The PASCAL Visual Object Classes Challenge

Deep learning with convolutional neural networks (deep ConvNets) has revolutionized computer vision through end-to-end learning, that is, learning from the raw data. There is increasing interest in using deep ConvNets for end-to-end EEG analysis, but a better understanding of how to design and train ConvNets for end-to-end EEG decoding and how to visualize the informative EEG features the ConvNets learn is still needed. Here, we studied deep ConvNets with a range of different architectures, designed for decoding imagined or executed tasks from raw EEG. Our results show that recent advances from the machine learning field, including batch normalization and exponential linear units, together with a cropped training strategy, boosted the deep ConvNets decoding performance, reaching at least as good performance as the widely used filter bank common spatial patterns (FBCSP) algorithm (mean decoding accuracies 82.1% FBCSP, 84.0% deep ConvNets). While FBCSP is designed to use spectral power modulations, the features used by ConvNets are not fixed a priori. Our novel methods for visualizing the learned features demonstrated that ConvNets indeed learned to use spectral power modulations in the alpha, beta, and high gamma frequencies, and proved useful for spatially mapping the learned features by revealing the topography of the causal contributions of features in different frequency bands to the decoding decision. Our study thus shows how to design and train ConvNets to decode task-related information from the raw EEG without handcrafted features and highlights the potential of deep ConvNets combined with advanced visualization techniques for EEG-based brain mapping. Hum Brain Mapp 38:5391-5420, 2017. © 2017 Wiley Periodicals, Inc.

Deep learning with convolutional neural networks for EEG decoding and visualization.

Hyperspectral remote sensing technology has advanced significantly in the past two decades. Current sensors onboard airborne and spaceborne platforms cover large areas of the Earth surface with unprecedented spectral, spatial, and temporal resolutions. These characteristics enable a myriad of applications requiring fine identification of materials or estimation of physical parameters. Very often, these applications rely on sophisticated and complex data analysis methods. The sources of difficulties are, namely, the high dimensionality and size of the hyperspectral data, the spectral mixing (linear and nonlinear), and the degradation mechanisms associated to the measurement process such as noise and atmospheric effects. This paper presents a tutorial/overview cross section of some relevant hyperspectral data analysis methods and algorithms, organized in six main topics: data fusion, unmixing, classification, target detection, physical parameter retrieval, and fast computing. In all topics, we describe the state-of-the-art, provide illustrative examples, and point to future challenges and research directions.

/pdf/hyperspectral-remote-sensing-data-analysis-and-future-1cxk3zgg98.pdf

Hyperspectral Remote Sensing Data Analysis and Future Challenges

For object detection, the two-stage approach (e.g., Faster R-CNN) has been achieving the highest accuracy, whereas the one-stage approach (e.g., SSD) has the advantage of high efficiency. To inherit the merits of both while overcoming their disadvantages, in this paper, we propose a novel single-shot based detector, called RefineDet, that achieves better accuracy than two-stage methods and maintains comparable efficiency of one-stage methods. RefineDet consists of two inter-connected modules, namely, the anchor refinement module and the object detection module. Specifically, the former aims to (1) filter out negative anchors to reduce search space for the classifier, and (2) coarsely adjust the locations and sizes of anchors to provide better initialization for the subsequent regressor. The latter module takes the refined anchors as the input from the former to further improve the regression accuracy and predict multi-class label. Meanwhile, we design a transfer connection block to transfer the features in the anchor refinement module to predict locations, sizes and class labels of objects in the object detection module. The multitask loss function enables us to train the whole network in an end-to-end way. Extensive experiments on PASCAL VOC 2007, PASCAL VOC 2012, and MS COCO demonstrate that RefineDet achieves state-of-the-art detection accuracy with high efficiency. Code is available at https://github.com/sfzhang15/RefineDet.

/pdf/single-shot-refinement-neural-network-for-object-detection-j6fdptx7kt.pdf

Single-Shot Refinement Neural Network for Object Detection

Objective Brain-computer interfaces (BCI) enable direct communication with a computer, using neural activity as the control signal. This neural signal is generally chosen from a variety of well-studied electroencephalogram (EEG) signals. For a given BCI paradigm, feature extractors and classifiers are tailored to the distinct characteristics of its expected EEG control signal, limiting its application to that specific signal. Convolutional neural networks (CNNs), which have been used in computer vision and speech recognition to perform automatic feature extraction and classification, have successfully been applied to EEG-based BCIs; however, they have mainly been applied to single BCI paradigms and thus it remains unclear how these architectures generalize to other paradigms. Here, we ask if we can design a single CNN architecture to accurately classify EEG signals from different BCI paradigms, while simultaneously being as compact as possible. Approach In this work we introduce EEGNet, a compact convolutional neural network for EEG-based BCIs. We introduce the use of depthwise and separable convolutions to construct an EEG-specific model which encapsulates well-known EEG feature extraction concepts for BCI. We compare EEGNet, both for within-subject and cross-subject classification, to current state-of-the-art approaches across four BCI paradigms: P300 visual-evoked potentials, error-related negativity responses (ERN), movement-related cortical potentials (MRCP), and sensory motor rhythms (SMR). Main results We show that EEGNet generalizes across paradigms better than, and achieves comparably high performance to, the reference algorithms when only limited training data is available across all tested paradigms. In addition, we demonstrate three different approaches to visualize the contents of a trained EEGNet model to enable interpretation of the learned features. Significance Our results suggest that EEGNet is robust enough to learn a wide variety of interpretable features over a range of BCI tasks. Our models can be found at: https://github.com/vlawhern/arl-eegmodels.

https://iopscience.iop.org/article/10.1088/1741-2552/aace8c/pdf

EEGNet: a compact convolutional neural network for EEG-based brain–computer interfaces

Recognizing an event in an image can be enhanced by detecting relevant objects in two ways: 1) indirectly utilizing object detection information within the unified architecture or 2) directly making use of the object detection output results. We introduce a novel approach, referred to as Doubly-injected Object Detection CNN (DOD-CNN), exploiting the object information in both ways for the task of event recognition. The structure of this network is inspired by the Integrated Object Detection CNN (IOD-CNN) where object information is indirectly exploited by the event recognition module through the shared portion of the network. In the DOD-CNN architecture, the intermediate object detection outputs are directly injected into the event recognition network while keeping the indirect sharing structure inherited from the IOD-CNN, thus being `doubly-injected'. We also introduce a batch pooling layer which constructs one representative feature map from multiple object hypotheses. We have demonstrated the effectiveness of injecting the object detection information in two different ways in the task of malicious event recognition.

