Gated Contextual Features for Salient Object Detection

Gupta, Ashish Kumar; Seal, Ayan; Khanna, Pritee; Yazidi, Anis; Krejcar, Ondřej

doi:10.1109/tim.2021.3064423

Cited by 12 publications

(6 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this section, ablation studies were uesd to discuss the effect of the fully convolutional (FC) neural network, Channel-Attention (CA) mechanism, Channel-Shuffle (CS) mechanism, and Inverted-Residual (IR) block. Referring to the ablation studies in literature [41,42], we design four variants of our ASIR-Net as follows for comparison:…”

Section: Discussionmentioning

confidence: 99%

A Lightweight Fully Convolutional Neural Network for SAR Automatic Target Recognition

Zhou

et al. 2021

Remote Sensing

View full text Add to dashboard Cite

Automatic target recognition (ATR) in synthetic aperture radar (SAR) images has been widely used in civilian and military fields. Traditional model-based methods and template matching methods do not work well under extended operating conditions (EOCs), such as depression angle variant, configuration variant, and noise corruption. To improve the recognition performance, methods based on convolutional neural networks (CNN) have been introduced to solve such problems and have shown outstanding performance. However, most of these methods rely on continuously increasing the width and depth of networks. This adds a large number of parameters and computational overhead, which is not conducive to deployment on edge devices. To solve these problems, a novel lightweight fully convolutional neural network based on Channel-Attention mechanism, Channel-Shuffle mechanism, and Inverted-Residual block, namely the ASIR-Net, is proposed in this paper. Specifically, we deploy Inverted-Residual blocks to extract features in high-dimensional space with fewer parameters and design a Channel-Attention mechanism to distribute different weights to different channels. Then, in order to increase the exchange of information between channels, we introduce the Channel-Shuffle mechanism into the Inverted-Residual block. Finally, to alleviate the matter of the scarcity of SAR images and strengthen the generalization performance of the network, four approaches of data augmentation are proposed. The effect and generalization performance of the proposed ASIR-Net have been proved by a lot of experiments under both SOC and EOCs on the MSTAR dataset. The experimental results indicate that ASIR-Net achieves higher recognition accuracy rates under both SOC and EOCs, which is better than the existing excellent ATR methods.

show abstract

Section: Discussionmentioning

confidence: 99%

A Lightweight Fully Convolutional Neural Network for SAR Automatic Target Recognition

Zhou

et al. 2021

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…For example, Liu et al [23] proposed a contextual information guidance strategy for multilevel information integration towards salient object detection. Gupta et al [25] proposed a gate-based context extraction module to emphasize invariance features for different scales of visual patterns. Siris et al [26] exploited the semantic scene contexts to learn the salient objects from the scene.…”

Section: A Cnns For Salient Object Detectionmentioning

confidence: 99%

Disentangled Capsule Routing for Fast Part-Object Relational Saliency

Liu

Zhang²,

Liu

et al. 2022

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

Recently, the Part-Object Relational (POR) saliency underpinned by the Capsule Network (CapsNet) has been demonstrated to be an effective modeling mechanism to improve the saliency detection accuracy. However, it is widely known that the current capsule routing operations have huge computational complexity, which seriously limited the usability of the POR saliency models in real-time applications. To this end, this paper takes an early step towards a fast POR saliency inference by proposing a novel disentangled part-object relational network. Concretely, we disentangle horizontal routing and vertical routing from the original omnidirectional capsule routing, thus generating Disentangled Capsule Routing (DCR). This mechanism enjoys two advantages. On one hand, DCR that disentangles orthogonal 1D (i.e., vertical and horizontal) routing greatly reduces parameters and routing complexity, resulting in much faster inference than omnidirectional 2D routing adopted by existing CapsNets. On the other hand, thanks to the light POR cues explored by DCR, we could conveniently integrate the part-object routing process to different feature layers in CNN, rather than just applying it to the small-scaled one as in previous works. This helps to increase saliency inference accuracy. Compared to previous POR saliency detectors, DPORTNet infers visual saliency (5 ∼ 9) × faster, and is more accurate. DPORTNet is available under the open-source license at https://github.com/liuyi1989/DCR.

show abstract

“…Next, the salience map is obtained in gbvsResult (Algorithm A3) (2). This algorithm is responsible for using an individual generated by the GP to process the input image and convert it into a salience map and store it in salMap (3). The masks, candidate segments, segment numbers and MCG features are stored in masks, maskCCs, numSegs, mcg_feats respectively (Algorithm A4) (4).…”

Section: Appendix Amentioning

confidence: 99%

“…Next, the channels (dimensions for the GP) to be used are chosen (2). The Gabor angles to use, the subsampling levels, the tolerance level of the eigenvector equilibrium mechanism, and the minimum subsampling size are established (3)(4)(5)(6). The individual generated by the GP is also stored as well as the control variables and weights (7)(8)(9).…”

Section: Outputmentioning

confidence: 99%

“…Giving a robot/machine this ability will allow it to choose/differentiate the most relevant information. Learning the algorithm for detecting and segmenting salient objects from natural scenes has attracted great interest in computer vision [2], instrumentation and measurement [3], pattern analysis [4], and recently by people working with genetic programming [5,6]. While many models and applications have emerged, a deep understanding of the inner workings remains lacking.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Automated Design of Salient Object Detection Algorithms with Brain Programming

et al. 2022

View full text Add to dashboard Cite

Despite recent improvements in computer vision, artificial visual systems’ design is still daunting since an explanation of visual computing algorithms remains elusive. Salient object detection is one problem that is still open due to the difficulty of understanding the brain’s inner workings. Progress in this research area follows the traditional path of hand-made designs using neuroscience knowledge or, more recently, deep learning, a particular branch of machine learning. Recently, a different approach based on genetic programming appeared to enhance handcrafted techniques following two different strategies. The first method follows the idea of combining previous hand-made methods through genetic programming and fuzzy logic. The second approach improves the inner computational structures of basic hand-made models through artificial evolution. This research proposes expanding the artificial dorsal stream using a recent proposal based on symbolic learning to solve salient object detection problems following the second technique. This approach applies the fusion of visual saliency and image segmentation algorithms as a template. The proposed methodology discovers several critical structures in the template through artificial evolution. We present results on a benchmark designed by experts with outstanding results in an extensive comparison with the state of the art, including classical methods and deep learning approaches to highlight the importance of symbolic learning in visual saliency.

show abstract

Gated Contextual Features for Salient Object Detection

Cited by 12 publications

References 52 publications

A Lightweight Fully Convolutional Neural Network for SAR Automatic Target Recognition

A Lightweight Fully Convolutional Neural Network for SAR Automatic Target Recognition

Disentangled Capsule Routing for Fast Part-Object Relational Saliency

Automated Design of Salient Object Detection Algorithms with Brain Programming

Contact Info

Product

Resources

About