Unsupervised image saliency detection with Gestalt-laws guided optimization and visual attention based refinement

IEEE Trans. on Image Process.

Zhang

et al. 2018

279

103

Abstract-In steerable filters, a filter of arbitrary orientation can be generated by a linear combination of a set of "basis filters". Steerable properties dominate the design of the traditional filters e.g., Gabor filters and endow features the capability of handling spatial transformations. However, such properties have not yet been well explored in the deep convolutional neural networks (DCNNs). In this paper, we develop a new deep model, namely Gabor Convolutional Networks (GCNs or Gabor CNNs), with Gabor filters incorporated into DCNNs such that the robustness of learned features against the orientation and scale changes can be reinforced. By manipulating the basic element of DCNNs, i.e., the convolution operator, based on Gabor filters, GCNs can be easily implemented and are readily compatible with any popular deep learning architecture. We carry out extensive experiments to demonstrate the promising performance of our GCNs framework and the results show its superiority in recognizing objects, especially when the scale and rotation changes take place frequently. Moreover, the proposed GCNs have much fewer network parameters to be learned and can effectively reduce the training complexity of the network, leading to a more compact deep learning model while still maintaining a high feature representation capacity. The source code can be found at https://github.com/bczhangbczhang .

Section: B Contributionsmentioning

confidence: 99%

Gabor Convolutional Networks

Luan

IEEE Trans. on Image Process.

Zhang

et al. 2018

279

103

“…It leads to quick processing of information, with an efficient information choice and concentration of the computing power on the crucial tasks [24]. [3] introduces the attention mechanism in the human cognitive system, with which human pays attention to the noteworthy information and ignores irrespective information [3,38,40]. In the cognitive computation area, the attention mechanism has been widely applied, such as the work to resolve the human visual neural computational problem [4] and that to model the retrieval mechanism of associations from the associative memory [34].…”

Section: Models Using the Attention Mechanismmentioning

confidence: 99%

Long Short-Term Attention

Zhong

Lin

Advances in Brain Inspired Cognitive Systems

et al. 2020

Attention is an important cognition process of humans, which helps humans concentrate on critical information during their perception and learning. However, although many machine learning models can remember information of data, they have no the attention mechanism. For example, the long short-term memory (LSTM) network is able to remember sequential information, but it cannot pay special attention to part of the sequences. In this paper, we present a novel model called long short-term attention (LSTA), which seamlessly integrates the attention mechanism into the inner cell of LSTM. More than processing long short term dependencies, LSTA can focus on important information of the sequences with the attention mechanism. Extensive experiments demonstrate that LSTA outperforms LSTM and related models on the sequence learning tasks.

“…In this study, we model the saliency of each corner-constraint patch by incorporating the Gestalt clues of perceptual grouping, including the laws of proximity and similarity, which can be described as follow [47,51]:…”

Section: Modeling Saliency Of Patches By Incorporating Gestalt Laws Omentioning

confidence: 99%

Automatic Extraction of Built-Up Areas from Very High-Resolution Satellite Imagery Using Patch-Level Spatial Features and Gestalt Laws of Perceptual Grouping

Huang

et al. 2019

Remote Sensing

Automatic extraction of built-up areas from very high-resolution (VHR) satellite images has received increasing attention in recent years. However, due to the complexity of spectral and spatial characteristics of built-up areas, it is still a challenging task to obtain their precise location and extent. In this study, a patch-based framework was proposed for unsupervised extraction of built-up areas from VHR imagery. First, a group of corner-constrained overlapping patches were defined to locate the candidate built-up areas. Second, for each patch, its salient textures and structural characteristics were represented as a feature vector using integrated high-frequency wavelet coefficients. Then, inspired by visual perception, a patch-level saliency model of built-up areas was constructed by incorporating Gestalt laws of proximity and similarity, which can effectively describe the spatial relationships between patches. Finally, built-up areas were extracted through thresholding and their boundaries were refined by morphological operations. The performance of the proposed method was evaluated on two VHR image datasets. The resulting average F-measure values were 0.8613 for the Google Earth dataset and 0.88 for the WorldView-2 dataset, respectively. Compared with existing models, the proposed method obtains better extraction results, which show more precise boundaries and preserve better shape integrity.