Search

Multiview systems have become a key technology in modern computer vision, offering advanced capabilities in scene understanding and analysis. However, these systems face critical challenges in bandwidth limitations and computational constraints, particularly for resource-limited camera nodes like drones. This paper presents a novel approach for communication-efficient distributed multiview detection and tracking using masked autoencoders (MAEs). We introduce a semantic-guided masking strategy that leverages pre-trained segmentation models and a tunable power function to prioritize informative image regions. This approach, combined with an MAE, reduces communication overhead while preserving essential visual information. We evaluate our method on both virtual and real-world multiview datasets, demonstrating comparable performance in terms of detection and tracking performance metrics compared to state-of-the-art techniques, even at high masking ratios. Our selective masking algorithm outperforms random masking, maintaining higher accuracy and precision as the masking ratio increases. Furthermore, our approach achieves a significant reduction in transmission data volume compared to baseline methods, thereby balancing multiview tracking performance with communication efficiency., Comment: 10 pages, conference

Federated Learning (FL) is a distributed machine learning paradigm designed for privacy-sensitive applications that run on resource-constrained devices with non-Identically and Independently Distributed (IID) data. Traditional FL frameworks adopt the client-server model with a single-level aggregation (AGR) process, where the server builds the global model by aggregating all trained local models received from client devices. However, this conventional approach encounters challenges, including susceptibility to model/data poisoning attacks. In recent years, advancements in the Internet of Things (IoT) and edge computing have enabled the development of hierarchical FL systems with a two-level AGR process running at edge and cloud servers. In this paper, we propose a Secure Hierarchical FL (SHFL) framework to address poisoning attacks in hierarchical edge networks. By aggregating trained models at the edge, SHFL employs two novel methods to address model/data poisoning attacks in the presence of client adversaries: 1) a client selection algorithm running at the edge for choosing IoT devices to participate in training, and 2) a model AGR method designed based on convex optimization theory to reduce the impact of edge models from networks with adversaries in the process of computing the global model (at the cloud level). The evaluation results reveal that compared to state-of-the-art methods, SHFL significantly increases the maximum accuracy achieved by the global model in the presence of client adversaries applying model/data poisoning attacks.

Environment Sound Classification has been a well-studied research problem in the field of signal processing and up till now more focus has been laid on fully supervised approaches. Over the last few years, focus has moved towards semi-supervised methods which concentrate on the utilization of unlabeled data, and self-supervised methods which learn the intermediate representation through pretext task or contrastive learning. However, both approaches require a vast amount of unlabelled data to improve performance. In this work, we propose a novel framework called Environmental Sound Classification with Hierarchical Ontology-guided semi-supervised Learning (ECHO) that utilizes label ontology-based hierarchy to learn semantic representation by defining a novel pretext task. In the pretext task, the model tries to predict coarse labels defined by the Large Language Model (LLM) based on ground truth label ontology. The trained model is further fine-tuned in a supervised way to predict the actual task. Our proposed novel semi-supervised framework achieves an accuracy improvement in the range of 1\% to 8\% over baseline systems across three datasets namely UrbanSound8K, ESC-10, and ESC-50., Comment: IEEE CONECCT 2024, Signal Processing and Pattern Recognition, Environmental Sound Classification, ESC

Federated Learning (FL) is a promising distributed learning framework designed for privacy-aware applications. FL trains models on client devices without sharing the client's data and generates a global model on a server by aggregating model updates. Traditional FL approaches risk exposing sensitive client data when plain model updates are transmitted to the server, making them vulnerable to security threats such as model inversion attacks where the server can infer the client's original training data from monitoring the changes of the trained model in different rounds. Google's Secure Aggregation (SecAgg) protocol addresses this threat by employing a double-masking technique, secret sharing, and cryptography computations in honest-but-curious and adversarial scenarios with client dropouts. However, in scenarios without the presence of an active adversary, the computational and communication cost of SecAgg significantly increases by growing the number of clients. To address this issue, in this paper, we propose ACCESS-FL, a communication-and-computation-efficient secure aggregation method designed for honest-but-curious scenarios in stable FL networks with a limited rate of client dropout. ACCESS-FL reduces the computation/communication cost to a constant level (independent of the network size) by generating shared secrets between only two clients and eliminating the need for double masking, secret sharing, and cryptography computations. To evaluate the performance of ACCESS-FL, we conduct experiments using the MNIST, FMNIST, and CIFAR datasets to verify the performance of our proposed method. The evaluation results demonstrate that our proposed method significantly reduces computation and communication overhead compared to state-of-the-art methods, SecAgg and SecAgg+.

