Unsupervised Domain Adaptation (UDA) is quite challenging due to the large distribution discrepancy between the source domain and the target domain. Inspired by diffusion models which have strong capability to gradually convert data distributions across a large gap, we consider to explore the diffusion technique to handle the challenging UDA task. However, using diffusion models to convert data distribution across different domains is a non-trivial problem as the standard diffusion models generally perform conversion from the Gaussian distribution instead of from a specific domain distribution. Besides, during the conversion, the semantics of the source-domain data needs to be preserved to classify correctly in the target domain. To tackle these problems, we propose a novel Domain-Adaptive Diffusion (DAD) module accompanied by a Mutual Learning Strategy (MLS), which can gradually convert data distribution from the source domain to the target domain while enabling the classification model to learn along the domain transition process. Consequently, our method successfully eases the challenge of UDA by decomposing the large domain gap into small ones and gradually enhancing the capacity of classification model to finally adapt to the target domain. Our method outperforms the current state-of-the-arts by a large margin on three widely used UDA datasets.

Vehicular fog-edge computing (VFEC) is a new paradigm that has significant advantages in expanding the resource capacity of mobile edge computing (MEC) servers in vehicular networks. This work studies an incentive-based vehicular fog-edge computational offloading, and resource allocation schemes for vehicular networks using 5G-NR V2X communications. Here, smart vehicles in a given area are assumed to have computationally intensive tasks which can offload to the roadside unit (RSU) with a MEC server. To expand the resource capacity of the MEC server, in this work, we propose an incentive-based vehicular fog-edge computational offloading, and resource allocation scheme to maximize the unified utility function of the system with delay and incentive satisfaction of the entities under deadline and incentive constraints. This results in the mixed integer non-linear programming problem that is solved using continuous relaxation and an alternating optimization between convex sub-problems. Simulations are provided to demonstrate the effectiveness of the proposed scheme.

We propose an online continual learning algorithm based on an enhanced Random Vector Functional Link Network (OCL-eRVFL), that learns a sequence of tasks continually, where each task is defined by streaming data with each sample arriving once and only once. As data for a new task in domain incremental or class incremental setting streams in, the output weights of an eRVFL is updated through Recursive least squares, such that the representations for the past tasks are not catastrophically forgotten. As the recursive least square update is based only on the currently streaming sample, samples are not stored. Hence, unlike state-of-the-art OCL that avoid catastrophic forgetting through memory replay of samples from past task, the proposed OCL-eRVFL needs no extra memory. The proposed OCL-eRVFL is evaluated on streaming split CIFAR10, split CIFAR100 and split CIFAR10/100 image classification data sets within a class and domain incremental setting. Performance results show that the proposed OCL-eRVFL efficiently learns a sequence of tasks with streaming data, without additional memory expense.

Robustness of learning algorithms remains an important problem to be solved from both the perspective of adversarial attacks and improving generalization. In this work, we investigate the robustness of biologically inspired Hebbian learning algorithm in depth. We find that Hebbian learning based algorithms outperform conventional learning algorithms like CNNs by a huge margin of upto 18% on the CIFAR-10 dataset under the addition of noise. We highlight that an important reason for this is the underlying representations that are being learnt by the learning algorithms. Specifically, we find that the Hebbian method learns the most robust representations compared to other methods that helps it to generalize better. We also conduct ablations on the Hebbian network and showcase that robustness of the model drops by upto 16% on the CIFAR-10 dataset if the representation capacity of the network is deteriorated. Hence, we find that the representations learnt play an important role in the resultant robustness of the models. We conduct experiments on multiple datasets and show that the results hold on all the datasets and at various noise levels.

