Conventional domain adaptation (DA) techniques aim to improve domain transferability by learning domain-invariant representations; while concurrently preserving the task-discriminability knowledge gathered from the labeled source data. However, the requirement of simultaneous access to labeled source and unlabeled target renders them unsuitable for the challenging source-free DA setting. The trivial solution of realizing an effective original to generic domain mapping improves transferability but degrades task discriminability. Upon analyzing the hurdles from both theoretical and empirical standpoints, we derive novel insights to show that a mixup between original and corresponding translated generic samples enhances the discriminability-transferability trade-off while duly respecting the privacy-oriented source-free setting. A simple but effective realization of the proposed insights on top of the existing source-free DA approaches yields state-of-the-art performance with faster convergence. Beyond single-source, we also outperform multi-source prior-arts across both classification and semantic segmentation benchmarks.

Balancing Discriminability and Transferability for Source-Free Domain Adaptation

Information security is considered one of the most important issues in various infrastructures related to the field of data communication where most of the modern studies focus on finding effective and low-weight secure approaches. Digital watermarking is a trend in security techniques that hides data by using data embedding and data extraction processes. Watermarking technology is integrated into different frames without adding an overheard as in the conventional encryption. Therefore, it is efficient to be used in data encryption for applications that run over limited resources such as the Internet of Things (IoT). In this paper, different digital watermarking algorithms and approaches are presented. Additionally, watermarking requirements and challenges are illustrated in detail. Moreover, the common architecture of the watermarking system is described. Furthermore, IoT technology and its challenges are highlighted. Finally, the paper provides the motivations, objectives and applications of the recent secure watermarking techniques in IoT and summarises them into one table. In addition, the paper highlights the potential to apply the modified watermark algorithms to secure IoT networks.

https://www.mdpi.com/2079-9292/10/14/1744/pdf

Secure Watermarking Schemes and Their Approaches in the IoT Technology: An Overview

Medical confidentiality is an essential duty in the medical profession. In this paper, we introduce a novel robust blind watermarking method for securing the medical report in a DICOM (Digital Imaging and Communications in Medicine) imaging. The insertion of each bit is done in the subtraction of adjacent DC coefficients of the FFT (fast Fourier transformation) using a key kw. Each bit of the watermark is eXORed with a bit generated by a proposed system which generates a bit sequence in function of the key kw. The proposed method has the features of having better security, invisibility, and robustness. Experimental results show that it is robust to single, double, and triple attacks and that it has better robustness than recently proposed watermarking schemes.

DICOM imaging watermarking for hiding medical reports

In unsupervised domain adaptation (UDA), a model trained on source data (e.g. synthetic) is adapted to target data (e.g. real-world) without access to target annotation. Most previous UDA methods struggle with classes that have a similar visual appearance on the target domain as no ground truth is available to learn the slight appearance differences. To address this problem, we propose a Masked Image Consistency (MIC) module to enhance UDA by learning spatial context relations of the target domain as additional clues for robust visual recognition. MIC enforces the consistency between predictions of masked target images, where random patches are withheld, and pseudo-labels that are generated based on the complete image by an exponential moving average teacher. To minimize the consistency loss, the network has to learn to infer the predictions of the masked regions from their context. Due to its simple and universal concept, MIC can be integrated into various UDA methods across different visual recognition tasks such as image classification, semantic segmentation, and object detection. MIC significantly improves the state-of-the-art performance across the different recognition tasks for synthetic-to-real, day-to-nighttime, and clear-to-adverse-weather UDA. For instance, MIC achieves an unprecedented UDA performance of 75.9 mIoU and 92.8% on GTA-to-Cityscapes and VisDA-2017, respectively, which corresponds to an improvement of +2.1 and +3.0 percent points over the previous state of the art. The implementation is available at https://github.com/lhoyer/MIC.

MIC: Masked Image Consistency for Context-Enhanced Domain Adaptation

This paper presents a novel digital image watermarking (DIW) scheme. This DIW scheme is based on a hybrid DWT-SVD transform domain and modified whale optimization algorithm (MWOA), making use of multiscale factors (MSFs) to control the trade-off between invisibility and robustness. The values of MSFs have been determined using MWOA, which is a nature-inspired optimization algorithm inspired by the bubble-net hunting strategy of humpback whales. The essential feature of modified WOA is that it provides a global solution and also requires less internal parameters for optimization. Normalized cross-correlation and peak signal to noise ratio are utilized in the objective function design. Results of simulations show that the proposed DIW scheme not only satisfies the need for invisibility but also has better or comparable robustness as compared to other recently published watermarking methods.

