AI vs. AI: Can AI Detect AI-Generated Images?

The proliferation of Artificial Intelligence (AI) models such as Generative Adversarial Networks (GANs) has shown impressive success in image synthesis. Artificial GAN-based synthesized images have been widely spread over the Internet with the advancement in generating naturalistic and photo-realistic images. This might have the ability to improve content and media; however, it also constitutes a threat with regard to legitimacy, authenticity, and security. Moreover, implementing an automated system that is able to detect and recognize GAN-generated images is significant for image synthesis models as an evaluation tool, regardless of the input modality. To this end, we propose a framework for reliably detecting AI-generated images from real ones through Convolutional Neural Networks (CNNs). First, GAN-generated images were collected based on different tasks and different architectures to help with the generalization. Then, transfer learning was applied. Finally, several Class Activation Maps (CAM) were integrated to determine the discriminative regions that guided the classification model in its decision. Our approach achieved 100% on our dataset, i.e., Real or Synthetic Images (RSI), and a superior performance on other datasets and configurations in terms of its accuracy. Hence, it can be used as an evaluation tool in image generation. Our best detector was a pre-trained EfficientNetB4 fine-tuned on our dataset with a batch size of 64 and an initial learning rate of 0.001 for 20 epochs. Adam was used as an optimizer, and learning rate reduction along with data augmentation were incorporated.

MANet: Multi-branch attention auxiliary learning for lung nodule detection and segmentation.

BACKGROUND AND OBJECTIVE: Pulmonary nodule detection and segmentation are currently two primary tasks in analyzing chest computed tomography (Chest CT) in order to detect signs of lung cancer, thereby providing early treatment measures to reduce mortality. Even though there are many proposed methods to reduce false positives for obtaining effective detection results, distinguishing between the pulmonary nodule and background region remains challenging because their biological characteristics are similar and varied in size. The purpose of our work is to propose a method for automatic nodule detection and segmentation in Chest CT by enhancing the feature information of pulmonary nodules. METHODS: We propose a new UNet-based backbone with multi-branch attention auxiliary learning mechanism, which contains three novel modules, namely, Projection module, Fast Cascading Context module, and Boundary Enhancement module, to further enhance the nodule feature representation. Based on that, we build MANet, a lung nodule localization network that simultaneously detects and segments precise nodule positions. Furthermore, our MANet contains a Proposal Refinement step which refines initially generated proposals to effectively reduce false positives and thereby produce the segmentation quality. RESULTS: Comprehensive experiments on the combination of two benchmarks LUNA16 and LIDC-IDRI show that our proposed model outperforms state-of-the-art methods in the tasks of nodule detection and segmentation tasks in terms of FROC, IoU, and DSC metrics. Our method reports an average FROC score of 88.11% in lung nodule detection. For the lung nodule segmentation, the results reach an average IoU score of 71.29% and a DSC score of 82.74%. The ablation study also shows the effectiveness of the new modules which can be integrated into other UNet-based models. CONCLUSIONS: The experiments demonstrated our method with multi-branch attention auxiliary learning ability are a promising approach for detecting and segmenting the pulmonary nodule instances compared to the original UNet design.

Instance-Level Few-Shot Learning With Class Hierarchy Mining.

Few-shot learning is proposed to tackle the problem of scarce training data in novel classes. However, prior works in instance-level few-shot learning have paid less attention to effectively utilizing the relationship between categories. In this paper, we exploit the hierarchical information to leverage discriminative and relevant features of base classes to effectively classify novel objects. These features are extracted from abundant data of base classes, which could be utilized to reasonably describe classes with scarce data. Specifically, we propose a novel superclass approach that automatically creates a hierarchy considering base and novel classes as fine-grained classes for few-shot instance segmentation (FSIS). Based on the hierarchical information, we design a novel framework called Soft Multiple Superclass (SMS) to extract relevant features or characteristics of classes in the same superclass. A new class assigned to the superclass is easier to classify by leveraging these relevant features. Besides, in order to effectively train the hierarchy-based-detector in FSIS, we apply the label refinement to further describe the associations between fine-grained classes. The extensive experiments demonstrate the effectiveness of our method on FSIS benchmarks. The source code is available here: https://github.com/nvakhoa/superclass-FSIS.

Multimodal Mutual Information Maximization: A Novel Approach for Unsupervised Deep Cross-Modal Hashing.