Deep neural networks model data for a task or a sequence of tasks, where the knowledge extracted from the data is encoded in the parameters and representations of the network. Extraction and utilization of these representations is vital when data is no longer available in the future, especially in a continual learning scenario. We introduce flashcards, which are visual representations that capture the encoded knowledge of a network as a recursive function of some predefined random image patterns. In a continual learning scenario, flashcards help to prevent catastrophic forgetting by consolidating the knowledge of all the previous tasks. Flashcards are required to be constructed only before learning the subsequent task, hence, they are independent of the number of tasks trained before, making them task agnostic. We demonstrate the efficacy of flashcards in capturing learned knowledge representation (as an alternative to the original data), and empirically validate on a variety of continual learning tasks: reconstruction, denoising, and task-incremental classification, using several heterogeneous (varying background and complexity) benchmark datasets. Experimental evidence indicates that: (i) flashcards as a replay strategy is task agnostic, (ii) performs better than generative replay, and (iii) is on par with episodic replay without additional memory overhead.

Backpropagation has revolutionized neural network training however, its biological plausibility remains questionable. Hebbian learning, a completely unsupervised and feedback free learning technique is a strong contender for a biologically plausible alternative. However, so far, it has neither achieved high accuracy performance vs. backprop, nor is the training procedure simple. In this work, we introduce a new Hebbian learning based neural network, called HebbNet. At the heart of HebbNet is an improved Hebbian approach that includes an updated activation threshold and gradient sparsity to the first principles of Hebbian learning. These enable an efficiently performing Hebbian approach with a simple training procedure. Further to this, the improved Hebbian rule also improves training dynamics by reducing the number of training epochs from 1500 to 200 and making training a one-step process from a two-step process. We also reduce heuristics by reducing hyper-parameters from 5 to 1, and number of search runs for hyper-parameter tuning from 12,600 to 13. Notwithstanding this, HebbNet still achieves strong test performance on MNIST and CIFAR-10 datasets vs. state-of-the-art.

Continual learning (CL) aims to learn new tasks by forward transfer of information learnt from previous tasks and without forgetting them. In task incremental CL, task information is vital during both strategy development and inference. Providing such partial knowledge about the test sample demands additional complexity and may become intractable, especially when the sample source is ambiguous. In this work, we design a task-agnostic approach that uses base-child hybrid setup to incrementally learn tasks while mitigating forgetting. Multiple base classifiers guided by reference points learn new tasks and this information is distilled via feature space induced sampling strategy. A central child classifier consolidates information across tasks and infers the task identifier automatically. Experimental results on standard datasets show that the proposed approach outperforms the various state-of-the-art regularization and replay CL algorithms in terms of accuracy, by 50% and 7% with homogeneous and heterogeneous tasks, respectively, in task-agnostic scenarios.

Steganalysis can be characterized as detecting a weak noise signal (hidden information) in textured regions of naturally occurring images. These noise signals are typically not perceptible to human eyes, which renders steganalysis a challenging task. On the other hand, recent breakthroughs in deep learning have seen remarkable progress in many applications, ranging from object recognition and segmentation to image generations. While there were efforts to build deep learning networks to perform steganalysis, the proposed architectures exhibit some limitations and a high tendency to overfit. We propose a hybrid deep learning architecture, namely H-StegoNet, to perform spatial steganalysis in this work. Precisely, by combining two different neural networks inspired by handcrafted features and the U-Net, we design a robust architecture that outperforms the existing approaches. Moreover, the experiments we performed under more realistic assumptions, including encoding with the syndrome trellis codes and assuming no prior knowledge of the payload used, thereby defining a rigorous and standard operation procedure for evaluating any steganalysis algorithm.

Quantitative measurements obtained from medical images guide clinicians in several use cases but manually obtaining such measurements are both laborious and subject to inter-observer variations. We develop a hybrid deep reinforced regression framework to robustly measure the Cardio-Thoracic ratio (CTR) from Chest X-ray (CXR) images, thereby directly identifying the presence of Cardiomegaly. The proposed hybrid framework initially employs a CNN based Regressor on pre-processed images to obtain approximate critical points. As the actual critical points are based on human expert's experience and subject to labeling uncertainties, a deep reinforcement learning (deep RL) approach is specifically designed to fine-tune estimated regression points from the CNN Regressor. The final regressed points are then used to measure CTR. Wingspan and ChestX-ray8 datasets are used for validating the proposed framework. The proposed framework shows generalization ability on ChestX-ray8 and outperforms the state-of-the-art results on Wingspan.