SuperCNN: A Superpixelwise Convolutional Neural Network for Salient Object Detection

He, Shengfeng; Lau, Rynson W. H.; Liu, Wenxi; Huang, Zhe; Yang, Qingxiong

doi:10.1007/s11263-015-0822-0

Cited by 264 publications

(117 citation statements)

References 48 publications

Supporting

Mentioning

117

Contrasting

Order By: Relevance

“…The random forest model [57] predicts image saliency by training a regressor on discriminative regional features. Most recently, multiple kernel learning [58] and convolutional neural network [59] techniques have been introduced to learn more robust discrimination between salient and non-salient regions.…”

Section: Related Workmentioning

confidence: 99%

Salient Object Detection via Structured Matrix Decomposition

Peng

Ling

et al. 2017

IEEE Trans. Pattern Anal. Mach. Intell.

343

210

View full text Add to dashboard Cite

Abstract-Low-rank recovery models have shown potential for salient object detection, where a matrix is decomposed into a low-rank matrix representing image background and a sparse matrix identifying salient objects. Two deficiencies, however, still exist. First, previous work typically assumes the elements in the sparse matrix are mutually independent, ignoring the spatial and pattern relations of image regions. Second, when the low-rank and sparse matrices are relatively coherent, e.g., when there are similarities between the salient objects and background or when the background is complicated, it is difficult for previous models to disentangle them. To address these problems, we propose a novel structured matrix decomposition model with two structural regularizations: (1) a tree-structured sparsity-inducing regularization that captures the image structure and enforces patches from the same object to have similar saliency values, and (2) a Laplacian regularization that enlarges the gaps between salient objects and the background in feature space. Furthermore, high-level priors are integrated to guide the matrix decomposition and boost the detection. We evaluate our model for salient object detection on five challenging datasets including single object, multiple objects and complex scene images, and show competitive results as compared with 24 state-of-the-art methods in terms of seven performance metrics.

show abstract

Section: Related Workmentioning

confidence: 99%

Salient Object Detection via Structured Matrix Decomposition

Peng

Ling

et al. 2017

IEEE Trans. Pattern Anal. Mach. Intell.

343

210

View full text Add to dashboard Cite

show abstract

“…One of our future work is to extend the spatial kernel of LSH, which is currently an exponential kernel, to a general kernel. On the other hand, as many vision problems can be modeled with histograms, another future work will focus on exploring more potential applications (e.g., saliency detection [20], [19]) of two efficient histograms.…”

Section: Discussionmentioning

confidence: 99%

“…However, the complexity of the joint bilateral filter in Eq. (19) is exponential in N . Thus, the computational complexity of the whole algorithm is linear in the image size but exponential in dimensions.…”

Section: Complexity Analysismentioning

confidence: 99%

Fast Weighted Histograms for Bilateral Filtering and Nearest Neighbor Searching

Yang

Lau

et al. 2016

IEEE Trans. Circuits Syst. Video Technol.

Self Cite

View full text Add to dashboard Cite

The locality sensitive histogram (LSH) injects spatial information into the local histogram in an efficient manner, and has been demonstrated to be very effective for visual tracking. In this paper, we explore the application of this efficient histogram in two important problems. We first extend the LSH to linear time bilateral filtering, and then propose a new type of histogram for efficiently computing edge-preserving nearest neighbor fields (NNF). While existing histogram-based bilateral filtering methods are the state-ofthe-art for efficient grayscale image processing, they are limited to box spatial filter kernels only. In our first application, we address this limitation by expressing the bilateral filter as a simple ratio of linear functions of the LSH, which is able to extend the box spatial kernel to an exponential kernel. The computational complexity of the proposed bilateral filter is linear in the number of image pixels. In our second application, we derive a new bilateral weighted histogram (BWH) for NNF. The new histogram maintains the efficiency of LSH, which allows approximate NNF to be computed independent of patch size. In addition, BWH takes into account both spatial and color information, and thus provides higher accuracy for histogram-based matching, especially around color edges.Index Terms-locality sensitive histograms, bilateral weighted histograms, bilateral filtering, nearest neighbor searching, edge-preserving smoothing.

show abstract

“…For example, Han et al [44] proposed multi-stream stacked denoising autoencoders that can detect salient regions by measuring the reconstruction residuals that reflect the distinctness between background and salient regions. He et al [45] adopted CNNs to characterize superpixels with hierarchical features so as to detect salient objects at multiple scales, while the superpixel-based saliency computation was used by [25], [46] as well. Considering that the task of fixation prediction is tightly correlated with SOD, a unified deep network was proposed in [47] for simultaneous fixation prediction and image-based SOD.…”

Section: B Modelsmentioning

confidence: 99%

A Benchmark Dataset and Saliency-Guided Stacked Autoencoders for Video-Based Salient Object Detection

Xia

Chen

2018

IEEE Trans. on Image Process.

131

View full text Add to dashboard Cite

Abstract-Image-based salient object detection (SOD) has been extensively studied in the past decades. However, videobased SOD is much less explored since there lack large-scale video datasets within which salient objects are unambiguously defined and annotated. Toward this end, this paper proposes a video-based SOD dataset that consists of 200 videos (64 minutes). In constructing the dataset, we manually annotate all objects and regions over 7,650 uniformly sampled keyframes and collect the eye-tracking data of 23 subjects that freeview all videos. From the user data, we find salient objects in video can be defined as objects that consistently pop-out throughout the video, and objects with such attributes can be unambiguously annotated by combining manually annotated object/region masks with eye-tracking data of multiple subjects. To the best of our knowledge, it is currently the largest dataset for video-based salient object detection.Based on this dataset, this paper proposes an unsupervised baseline approach for video-based SOD by using saliencyguided stacked autoencoders. In the proposed approach, multiple spatiotemporal saliency cues are first extracted at pixel, superpixel and object levels. With these saliency cues, stacked autoencoders are unsupervisedly constructed which automatically infer a saliency score for each pixel by progressively encoding the high-dimensional saliency cues gathered from the pixel and its spatiotemporal neighbors. Experimental results show that the proposed unsupervised approach outperforms 30 state-of-the-art models on the proposed dataset, including 19 image-based & classic (unsupervised or non-deep learning), 6 image-based & deep learning, and 5 video-based & unsupervised. Moreover, benchmarking results show that the proposed dataset is very challenging and has the potential to boost the development of video-based SOD.

show abstract

SuperCNN: A Superpixelwise Convolutional Neural Network for Salient Object Detection

Cited by 264 publications

References 48 publications

Salient Object Detection via Structured Matrix Decomposition

Salient Object Detection via Structured Matrix Decomposition

Fast Weighted Histograms for Bilateral Filtering and Nearest Neighbor Searching

A Benchmark Dataset and Saliency-Guided Stacked Autoencoders for Video-Based Salient Object Detection

Contact Info

Product

Resources

About