Image Classification on Accelerated Neural Networks

For image classification problems, various neural network models are commonly used due to their success in yielding high accuracies. Convolutional Neural Network (CNN) is one of the most frequently used deep learning methods for image classification applications. It may produce extraordinarily accurate results with regard to its complexity. However, the more complex the model is the longer it takes to train. In this paper, an acceleration design that uses the power of FPGA is given for a basic CNN model which consists of one convolutional layer and one fully connected layer for the training phase of the fully connected layer. Nonetheless, inference phase is also accelerated automatically due to the fact that training phase includes inference. In this design, the convolutional layer is calculated by the host computer and the fully connected layer is calculated by an FPGA board. It should be noted that the training of convolutional layer is not taken into account in this design and is left for future research. The results are quite encouraging as this FPGA design tops the performance of some of the state-of-the-art deep learning platforms such as Tensorflow on the host computer approximately 2 times in both training and inference.

The Ability of Image-Language Explainable Models to Resemble Domain Expertise

Recent advances in vision and language (V+L) models have a promising impact in the healthcare field. However, such models struggle to explain how and why a particular decision was made. In addition, model transparency and involvement of domain expertise are critical success factors for machine learning models to make an entrance into the field. In this work, we study the use of the local surrogate explainability technique to overcome the problem of black-box deep learning models. We explore the feasibility of resembling domain expertise using the local surrogates in combination with an underlying V+L to generate multi-modal visual and language explanations. We demonstrate that such explanations can serve as helpful feedback in guiding model training for data scientists and machine learning engineers in the field.

Low-Light Hyperspectral Image Enhancement

Due to inadequate energy captured by the hyperspectral camera sensor in poor illumination conditions, low-light hyperspectral images (HSIs) usually suffer from low visibility, spectral distortion, and various noises. A range of HSI restoration methods have been developed, yet their effectiveness in enhancing low-light HSIs is constrained. This work focuses on the low-light HSI enhancement task, which aims to reveal the spatial-spectral information hidden in darkened areas. To facilitate the development of low-light HSI processing, we collect a low-light HSI (LHSI) dataset of both indoor and outdoor scenes. Based on Laplacian pyramid decomposition and reconstruction, we developed an end-to-end data-driven low-light HSI enhancement (HSIE) approach trained on the LHSI dataset. With the observation that illumination is related to the low-frequency component of HSI, while textural details are closely correlated to the high-frequency component, the proposed HSIE is designed to have two branches. The illumination enhancement branch is adopted to enlighten the low-frequency component with reduced resolution. The high-frequency refinement branch is utilized for refining the high-frequency component via a predicted mask. In addition, to improve information flow and boost performance, we introduce an effective channel attention block (CAB) with residual dense connection, which served as the basic block of the illumination enhancement branch. The effectiveness and efficiency of HSIE both in quantitative assessment measures and visual effects are demonstrated by experimental results on the LHSI dataset. According to the classification performance on the remote sensing Indian Pines dataset, downstream tasks benefit from the enhanced HSI. Datasets and codes are available: \href{https://github.com/guanguanboy/HSIE}{https://github.com/guanguanboy/HSIE}.

Learning Location from Shared Elevation Profiles in Fitness Apps: A Privacy Perspective

The extensive use of smartphones and wearable devices has facilitated many useful applications. For example, with Global Positioning System (GPS)-equipped smart and wearable devices, many applications can gather, process, and share rich metadata, such as geolocation, trajectories, elevation, and time. For example, fitness applications, such as Runkeeper and Strava, utilize the information for activity tracking and have recently witnessed a boom in popularity. Those fitness tracker applications have their own web platforms and allow users to share activities on such platforms or even with other social network platforms. To preserve the privacy of users while allowing sharing, several of those platforms may allow users to disclose partial information, such as the elevation profile for an activity, which supposedly would not leak the location of the users. In this work, and as a cautionary tale, we create a proof of concept where we examine the extent to which elevation profiles can be used to predict the location of users. To tackle this problem, we devise three plausible threat settings under which the city or borough of the targets can be predicted. Those threat settings define the amount of information available to the adversary to launch the prediction attacks. Establishing that simple features of elevation profiles, e.g., spectral features, are insufficient, we devise both natural language processing (NLP)-inspired text-like representation and computer vision-inspired image-like representation of elevation profiles, and we convert the problem at hand into text and image classification problem. We use both traditional machine learning- and deep learning-based techniques and achieve a prediction success rate ranging from 59.59\% to 99.80\%. The findings are alarming, highlighting that sharing elevation information may have significant location privacy risks.

Self-adversarial Multi-scale Contrastive Learning for Semantic Segmentation of Thermal Facial Images

Segmentation of thermal facial images is a challenging task. This is because facial features often lack salience due to high-dynamic thermal range scenes and occlusion issues. Limited availability of datasets from unconstrained settings further limits the use of the state-of-the-art segmentation networks, loss functions and learning strategies which have been built and validated for RGB images. To address the challenge, we propose Self-Adversarial Multi-scale Contrastive Learning (SAM-CL) framework as a new training strategy for thermal image segmentation. SAM-CL framework consists of a SAM-CL loss function and a thermal image augmentation (TiAug) module as a domain-specific augmentation technique. We use the Thermal-Face-Database to demonstrate effectiveness of our approach. Experiments conducted on the existing segmentation networks (UNET, Attention-UNET, DeepLabV3 and HRNetv2) evidence the consistent performance gains from the SAM-CL framework. Furthermore, we present a qualitative analysis with UBComfort and DeepBreath datasets to discuss how our proposed methods perform in handling unconstrained situations.