In this article, we adopt the maximizing mutual information (MI) approach to tackle the problem of unsupervised learning of binary hash codes for efficient cross-modal retrieval. We proposed a novel method, dubbed cross-modal info-max hashing (CMIMH). First, to learn informative representations that can preserve both intramodal and intermodal similarities, we leverage the recent advances in estimating variational lower bound of MI to maximizing the MI between the binary representations and input features and between binary representations of different modalities. By jointly maximizing these MIs under the assumption that the binary representations are modeled by multivariate Bernoulli distributions, we can learn binary representations, which can preserve both intramodal and intermodal similarities, effectively in a mini-batch manner with gradient descent. Furthermore, we find out that trying to minimize the modality gap by learning similar binary representations for the same instance from different modalities could result in less informative representations. Hence, balancing between reducing the modality gap and losing modality-private information is important for the cross-modal retrieval tasks. Quantitative evaluations on standard benchmark datasets demonstrate that the proposed method consistently outperforms other state-of-the-art cross-modal retrieval methods.

Revisiting natural user interaction in virtual world.

Natural user interaction in virtual environment is a prominent factor in any mixed reality applications. In this paper, we revisit the assessment of natural user interaction via a case study of a virtual aquarium. Viewers with the wearable headsets are able to interact with virtual objects via head orientation, gaze, gesture, and visual markers. The virtual environment is operated on both Google Cardboard and HoloLens, the two popular wireless head-mounted displays. Evaluation results reveal the preferences of users over different natural user interaction methods.

Intensified salinity intrusion in coastal aquifers due to groundwater overextraction: a case study in the Mekong Delta, Vietnam.

Groundwater salinization is one of the most severe environmental problems in coastal aquifers worldwide, causing exceeding salinity in groundwater supply systems for many purposes. High salinity concentration in groundwater can be detected several kilometers inland and may result in an increased risk for coastal water supply systems and human health problems. This study investigates the impacts of groundwater pumping practices and regional groundwater flow dynamics on groundwater flow and salinity intrusion in the coastal aquifers of the Vietnamese Mekong Delta using the SEAWAT model-a variable-density groundwater flow and solute transport model. The model was constructed in three dimensions (3D) and accounted for multi-aquifers, variation of groundwater levels in neighboring areas, pumping, and paleo-salinity. Model calibration was carried for 13 years (2000 to 2012), and validation was conducted for 4 years (2013 to 2016). The best-calibrated model was used to develop prediction models for the next 14 years (2017 to 2030). Six future scenarios were introduced based on pumping rates and regional groundwater levels. Modeling results revealed that groundwater pumping activities and variation of regional groundwater flow systems strongly influence groundwater level depletion and saline movement from upper layers to lower layers. High salinity (>2.0 g/L) was expected to expand downward up to 150 m in depth and 2000 m toward surrounding areas in the next 14 years under increasing groundwater pumping capacity. A slight recovery in water level was also observed with decreasing groundwater exploitation. The reduction in the pumping rate from both local and regional scales will be necessary to recover groundwater levels and protect fresh aquifers from expanding paleo-saline in groundwater.

Camouflaged Instance Segmentation In-the-Wild: Dataset, Method, and Benchmark Suite.

This paper pushes the envelope on decomposing camouflaged regions in an image into meaningful components, namely, camouflaged instances. To promote the new task of camouflaged instance segmentation of in-the-wild images, we introduce a dataset, dubbed CAMO++, that extends our preliminary CAMO dataset (camouflaged object segmentation) in terms of quantity and diversity. The new dataset substantially increases the number of images with hierarchical pixel-wise ground truths. We also provide a benchmark suite for the task of camouflaged instance segmentation. In particular, we present an extensive evaluation of state-of-the-art instance segmentation methods on our newly constructed CAMO++ dataset in various scenarios. We also present a camouflage fusion learning (CFL) framework for camouflaged instance segmentation to further improve the performance of state-of-the-art methods. The dataset, model, evaluation suite, and benchmark will be made publicly available on our project page.

Masked Face Analysis via Multi-Task Deep Learning.

Face recognition with wearable items has been a challenging task in computer vision and involves the problem of identifying humans wearing a face mask. Masked face analysis via multi-task learning could effectively improve performance in many fields of face analysis. In this paper, we propose a unified framework for predicting the age, gender, and emotions of people wearing face masks. We first construct FGNET-MASK, a masked face dataset for the problem. Then, we propose a multi-task deep learning model to tackle the problem. In particular, the multi-task deep learning model takes the data as inputs and shares their weight to yield predictions of age, expression, and gender for the masked face. Through extensive experiments, the proposed framework has been found to provide a better performance than other existing methods.

Olympic Games Event Recognition via Transfer Learning with Photobombing Guided Data Augmentation.