There has been rampant propagation of fake news and misinformation videos on many platforms lately, and moderation of such content faces many challenges that must be overcome. Recent research has shown the feasibility of identifying video titles from encrypted network traffic within a single platform, for example, within YouTube or Facebook. However, there are no existing methods for cross-platform video recognition, a crucial gap that this works aims to address. Encrypted video traffic classification within a single platform, that is, classifying the video title of a traffic trace of a video on one platform by training on traffic traces of videos on the same platform, has significant limitations due to the large number of video platforms available to users to upload harmful content to. To attempt to address this limitation, we conduct a feasibility analysis into and attempt to solve the challenge of recognizing videos across multiple platforms by using the traffic traces of videos on one platform only. We propose TripletViNet, a framework that encompasses i) platform-wise pre-processing, ii) an encoder trained utilizing triplet learning for improved accuracy and iii) multiclass classifier for classifying the video title of a traffic trace. To evaluate the performance of TripletViNet, a comprehensive dataset with traffic traces for 100 videos on six major platforms with the potential for spreading misinformation such as YouTube, X, Instagram, Facebook, Rumble, and Tumblr was collected and used to test TripletViNet in both closed-set and open-set scenarios. TripletViNet achieves significant improvements in accuracy due to the correlation between video traffic and the video's VBR, with impressive final accuracies exceeding 90% in certain scenarios., Comment: This paper has already been published in ACM SCID '24

LLMs with visual inputs, i.e., Vision Language Models (VLMs), have the capacity to process state information as visual-textual prompts and respond with policy decisions in text. We propose LLaRA: Large Language and Robotics Assistant, a framework that formulates robot action policy as conversations and provides improved action outputs when trained with auxiliary data that complements policy learning. We first introduce an automated pipeline to generate conversation-style instruction tuning data from existing behavior cloning data. Then we enrich the dataset in a self-supervised fashion by formulating six auxiliary tasks. A VLM finetuned with the resulting collection of datasets can generate meaningful robot action policy decisions. Our experiments across multiple simulated and real-world environments demonstrate the state-of-the-art performance of the proposed LLaRA framework. The code, datasets, and pretrained models are available at https://github.com/LostXine/LLaRA.

Long-form videos that span across wide temporal intervals are highly information redundant and contain multiple distinct events or entities that are often loosely related. Therefore, when performing long-form video question answering (LVQA), all information necessary to generate a correct response can often be contained within a small subset of frames. Recent literature explore the use of large language models (LLMs) in LVQA benchmarks, achieving exceptional performance, while relying on vision language models (VLMs) to convert all visual content within videos into natural language. Such VLMs often independently caption a large number of frames uniformly sampled from long videos, which is not efficient and can mostly be redundant. Questioning these decision choices, we explore optimal strategies for key-frame selection that can significantly reduce these redundancies, namely Hierarchical Keyframe Selector. Our proposed framework, LVNet, achieves state-of-the-art performance at a comparable caption scale across three benchmark LVQA datasets: EgoSchema, IntentQA, NExT-QA. The code can be found at https://github.com/jongwoopark7978/LVNet

In many federated learning (FL) models, a common strategy employed to ensure the progress in the training process, is to wait for at least $M$ clients out of the total $N$ clients to send back their local gradients based on a reporting deadline $T$, once the parameter server (PS) has broadcasted the global model. If enough clients do not report back within the deadline, the particular round is considered to be a failed round and the training round is restarted from scratch. If enough clients have responded back, the round is deemed successful and the local gradients of all the clients that responded back are used to update the global model. In either case, the clients that failed to report back an update within the deadline would have wasted their computational resources. Having a tighter deadline (small $T$) and waiting for a larger number of participating clients (large $M$) leads to a large number of failed rounds and therefore greater communication cost and computation resource wastage. However, having a larger $T$ leads to longer round durations whereas smaller $M$ may lead to noisy gradients. Therefore, there is a need to optimize the parameters $M$ and $T$ such that communication cost and the resource wastage is minimized while having an acceptable convergence rate. In this regard, we show that the average age of a client at the PS appears explicitly in the theoretical convergence bound, and therefore, can be used as a metric to quantify the convergence of the global model. We provide an analytical scheme to select the parameters $M$ and $T$ in this setting.