Specialized Re-Ranking: A Novel Retrieval-Verification Framework for Cloth Changing Person Re-Identification

Cloth changing person re-identification(Re-ID) can work under more complicated scenarios with higher security than normal Re-ID and biometric techniques and is therefore extremely valuable in applications. Meanwhile, higher flexibility in appearance always leads to more similar-looking confusing images, which is the weakness of the widely used retrieval methods. In this work, we shed light on how to handle these similar images. Specifically, we propose a novel retrieval-verification framework. Given an image, the retrieval module can search for similar images quickly. Our proposed verification network will then compare the input image and the candidate images by contrasting those local details and give a similarity score. An innovative ranking strategy is also introduced to take a good balance between retrieval and verification results. Comprehensive experiments are conducted to show the effectiveness of our framework and its capability in improving the state-of-the-art methods remarkably on both synthetic and realistic datasets.

Towards Multi-Modal Sarcasm Detection via Hierarchical Congruity Modeling with Knowledge Enhancement

Sarcasm is a linguistic phenomenon indicating a discrepancy between literal meanings and implied intentions. Due to its sophisticated nature, it is usually challenging to be detected from the text itself. As a result, multi-modal sarcasm detection has received more attention in both academia and industries. However, most existing techniques only modeled the atomic-level inconsistencies between the text input and its accompanying image, ignoring more complex compositions for both modalities. Moreover, they neglected the rich information contained in external knowledge, e.g., image captions. In this paper, we propose a novel hierarchical framework for sarcasm detection by exploring both the atomic-level congruity based on multi-head cross attention mechanism and the composition-level congruity based on graph neural networks, where a post with low congruity can be identified as sarcasm. In addition, we exploit the effect of various knowledge resources for sarcasm detection. Evaluation results on a public multi-modal sarcasm detection dataset based on Twitter demonstrate the superiority of our proposed model.

SCAM! Transferring humans between images with Semantic Cross Attention Modulation

A large body of recent work targets semantically conditioned image generation. Most such methods focus on the narrower task of pose transfer and ignore the more challenging task of subject transfer that consists in not only transferring the pose but also the appearance and background. In this work, we introduce SCAM (Semantic Cross Attention Modulation), a system that encodes rich and diverse information in each semantic region of the image (including foreground and background), thus achieving precise generation with emphasis on fine details. This is enabled by the Semantic Attention Transformer Encoder that extracts multiple latent vectors for each semantic region, and the corresponding generator that exploits these multiple latents by using semantic cross attention modulation. It is trained only using a reconstruction setup, while subject transfer is performed at test time. Our analysis shows that our proposed architecture is successful at encoding the diversity of appearance in each semantic region. Extensive experiments on the iDesigner and CelebAMask-HD datasets show that SCAM outperforms SEAN and SPADE; moreover, it sets the new state of the art on subject transfer.

ARUBA: An Architecture-Agnostic Balanced Loss for Aerial Object Detection

Deep neural networks tend to reciprocate the bias of their training dataset. In object detection, the bias exists in the form of various imbalances such as class, background-foreground, and object size. In this paper, we denote size of an object as the number of pixels it covers in an image and size imbalance as the over-representation of certain sizes of objects in a dataset. We aim to address the problem of size imbalance in drone-based aerial image datasets. Existing methods for solving size imbalance are based on architectural changes that utilize multiple scales of images or feature maps for detecting objects of different sizes. We, on the other hand, propose a novel ARchitectUre-agnostic BAlanced Loss (ARUBA) that can be applied as a plugin on top of any object detection model. It follows a neighborhood-driven approach inspired by the ordinality of object size. We evaluate the effectiveness of our approach through comprehensive experiments on aerial datasets such as HRSC2016, DOTAv1.0, DOTAv1.5 and VisDrone and obtain consistent improvement in performance.

ARIA: Adversarially Robust Image Attribution for Content Provenance

Image attribution -- matching an image back to a trusted source -- is an emerging tool in the fight against online misinformation. Deep visual fingerprinting models have recently been explored for this purpose. However, they are not robust to tiny input perturbations known as adversarial examples. First we illustrate how to generate valid adversarial images that can easily cause incorrect image attribution. Then we describe an approach to prevent imperceptible adversarial attacks on deep visual fingerprinting models, via robust contrastive learning. The proposed training procedure leverages training on $\ell_\infty$-bounded adversarial examples, it is conceptually simple and incurs only a small computational overhead. The resulting models are substantially more robust, are accurate even on unperturbed images, and perform well even over a database with millions of images. In particular, we achieve 91.6% standard and 85.1% adversarial recall under $\ell_\infty$-bounded perturbations on manipulated images compared to 80.1% and 0.0% from prior work. We also show that robustness generalizes to other types of imperceptible perturbations unseen during training. Finally, we show how to train an adversarially robust image comparator model for detecting editorial changes in matched images.