A Natural Images Pre-Trained Deep Learning Method for Seismic Random Noise Attenuation

Seismic field data are usually contaminated by random or complex noise, which seriously affect the quality of seismic data contaminating seismic imaging and seismic interpretation. Improving the signal-to-noise ratio (SNR) of seismic data has always been a key step in seismic data processing. Deep learning approaches have been successfully applied to suppress seismic random noise. The training examples are essential in deep learning methods, especially for the geophysical problems, where the complete training data are not easy to be acquired due to high cost of acquisition. In this work, we propose a natural images pre-trained deep learning method to suppress seismic random noise through insight of the transfer learning. Our network contains pre-trained and post-trained networks: the former is trained by natural images to obtain the preliminary denoising results, while the latter is trained by a small amount of seismic images to fine-tune the denoising effects by semi-supervised learning to enhance the continuity of geological structures. The results of four types of synthetic seismic data and six field data demonstrate that our network has great performance in seismic random noise suppression in terms of both quantitative metrics and intuitive effects.

Slow Feature Extraction Algorithm Based on Visual Selection Consistency Continuity and Its Application

The conventional slow feature analysis (SFA) algorithm has no support of computational theory of vision for primates, nor does it have the ability to learn the global features with visual selection consistency continuity. And what is more, the algorithm is highly complex. Based on this, Slow Feature Extraction Algorithm Based on Visual selection consistency continuity and Its Application was proposed. Inspired by the visual selection consistency continuity theory for primates, this paper replaced the principal component analysis (PCA) method of the conventional SFA algorithm with the myTICA method, extracted the Gabor basis functions of natural images, initialized the basis function family; it used the feature basis expansion algorithm based on visual selection consistency continuity (the VSCC_FBEA algorithm) to replace the polynomial expansion method in the original SFA algorithm to generates the Gabor basis functions of features with long and short-term visual selectivity in the family of basis functions, which solved the drawbacks of the polynomial prediction algorithm; it also designed the Lipschitz consistency constraint, and proposed the Lipschitz-Orthogonal-Pruning-Method (LOPM algorithm) to optimize the basis function family into an over-complete family of basis functions. In addition, this paper used the feature expression method based on visual invariance theory (visual invariance theory -FEM) to establish the set of features of natural images with visual selection consistency continuity. Subsequently, it adopted three error evaluation methods and mySFA classification method to evaluate the proposed algorithm. According to the experimental results, the proposed algorithm showed good prediction performance with respect to the LSVRC2012 data set; compared with the SFA, GSFA, TICA, myICA and mySFA algorithms, the proposed algorithm is correct and feasible; when the classification threshold of the algorithm was set at 8.0, the recognition rate of the proposed algorithm reached 99.66%, and neither of the false recognition rate and the false rejection rate was higher than 0.33%. The proposed algorithm has good performance in prediction and classification, and also shows good anti-noise capacity under limited noise conditions.

Introducing the Prototypical Stimulus Characteristics Toolbox: Protosc

Many studies use different categories of images to define their conditions. Since any difference between these categories is a valid candidate to explain category-related behavioral differences, knowledge about the objective image differences between categories is crucial for the interpretation of the behaviors. However, natural images vary in many image features and not every feature is equally important in describing the differences between the categories. Here, we provide a methodological approach to find as many of the image features as possible, using machine learning performance as a tool, that have predictive value over the category the images belong to. In other words, we describe a means to find the features of a group of images by which the categories can be objectively and quantitatively defined. Note that we are not aiming to provide a means for the best possible decoding performance; instead, our aim is to uncover prototypical characteristics of the categories. To facilitate the use of this method, we offer an open-source, MATLAB-based toolbox that performs such an analysis and aids the user in visualizing the features of relevance. We first applied the toolbox to a mock data set with a ground truth to show the sensitivity of the approach. Next, we applied the toolbox to a set of natural images as a more practical example.

Demonstration of light reflection concepts for rendering realistic 3D tree images

With advancements in computer graphics, creating natural images has always been the main purpose, image rendering is all based on principles of physics. So, understanding the physics of image rendering will enable us to create the most realistic images. A ray of light hit a surface with different orientation and reflects as per the rules of physics. It is difficult to calculate the light reflection of complex foliage, such as trees, so, the reflection of this natural complexity needs to be adapted to rendering situations. In this research, the researchers provide demonstrations to enable students to understand the light reflection in nature, light calculation in computer graphics and methods to apply them to render realistic tree images. The researchers assign students to render 3D realistic tree images to assess the students’ understanding by applying the diffuse reflection value, specular reflection value and surface normal direction to render realistic tree images. The researchers find that most students understand of diffuse reflection, specular reflection, and surface normal direction causes the rendering results to be most realistic.

Emergence of Lie Symmetries in Functional Architectures Learned by CNNs

In this paper we study the spontaneous development of symmetries in the early layers of a Convolutional Neural Network (CNN) during learning on natural images. Our architecture is built in such a way to mimic some properties of the early stages of biological visual systems. In particular, it contains a pre-filtering step ℓ0 defined in analogy with the Lateral Geniculate Nucleus (LGN). Moreover, the first convolutional layer is equipped with lateral connections defined as a propagation driven by a learned connectivity kernel, in analogy with the horizontal connectivity of the primary visual cortex (V1). We first show that the ℓ0 filter evolves during the training to reach a radially symmetric pattern well approximated by a Laplacian of Gaussian (LoG), which is a well-known model of the receptive profiles of LGN cells. In line with previous works on CNNs, the learned convolutional filters in the first layer can be approximated by Gabor functions, in agreement with well-established models for the receptive profiles of V1 simple cells. Here, we focus on the geometric properties of the learned lateral connectivity kernel of this layer, showing the emergence of orientation selectivity w.r.t. the tuning of the learned filters. We also examine the short-range connectivity and association fields induced by this connectivity kernel, and show qualitative and quantitative comparisons with known group-based models of V1 horizontal connections. These geometric properties arise spontaneously during the training of the CNN architecture, analogously to the emergence of symmetries in visual systems thanks to brain plasticity driven by external stimuli.

Visual prototypes in the ventral stream are attuned to complexity and gaze behavior

Early theories of efficient coding suggested the visual system could compress the world by learning to represent features where information was concentrated, such as contours. This view was validated by the discovery that neurons in posterior visual cortex respond to edges and curvature. Still, it remains unclear what other information-rich features are encoded by neurons in more anterior cortical regions (e.g., inferotemporal cortex). Here, we use a generative deep neural network to synthesize images guided by neuronal responses from across the visuocortical hierarchy, using floating microelectrode arrays in areas V1, V4 and inferotemporal cortex of two macaque monkeys. We hypothesize these images (“prototypes”) represent such predicted information-rich features. Prototypes vary across areas, show moderate complexity, and resemble salient visual attributes and semantic content of natural images, as indicated by the animals’ gaze behavior. This suggests the code for object recognition represents compressed features of behavioral relevance, an underexplored aspect of efficient coding.