arXiv subjects

Ivan V. Bajić

Publications and source records attributed to Ivan V. Bajić.

At least 37 records · Page 2Linked to original sources

arXiv2023

SplitFed resilience to packet loss: Where to split, that is the question

Decentralized machine learning has broadened its scope recently with the invention of Federated Learning (FL), Split Learning (SL), and their hybrids like Split Federated Learning (SplitFed or SFL). The goal of SFL is to reduce the computational power required by each client in FL and parallelize SL while maintaining privacy. This paper investigates the robustness of SFL against packet loss on communication links. The performance of various SFL aggregation strategies is examined by splitting the model at two points -- shallow split and deep split -- and testing whether the split point makes a statistically significant difference to the accuracy of the final model. Experiments are carried out on a segmentation model for human embryo images and indicate the statistically significant advantage of a deeper split point.

cs.CV↗

arXiv2023

Metaverse: A Young Gamer's Perspective

When developing technologies for the Metaverse, it is important to understand the needs and requirements of end users. Relatively little is known about the specific perspectives on the use of the Metaverse by the youngest audience: children ten and under. This paper explores the Metaverse from the perspective of a young gamer. It examines their understanding of the Metaverse in relation to the physical world and other technologies they may be familiar with, looks at some of their expectations of the Metaverse, and then relates these to the specific multimedia signal processing (MMSP) research challenges. The perspectives presented in the paper may be useful for planning more detailed subjective experiments involving young gamers, as well as informing the research on MMSP technologies targeted at these users.

eess.IV↗

arXiv2023

Base Layer Efficiency in Scalable Human-Machine Coding

A basic premise in scalable human-machine coding is that the base layer is intended for automated machine analysis and is therefore more compressible than the same content would be for human viewing. Use cases for such coding include video surveillance and traffic monitoring, where the majority of the content will never be seen by humans. Therefore, base layer efficiency is of paramount importance because the system would most frequently operate at the base-layer rate. In this paper, we analyze the coding efficiency of the base layer in a state-of-the-art scalable human-machine image codec, and show that it can be improved. In particular, we demonstrate that gains of 20-40% in BD-Rate compared to the currently best results on object detection and instance segmentation are possible.

eess.IV↗

arXiv2023

Conditional and Residual Methods in Scalable Coding for Humans and Machines

We present methods for conditional and residual coding in the context of scalable coding for humans and machines. Our focus is on optimizing the rate-distortion performance of the reconstruction task using the information available in the computer vision task. We include an information analysis of both approaches to provide baselines and also propose an entropy model suitable for conditional coding with increased modelling capacity and similar tractability as previous work. We apply these methods to image reconstruction, using, in one instance, representations created for semantic segmentation on the Cityscapes dataset, and in another instance, representations created for object detection on the COCO dataset. In both experiments, we obtain similar performance between the conditional and residual methods, with the resulting rate-distortion curves contained within our baselines.

eess.IV↗

arXiv2023

Grad-FEC: Unequal Loss Protection of Deep Features in Collaborative Intelligence

Collaborative intelligence (CI) involves dividing an artificial intelligence (AI) model into two parts: front-end, to be deployed on an edge device, and back-end, to be deployed in the cloud. The deep feature tensors produced by the front-end are transmitted to the cloud through a communication channel, which may be subject to packet loss. To address this issue, in this paper, we propose a novel approach to enhance the resilience of the CI system in the presence of packet loss through Unequal Loss Protection (ULP). The proposed ULP approach involves a feature importance estimator, which estimates the importance of feature packets produced by the front-end, and then selectively applies Forward Error Correction (FEC) codes to protect important packets. Experimental results demonstrate that the proposed approach can significantly improve the reliability and robustness of the CI system in the presence of packet loss.

eess.IV↗

arXiv2023

Quality-Adaptive Split-Federated Learning for Segmenting Medical Images with Inaccurate Annotations

SplitFed Learning, a combination of Federated and Split Learning (FL and SL), is one of the most recent developments in the decentralized machine learning domain. In SplitFed learning, a model is trained by clients and a server collaboratively. For image segmentation, labels are created at each client independently and, therefore, are subject to clients' bias, inaccuracies, and inconsistencies. In this paper, we propose a data quality-based adaptive averaging strategy for SplitFed learning, called QA-SplitFed, to cope with the variation of annotated ground truth (GT) quality over multiple clients. The proposed method is compared against five state-of-the-art model averaging methods on the task of learning human embryo image segmentation. Our experiments show that all five baseline methods fail to maintain accuracy as the number of corrupted clients increases. QA-SplitFed, however, copes effectively with corruption as long as there is at least one uncorrupted client.