DOD-CNN: Doubly-injecting Object Information for Event Recognition

Currently, accurate detection of natural phenomena, such as red tide, that adversely affect wildlife and human, using satellite images has been increasingly utilized. However, red tide detection on satellite images still remains a very hard task due to unpredictable nature of red tide occurrence, extreme sparsity of red tide samples, difficulties in accurate groundtruthing, etc. In this paper, we aim to tackle both the data sparsity and groundtruthing issues by primarily addressing two challenges: i) significant lack of hard examples of non-red tide that can enhance detection performance and ii) extreme data imbalance between red tide and non-red tide examples. In the proposed work, we devise a 9-layer fully convolutional network jointly optimized with two plug-in modules tailored to overcoming the two challenges: i) a hard negative example generator (HNG) to supplement the hard negative (non-red tide) examples and ii) cascaded online hard example mining (cOHEM) to ease the data imbalance. Our proposed network jointly trained with HNG and cOHEM provides state-of-the-art red tide detection accuracy on GOCI satellite images.

Discovering and Generating Hard Examples for Training a Red Tide Detector.

. We present a Momentum Re-identification (MoReID) framework that can leverage a very large number of negative samples in training for general re-identification task. The design of this framework is inspired by Momentum Contrast (MoCo), which uses a dictionary to store current and past batches to build a large set of encoded samples. As we find it less effective to use past positive samples which may be highly inconsistent to the encoded feature property formed with the current positive samples, MoReID is designed to use only a large number of negative samples stored in the dictionary. However, if we train the model using the widely used Triplet loss that uses only one sample to represent a set of positive/negative samples, it is hard to effectively leverage the enlarged set of negative samples acquired by the MoReID framework. To maximize the advantage of using the scaled-up negative sample set, we newly introduce Hard-distance Elastic loss (HE loss), which is capa-ble of using more than one hard sample to represent a large number of samples. Our experiments demonstrate that a large number of negative samples provided by MoReID framework can be utilized at full capacity only with the HE loss, achieving the state-of-the-art accuracy on three re-ID benchmarks, VeRi-776, Market-1501, and VeRi-Wild.

Negative Samples are at Large: Leveraging Hard-distance Elastic Loss for Re-identification

A novel approach for the fusion of heterogeneous object detection methods is proposed. In order to effectively integrate the outputs of multiple detectors, the level of ambiguity in each individual detection score is estimated using the precision/recall relationship of the corresponding detector. The main contribution of the proposed work is a novel fusion method, called Dynamic Belief Fusion (DBF), which dynamically assigns probabilities to hypotheses (target, non-target, intermediate state (target or non-target)) based on confidence levels in the detection results conditioned on the prior performance of individual detectors. In DBF, a joint basic probability assignment, optimally fusing information from all detectors, is determined by the Dempster's combination rule, and is easily reduced to a single fused detection score. Experiments on ARL and PASCAL VOC 07 datasets demonstrate that the detection accuracy of DBF is considerably greater than conventional fusion approaches as well as individual detectors used for the fusion.

Dynamic Belief Fusion for Object Detection

Brain–computer interfaces (BCIs) have traditionally been used to enable communication and control for paralyzed patients.1 However, it is also thought that BCIs hold promise for fulfilling the longstanding goal of creating artificial systems (i.e., which can perform with the adaptability, robustness, and general intelligence of humans). To augment the sensing and processing capabilities of such artificial systems, BCI systems can thus be used on healthy individuals. In this way, the biological machinery that enables human cognition can be leveraged. Image triage—a visual target search over a set of images—is a prime application for this new class of BCI. Humans can effortlessly identify target objects in scenes that stymie even the best machine vision techniques. Manual inspection by humans, however, is limited by the speed at which targets can be consciously detected and reported by a behavioral response. For example, when targets are identified by pressing a button, the button is typically pressed two to five images after the target image is shown (when the image stream is presented at 5Hz). This forces the observer to assume a distribution of images for the several images that precede the button press.2 In addition, humans perform inconsistently because of exogenous distractions or endogenous factors (e.g., fatigue), whereas computer vision algorithms offer constant and predictable performance. As an alternative, machine learning approaches can be applied to raw human neurophysiological data and thus reveal signals that are relevant to the detection of target images. Ultimately, this can increase both the accuracy and the response rate of image triage classification tasks. Indeed, in recent work, it has been shown that the classification performance in a rapid serial Figure 1. Illustrating the display of images during a rapid serial visual presentation (RSVP) task. In this case, the images are presented at 5Hz and the subjects are required to indicate (via a behavioral response) when an—infrequently occurring—target image is shown.

Heesung Kwon

Papers

DOD-CNN: Doubly-injecting Object Information for Event Recognition

Discovering and Generating Hard Examples for Training a Red Tide Detector.

Negative Samples are at Large: Leveraging Hard-distance Elastic Loss for Re-identification

Dynamic Belief Fusion for Object Detection

A novel convolutional neural network for deep-learning classification