Integration of Large Language Models (LLMs) into visual domain tasks, resulting in visual-LLMs (V-LLMs), has enabled exceptional performance in vision-language tasks, particularly for visual question answering (VQA). However, existing V-LLMs (e.g. BLIP-2, LLaVA) demonstrate weak spatial reasoning and localization awareness. Despite generating highly descriptive and elaborate textual answers, these models fail at simple tasks like distinguishing a left vs right location. In this work, we explore how image-space coordinate based instruction fine-tuning objectives could inject spatial awareness into V-LLMs. We discover optimal coordinate representations, data-efficient instruction fine-tuning objectives, and pseudo-data generation strategies that lead to improved spatial awareness in V-LLMs. Additionally, our resulting model improves VQA across image and video domains, reduces undesired hallucination, and generates better contextual object descriptions. Experiments across 5 vision-language tasks involving 14 different datasets establish the clear performance improvements achieved by our proposed framework.

Large Language Models (LLMs), known to contain a strong awareness of world knowledge, have allowed recent approaches to achieve excellent performance on Long-Video Understanding benchmarks, but at high inference costs. In this work, we first propose Likelihood Selection, a simple technique that unlocks faster inference in autoregressive LLMs for multiple-choice tasks common in long-video benchmarks. In addition to faster inference, we discover the resulting models to yield surprisingly good accuracy on long-video tasks, even with no video specific information. Building on this, we inject video-specific object-centric information extracted from off-the-shelf pre-trained models and utilize natural language as a medium for information fusion. Our resulting Multimodal Video Understanding (MVU) framework demonstrates state-of-the-art performance across long-video and fine-grained action recognition benchmarks. Code available at: https://github.com/kahnchana/mvu, Comment: 24 pages

Large Language Models (LLMs) are foundational to AI advancements, facilitating applications like predictive text generation. Nonetheless, they pose risks by potentially memorizing and disseminating sensitive, biased, or copyrighted information from their vast datasets. Machine unlearning emerges as a cutting-edge solution to mitigate these concerns, offering techniques for LLMs to selectively discard certain data. This paper reviews the latest in machine unlearning for LLMs, introducing methods for the targeted forgetting of information to address privacy, ethical, and legal challenges without necessitating full model retraining. It divides existing research into unlearning from unstructured/textual data and structured/classification data, showcasing the effectiveness of these approaches in removing specific data while maintaining model efficacy. Highlighting the practicality of machine unlearning, this analysis also points out the hurdles in preserving model integrity, avoiding excessive or insufficient data removal, and ensuring consistent outputs, underlining the role of machine unlearning in advancing responsible, ethical AI.

Language has become a prominent modality in computer vision with the rise of multi-modal LLMs. Despite supporting long context-lengths, their effectiveness in handling long-term information gradually declines with input length. This becomes critical, especially in applications such as long-form video understanding. In this paper, we introduce a Language Repository (LangRepo) for LLMs, that maintains concise and structured information as an interpretable (i.e., all-textual) representation. Our repository is updated iteratively based on multi-scale video chunks. We introduce write and read operations that focus on pruning redundancies in text, and extracting information at various temporal scales. The proposed framework is evaluated on zero-shot visual question-answering benchmarks including EgoSchema, NExT-QA, IntentQA and NExT-GQA, showing state-of-the-art performance at its scale. Our code is available at https://github.com/kkahatapitiya/LangRepo.