cs.CV↗

arXiv2023

LCCM-VC: Learned Conditional Coding Modes for Video Compression

End-to-end learning-based video compression has made steady progress over the last several years. However, unlike learning-based image coding, which has already surpassed its handcrafted counterparts, learning-based video coding still has some ways to go. In this paper we present learned conditional coding modes for video coding (LCCM-VC), a video coding model that achieves state-of-the-art results among learning-based video coding methods. Our model utilizes conditional coding engines from the recent conditional augmented normalizing flows (CANF) pipeline, and introduces additional coding modes to improve compression performance. The compression efficiency is especially good in the high-quality/high-bitrate range, which is important for broadcast and video-on-demand streaming applications. The implementation of LCCM-VC is available at https://github.com/hadihdz/lccm_vc

eess.IV↗

arXiv2023

Multi-Task Learning for Screen Content Image Coding

With the rise of remote work and collaboration, compression of screen content images (SCI) is becoming increasingly important. While there are efficient codecs for natural images, as well as codecs for purely-synthetic images, those SCIs that contain both synthetic and natural content pose a particular challenge. In this paper, we propose a learning-based image coding model developed for such SCIs. By training an encoder to provide a latent representation suitable for two tasks -- input reconstruction and synthetic/natural region segmentation -- we create an effective SCI image codec whose strong performance is verified through experiments. Once trained, the second task (segmentation) need not be used; the codec still benefits from the segmentation-friendly latent representation.

eess.IV↗

arXiv2022

Privacy-Preserving Feature Coding for Machines

Automated machine vision pipelines do not need the exact visual content to perform their tasks. Therefore, there is a potential to remove private information from the data without significantly affecting the machine vision accuracy. We present a novel method to create a privacy-preserving latent representation of an image that could be used by a downstream machine vision model. This latent representation is constructed using adversarial training to prevent accurate reconstruction of the input while preserving the task accuracy. Specifically, we split a Deep Neural Network (DNN) model and insert an autoencoder whose purpose is to both reduce the dimensionality as well as remove information relevant to input reconstruction while minimizing the impact on task accuracy. Our results show that input reconstruction ability can be reduced by about 0.8 dB at the equivalent task accuracy, with degradation concentrated near the edges, which is important for privacy. At the same time, 30% bit savings are achieved compared to coding the features directly.

eess.IV↗

arXiv2022

Joint Image Compression and Denoising via Latent-Space Scalability

When it comes to image compression in digital cameras, denoising is traditionally performed prior to compression. However, there are applications where image noise may be necessary to demonstrate the trustworthiness of the image, such as court evidence and image forensics. This means that noise itself needs to be coded, in addition to the clean image itself. In this paper, we present a learning-based image compression framework where image denoising and compression are performed jointly. The latent space of the image codec is organized in a scalable manner such that the clean image can be decoded from a subset of the latent space (the base layer), while the noisy image is decoded from the full latent space at a higher rate. Using a subset of the latent space for the denoised image allows denoising to be carried out at a lower rate. Besides providing a scalable representation of the noisy input image, performing denoising jointly with compression makes intuitive sense because noise is hard to compress; hence, compressibility is one of the criteria that may help distinguish noise from the signal. The proposed codec is compared against established compression and denoising benchmarks, and the experiments reveal considerable bitrate savings compared to a cascade combination of a state-of-the-art codec and a state-of-the-art denoiser.

eess.IV↗

arXiv2022

Scalable Video Coding for Humans and Machines

Video content is watched not only by humans, but increasingly also by machines. For example, machine learning models analyze surveillance video for security and traffic monitoring, search through YouTube videos for inappropriate content, and so on. In this paper, we propose a scalable video coding framework that supports machine vision (specifically, object detection) through its base layer bitstream and human vision via its enhancement layer bitstream. The proposed framework includes components from both conventional and Deep Neural Network (DNN)-based video coding. The results show that on object detection, the proposed framework achieves 13-19% bit savings compared to state-of-the-art video codecs, while remaining competitive in terms of MS-SSIM on the human vision task.

