DRFI [40], MR [16], SO [18] and MBS [41], DSR [15], MWS [8] and ours detection datasets. The ECSSD dataset has 1000 images with complex structures.…”

Section: Datasets and Evaluation Metricsmentioning

confidence: 99%

Weakly supervised salient object detection via double object proposals guidance

Zhou

Guo

Dai

et al. 2021

IET Image Processing

View full text Add to dashboard Cite

The weakly supervised methods for salient object detection are attractive, since they greatly release the burden of annotating time-consuming pixel-wise masks. However, the imagelevel annotations utilized by current weakly supervised salient object detection models are too weak to provide sufficient supervision for this dense prediction task. To this end, a weakly supervised salient object detection method is proposed via double object proposals guidance, which is generated under the supervision of double bounding boxes annotations. With the double object proposals, the authors' method is capable of capturing both accurate but incomplete salient foreground and background information, which contributes to generating saliency maps with uniformly highlighted saliency regions and effectively suppressed background. In addition, an unsupervised salient object segmentation method is proposed, taking advantage of the non-parametric statistical active contour model (NSACM), for segmenting salient objects with complete and compact boundaries. Experiments on five benchmark datasets show that the authors' weakly supervised salient object detection approach consistently outperforms other weakly supervised and unsupervised methods by a considerable margin, and even has comparable performance to the fully supervised ones.

show abstract

Multi-Source Weak Supervision for Saliency Detection

Cited by 152 publications

References 35 publications

A Multi-Scale Colour and Keypoint Density-Based Approach for Visual Saliency Detection

A Multi-Scale Colour and Keypoint Density-Based Approach for Visual Saliency Detection

RGB-D salient object detection: A survey

Weakly supervised salient object detection via double object proposals guidance

Contact Info

Product

Resources

About