Self-supervised representation learning has been highly promising for histopathology image analysis with numerous approaches leveraging their patient-slide-patch hierarchy to learn better representations. In this paper, we explore how the combination of domain specific natural language information with such hierarchical visual representations can benefit rich representation learning for medical image tasks. Building on automated language description generation for features visible in histopathology images, we present a novel language-tied self-supervised learning framework, Hierarchical Language-tied Self-Supervision (HLSS) for histopathology images. We explore contrastive objectives and granular language description based text alignment at multiple hierarchies to inject language modality information into the visual representations. Our resulting model achieves state-of-the-art performance on two medical imaging benchmarks, OpenSRH and TCGA datasets. Our framework also provides better interpretability with our language aligned representation space. Code is available at https://github.com/Hasindri/HLSS., Comment: 13 pages and 5 figures

In this paper, we introduce the problem of zero-shot text-guided exploration of the solutions to open-domain image super-resolution. Our goal is to allow users to explore diverse, semantically accurate reconstructions that preserve data consistency with the low-resolution inputs for different large downsampling factors without explicitly training for these specific degradations. We propose two approaches for zero-shot text-guided super-resolution - i) modifying the generative process of text-to-image \textit{T2I} diffusion models to promote consistency with low-resolution inputs, and ii) incorporating language guidance into zero-shot diffusion-based restoration methods. We show that the proposed approaches result in diverse solutions that match the semantic meaning provided by the text prompt while preserving data consistency with the degraded inputs. We evaluate the proposed baselines for the task of extreme super-resolution and demonstrate advantages in terms of restoration quality, diversity, and explorability of solutions., Comment: CVPR 2024

This paper provides an overview of current approaches for solving inverse problems in imaging using variational methods and machine learning. A special focus lies on point estimators and their robustness against adversarial perturbations. In this context results of numerical experiments for a one-dimensional toy problem are provided, showing the robustness of different approaches and empirically verifying theoretical guarantees. Another focus of this review is the exploration of the subspace of data-consistent solutions through explicit guidance to satisfy specific semantic or textural properties.

Low dose computed tomography (CT) acquisition using reduced radiation or sparse angle measurements is recommended to decrease the harmful effects of X-ray radiation. Recent works successfully apply deep networks to the problem of low dose CT recovery on bench-mark datasets. However, their robustness needs a thorough evaluation before use in clinical settings. In this work, we evaluate the robustness of different deep learning approaches and classical methods for CT recovery. We show that deep networks, including model-based networks encouraging data consistency, are more susceptible to untargeted attacks. Surprisingly, we observe that data consistency is not heavily affected even for these poor quality reconstructions, motivating the need for better regularization for the networks. We demonstrate the feasibility of universal attacks and study attack transferability across different methods. We analyze robustness to attacks causing localized changes in clinically relevant regions. Both classical approaches and deep networks are affected by such attacks leading to changes in the visual appearance of localized lesions, for extremely small perturbations. As the resulting reconstructions have high data consistency with the original measurements, these localized attacks can be used to explore the solution space of the CT recovery problem., Comment: MIDL 2023

We grew needle-shaped single crystals of GdAgGe, which crystallizes in a noncentrosymmetric hexagonal crystal structure with space group P$\overline{6}$2$m$ (189). The magnetic susceptibility data for $H \perp c$ reveal two pronounced antiferromagnetic transitions at $T_{N1}$ = 20 K and $T_{N2}$ = 14.5 K. The magnetic susceptibility anomalies are less prominent for $H \parallel c$. The transition at $T_{N1}$ is accompanied by a pronounced heat capacity anomaly confirming the bulk nature of the magnetic transition. Below $T_{N1}$, the electrical resistivity data follows a $T^{3/2}$ dependence. In the magnetically ordered state, GdAgGe shows positive transverse magnetoresistance, which increases with decreasing temperature and increasing field, reaching a value of $\sim$ 27% at 9 T and 10 K. The Hall resistivity data and electronic band structure calculations suggest that both the hole and electron charge carriers contribute to the transport properties. The electronic band structure displays linear band crossings near the Fermi level. The calculations reveal that GdAgGe has a nodal line with drumhead surface states coupled with a nonzero Berry phase, making it a nontrivial nodal-line semimetal., Comment: 9 pages, 9 figures