A Modified Whale Optimization Algorithm Based Digital Image Watermarking Approach

Domain adversarial training has been ubiqui-tous for achieving invariant representations and is used widely for various domain adaptation tasks. In recent times, methods converging to smooth optima have shown improved generalization for supervised learning tasks like classification. In this work, we analyze the effect of smoothness enhancing formulations on domain adversarial training, the objective of which is a combination of task loss (eg. classification, regression etc.) and adversarial terms. We find that converging to a smooth minima with respect to (w.r.t.) task loss stabilizes the adversarial training leading to better performance on target domain. In contrast to task loss, our analysis shows that converging to smooth minima w.r.t. adversarial loss leads to sub-optimal generalization on the target domain. Based on the analysis, we introduce the Smooth Domain Adversarial Training (SDAT) procedure, which effectively enhances the performance of existing domain adversarial methods for both classification and object detection tasks. Our analysis also provides insight into the extensive usage of SGD over Adam in the community for domain adversarial training.

A Closer Look at Smoothness in Domain Adversarial Training

In digital watermarking, a watermark is embedded into a cover image in such a way that the resulting watermarked signal is robust to certain distortions caused by either standard data processing in a friendly environment or malicious attacks in an unfriendly environment. This work provides Digital Image Watermarking based on Hybrid DWT-FFT with different malicious attacks (JPEG compression, Salt & Peppers Noise, Gaussian Noise, Blurring and Blurring & Noise). Signal to Noise Ratio (SNR) is computed to measure image quality for proposed technique for better results as compared to previous techniques of information hiding.

Digital Image Watermarking using Hybrid DWT-FFT technique with different attacks

. The goal of lifelong learning is to continuously learn from non-stationary distributions, where the non-stationarity is typically imposed by a sequence of distinct tasks. Prior works have mostly considered idealistic settings, where the identity of tasks is known at least at training. In this paper we focus on a fundamentally harder, so-called task-agnostic, setting where the task identities are not known and the learning machine needs to infer them from the observations. Our algorithm, which we call TAME ( T ask- A gnostic continual learning using M ultiple E xperts), automatically detects the shift in data distributions and switches between task expert networks in an online manner. At training, the strategy for switching between tasks hinges on an extremely simple observation that for each new coming task there occurs a statistically-significant deviation in the value of the loss function that marks the onset of this new task. At inference, the switching between experts is governed by the selector network that forwards the test sample to its relevant expert network. The selector network is trained on a small subset of data drawn uniformly at random. We control the growth of the task expert networks as well as selector network by employing online pruning. Our experimental results show the efficacy of our approach on benchmark continual learning data sets, outperforming the previous task-agnostic methods and even the techniques that admit task identities at both training and testing, while at the same time using a comparable model size.

TAME: Task Agnostic Continual Learning using Multiple Experts

Clinical Practice Guidelines (CPGs) for cancer diseases evolve rapidly due to new evidence generated by active research. Currently, CPGs are primarily published in a document format that is ill-suited for managing this developing knowledge. A knowledge model of the guidelines document suitable for programmatic interaction is required. This work proposes an automated method for extraction of knowledge from National Comprehensive Cancer Network (NCCN) CPGs in Oncology and generating a structured model containing the retrieved knowledge. The proposed method was tested using two versions of NCCN Non-Small Cell Lung Cancer (NSCLC) CPG to demonstrate the effectiveness in faithful extraction and modeling of knowledge. Three enrichment strategies using Cancer staging information, Unified Medical Language System (UMLS) Metathesaurus&National Cancer Institute thesaurus (NCIt) concepts, and Node classification are also presented to enhance the model towards enabling programmatic traversal and querying of cancer care guidelines. The Node classification was performed using a Support Vector Machine (SVM) model, achieving a classification accuracy of 0.81 with 10-fold cross-validation.

Arihant Kumar Jain

Papers

A Closer Look at Smoothness in Domain Adversarial Training

Digital Image Watermarking using Hybrid DWT-FFT technique with different attacks

TAME: Task Agnostic Continual Learning using Multiple Experts

Automated Knowledge Modeling for Cancer Clinical Practice Guidelines