Automatic event recognition in sports photos is both an interesting and valuable research topic in the field of computer vision and deep learning. With the rapid increase and the explosive spread of data, which is being captured momentarily, the need for fast and precise access to the right information has become a challenging task with considerable importance for multiple practical applications, i.e., sports image and video search, sport data analysis, healthcare monitoring applications, monitoring and surveillance systems for indoor and outdoor activities, and video captioning. In this paper, we evaluate different deep learning models in recognizing and interpreting the sport events in the Olympic Games. To this end, we collect a dataset dubbed Olympic Games Event Image Dataset (OGED) including 10 different sport events scheduled for the Olympic Games Tokyo 2020. Then, the transfer learning is applied on three popular deep convolutional neural network architectures, namely, AlexNet, VGG-16 and ResNet-50 along with various data augmentation methods. Extensive experiments show that ResNet-50 with the proposed photobombing guided data augmentation achieves 90% in terms of accuracy.

Unsupervised Deep Cross-modality Spectral Hashing.

This paper presents a novel framework, namely Deep Cross-modality Spectral Hashing (DCSH), to tackle the unsupervised learning problem of binary hash codes for efficient cross-modal retrieval. The framework is a two-step hashing approach which decouples the optimization into (1) binary optimization and (2) hashing function learning. In the first step, we propose a novel spectral embedding-based algorithm to simultaneously learn single-modality and binary cross-modality representations. While the former is capable of well preserving the local structure of each modality, the latter reveals the hidden patterns from all modalities. In the second step, to learn mapping functions from informative data inputs (images and word embeddings) to binary codes obtained from the first step, we leverage the powerful CNN for images and propose a CNN-based deep architecture to learn text modality. Quantitative evaluations on three standard benchmark datasets demonstrate that the proposed DCSH method consistently outperforms other state-of-the-art methods.

Simultaneous Feature Aggregating and Hashing for Compact Binary Code Learning.

Representing images by compact hash codes is an attractive approach for large-scale content-based image retrieval. In most state-of-the-art hashing-based image retrieval systems, for each image, local descriptors are first aggregated as a global representation vector. This global vector is then subjected to a hashing function to generate a binary hash code. In previous works, the aggregating and the hashing processes are designed independently. Hence, these frameworks may generate suboptimal hash codes. In this paper, we first propose a novel unsupervised hashing framework in which feature aggregating and hashing are designed simultaneously and optimized jointly. Specifically, our joint optimization generates aggregated representations that can be better reconstructed by some binary codes. This leads to more discriminative binary hash codes and improved retrieval accuracy. In addition, the proposed method is flexible. It can be extended for supervised hashing. When the data label is available, the framework can be adapted to learn binary codes which minimize the reconstruction loss with respect to label vectors. Furthermore, we also propose a fast version of the state-of-the-art hashing method Binary Autoencoder to be used in our proposed frameworks. Extensive experiments on benchmark datasets under various settings show that the proposed methods outperform the state-of-the-art unsupervised and supervised hashing methods.

Semantic Prior Analysis for Salient Object Detection.

Salient object detection aims to detect the main objects in the given image. In this paper, we proposed an approach that integrates semantic priors into the salient object detection process. The method first obtains an explicit saliency map that is refined by the explicit semantic priors learned from data. Then an implicit saliency map is constructed using a trained model that maps the implicit semantic priors embedded into superpixel features with the saliency values. Next, the fusion saliency map is computed by adaptively fusing both the explicit and implicit semantic maps. The final saliency map is eventually computed via the post-processing refinement step. Experimental results have demonstrated the effectiveness of the proposed method, particularly, it achieves competitive performance with the state-of-the-art baselines on three challenging datasets, namely, ECSSD, HKUIS, and iCoSeg.

Risk factors for anemia in Vietnam.

Anemia is a significant public health problem in Vietnam, but representative national data and comprehensive risk factors analysis are lacking. The objectives of this study were to: 1) determine the distribution and severity of anemia in Vietnam, and 2) to assess potential risk factors for anemia. Nine thousand five hundred fifty households in 53 provinces were covered using a stratified two-stage cluster survey carried out in 1995. Selected household members were interviewed; intestinal helminthes were tested in non-pregnant women by Kato-Katz technique; hemoglobin concentrations were measured with Hemocue. Data were weighted and analyzed by survey procedures using SAS 9.0. Overall, 60% of children under 2 years old, 53% of pregnant women, 40% of non-pregnant women and 15.6% of men were anemic. Hookworm infection was the strongest factor associated with anemia (OR = 1.7; 2.9 and 4.5 for 11,999, 2,000-3,999 and > or = 4,000 hookworm egg counts, respectively) and accounted for 22% of anemia. Hookworm intensity was significantly associated with hemoglobin level; for each 1,000 egg increase, hemoglobin was reduced by 2.4 g/l. Living in different ecological zones, eating < 1 serving of meat/ week, and farming were significantly associated with anemia in women and children. Other risk factors in women included having > 3 children and having a child < 24 months old. In men, no variables were found significantly associated with anemia.