eess.IV↗

arXiv2022

Adversarial Attacks on Human Vision

This article presents an introduction to visual attention retargeting, its connection to visual saliency, the challenges associated with it, and ideas for how it can be approached. The difficulty of attention retargeting as a saliency inversion problem lies in the lack of one-to-one mapping between saliency and the image domain, in addition to the possible negative impact of saliency alterations on image aesthetics. A few approaches from recent literature to solve this challenging problem are reviewed, and several suggestions for future development are presented.

cs.CV↗

arXiv2022

License Plate Privacy in Collaborative Visual Analysis of Traffic Scenes

Traffic scene analysis is important for emerging technologies such as smart traffic management and autonomous vehicles. However, such analysis also poses potential privacy threats. For example, a system that can recognize license plates may construct patterns of behavior of the corresponding vehicles' owners and use that for various illegal purposes. In this paper we present a system that enables traffic scene analysis while at the same time preserving license plate privacy. The system is based on a multi-task model whose latent space is selectively compressed depending on the amount of information the specific features carry about analysis tasks and private information. Effectiveness of the proposed method is illustrated by experiments on the Cityscapes dataset, for which we also provide license plate annotations.

cs.CV↗

arXiv2022

Does Video Compression Impact Tracking Accuracy?

Everyone "knows" that compressing a video will degrade the accuracy of object tracking. Yet, a literature search on this topic reveals that there is very little documented evidence for this presumed fact. Part of the reason is that, until recently, there were no object tracking datasets for uncompressed video, which made studying the effects of compression on tracking accuracy difficult. In this paper, using a recently published dataset that contains tracking annotations for uncompressed videos, we examined the degradation of tracking accuracy due to video compression using rigorous statistical methods. Specifically, we examined the impact of quantization parameter (QP) and motion search range (MSR) on Multiple Object Tracking Accuracy (MOTA). The results show that QP impacts MOTA at the 95% confidence level, while there is insufficient evidence to claim that MSR impacts MOTA. Moreover, regression analysis allows us to derive a quantitative relationship between MOTA and QP for the specific tracker used in the experiments.

cs.CV↗

arXiv2022

Practical Noise Simulation for RGB Images

This document describes a noise generator that simulates realistic noise found in smartphone cameras. The generator simulates Poissonian-Gaussian noise whose parameters have been estimated on the Smartphone Image Denoising Dataset (SIDD). The generator is available online, and is currently being used in compressed-domain denoising exploration experiments in JPEG AI.

eess.IV↗

arXiv2021

SFU-HW-Tracks-v1: Object Tracking Dataset on Raw Video Sequences

We present a dataset that contains object annotations with unique object identities (IDs) for the High Efficiency Video Coding (HEVC) v1 Common Test Conditions (CTC) sequences. Ground-truth annotations for 13 sequences were prepared and released as the dataset called SFU-HW-Tracks-v1. For each video frame, ground truth annotations include object class ID, object ID, and bounding box location and its dimensions. The dataset can be used to evaluate object tracking performance on uncompressed video sequences and study the relationship between video compression and object tracking.

cs.CV↗

arXiv2021

DFTS2: Simulating Deep Feature Transmission Over Packet Loss Channels

In edge-cloud collaborative intelligence (CI), an unreliable transmission channel exists in the information path of the AI model performing the inference. It is important to be able to simulate the performance of the CI system across an imperfect channel in order to understand system behavior and develop appropriate error control strategies. In this paper we present a simulation framework called DFTS2, which enables researchers to define the components of the CI system in TensorFlow~2, select a packet-based channel model with various parameters, and simulate system behavior under various channel conditions and error/loss control strategies. Using DFTS2, we also present the most comprehensive study to date of the packet loss concealment methods for collaborative image classification models.

eess.IV↗

arXiv2021

CALTeC: Content-Adaptive Linear Tensor Completion for Collaborative Intelligence

In collaborative intelligence, an artificial intelligence (AI) model is typically split between an edge device and the cloud. Feature tensors produced by the edge sub-model are sent to the cloud via an imperfect communication channel. At the cloud side, parts of the feature tensor may be missing due to packet loss. In this paper we propose a method called Content-Adaptive Linear Tensor Completion (CALTeC) to recover the missing feature data. The proposed method is fast, data-adaptive, does not require pre-training, and produces better results than existing methods for tensor data recovery in collaborative intelligence.

eess.IV↗