We report the physical properties of GdAuGe single crystals, which were grown using Bi flux. The powder x-ray diffraction data shows that the compound crystallizes in hexagonal NdPtSb-type structure (space group P63mc). Magnetization measurements performed for field configuration H||c and H||ab show that GdAuGe orders antiferromagnetically at the Neel temperature, TN = 17.2 K. Around this temperature, heat capacity and electrical resistivity data exhibit prominent anomaly due to the antiferromagnetic (AFM) transition. In addition to an AFM phase transition, the magnetization data for H||c display the signature of field-induced metamagnetic (MM) transitions below TN. The critical field range for these transitions vary from 0.2 to 6.2 T. The critical fields for the MM transitions decrease with increasing temperature and approach zero value for temperature approaching TN. Interestingly, the magnetoresistance (MR) data (for H||c) record a sharp increase in values at the critical fields that coincide with those seen in magnetization data, tracking the presence of MM transitions. MR is positive and large (169% at 9 T and 2 K) at low temperatures. Above TN, MR becomes small and switches to negative values. Hall resistivity data reveal the predominance of hole charge carriers in the system. In addition, we observe an emergence of step-like feature in the Hall resistivity data within the field range of second MM, and a significantly large anomalous Hall conductivity of 1270 {\Omega}-1 cm-1 at 2 K. The H-T phase diagram constructed from our detailed magnetization and magnetotransport measurements reveals multiple intricate magnetic phase transitions. The electronic and magnetic structure of GdAuGe are also thoroughly investigated using first-principles methods. The electronic band structure calculations reveal that GdAuGe is a Dirac nodal-line semimetal., Comment: 11 pages, 12 figures

We explore the problem of computationally generating special `prime' images that produce optical illusions when physically arranged and viewed in a certain way. First, we propose a formal definition for this problem. Next, we introduce Diffusion Illusions, the first comprehensive pipeline designed to automatically generate a wide range of these illusions. Specifically, we both adapt the existing `score distillation loss' and propose a new `dream target loss' to optimize a group of differentially parametrized prime images, using a frozen text-to-image diffusion model. We study three types of illusions, each where the prime images are arranged in different ways and optimized using the aforementioned losses such that images derived from them align with user-chosen text prompts or images. We conduct comprehensive experiments on these illusions and verify the effectiveness of our proposed method qualitatively and quantitatively. Additionally, we showcase the successful physical fabrication of our illusions -- as they are all designed to work in the real world. Our code and examples are publicly available at our interactive project website: https://diffusionillusions.com

Point cloud streaming is increasingly getting popular, evolving into the norm for interactive service delivery and the future Metaverse. However, the substantial volume of data associated with point clouds presents numerous challenges, particularly in terms of high bandwidth consumption and large storage capacity. Despite various solutions proposed thus far, with a focus on point cloud compression, upsampling, and completion, these reconstruction-related methods continue to fall short in delivering high fidelity point cloud output. As a solution, in DiffPMAE, we propose an effective point cloud reconstruction architecture. Inspired by self-supervised learning concepts, we combine Masked Auto-Encoding and Diffusion Model mechanism to remotely reconstruct point cloud data. By the nature of this reconstruction process, DiffPMAE can be extended to many related downstream tasks including point cloud compression, upsampling and completion. Leveraging ShapeNet-55 and ModelNet datasets with over 60000 objects, we validate the performance of DiffPMAE exceeding many state-of-the-art methods in-terms of auto-encoding and downstream tasks considered.

Network data analytics are now at the core of almost every networking solution. Nonetheless, limited access to networking data has been an enduring challenge due to many reasons including complexity of modern networks, commercial sensitivity, privacy and regulatory constraints. In this work, we explore how to leverage recent advancements in Diffusion Models (DM) to generate synthetic network traffic data. We develop an end-to-end framework - NetDiffus that first converts one-dimensional time-series network traffic into two-dimensional images, and then synthesizes representative images for the original data. We demonstrate that NetDiffus outperforms the state-of-the-art traffic generation methods based on Generative Adversarial Networks (GANs) by providing 66.4% increase in fidelity of the generated data and 18.1% increase in downstream machine learning tasks. We evaluate NetDiffus on seven diverse traffic traces and show that utilizing synthetic data significantly improves traffic fingerprinting, anomaly detection and traffic classification., Comment: 9 pages and 8 figures