arXiv subjects

Ivan V. Bajić

Publications and source records attributed to Ivan V. Bajić.

At least 19 recordsLinked to original sources

arXiv2026

Bit Allocation Transfer for Perceptual Quality Enhancement of Traditional Video Codecs

Traditional block-based video codecs, such as H.264/AVC, H.265/HEVC and H.266/VVC, rely on hand-crafted Rate-Distortion Optimization (RDO) processes that primarily minimize Mean Squared Error (MSE), which correlates poorly with human perceptual quality. While neural video compression methods can easily optimize perceptually aligned metrics like MS-SSIM, their high computational complexity limits practical deployment. This paper proposes a novel bit allocation transfer framework that bridges these two paradigms to enhance the perceptual quality of conventional video codecs. Specifically, we train a quantization step generation model using a perceptual loss within a neural video compression framework (DCVC-FM). The model takes the original frame and a motion-compensated prediction as input and outputs a quantization step map. We then derive a block-wise bit ratio from this map and convert it into a Quantization Parameter (QP) map for a traditional video codec. Experimental results on the HEVC B$\sim$D dataset demonstrate that our method achieves 20.20\%, 8.25\%, and 8.37\% bitrate savings in terms of MS-SSIM compared with the standard reference software JM-19.0, HM-16.20, and VTM-23.0, respectively, with additional gains when utilizing predicted frames. Our approach effectively transfers the implicit perceptual importance learned by neural video compression models to guide block-level bit allocation in traditional video codecs without modifying their core decoding syntax.

eess.IV↗

arXiv2026

Understanding Rate-Distortion Performance in Distributed Transformer Inference

Transformers achieve superior performance on many tasks, but impose heavy compute and memory requirements during inference. This inference can be made more efficient by partitioning the process across multiple devices, which, in turn, requires compressing its intermediate representations. We study compressibility of transformer's intermediate representations via learned compression through the lens of rate-distortion and the theory of usable information. Our study reveals that, unlike convolutional models, deeper representations in transformers become more difficult to compress. The reason for this behavior is twofold: first, the complexity of representation increases as we move deeper into the transformer, necessitating a higher rate; and second, the higher complexity of representations worsens the generaliztion bound for learned entropy estimates, which further compromises compression performance. Through a combination of experiments and theory, we characterize and analyze the compressibility of transformer representations, derive bounds on the achievable rate of learned codecs applied to these representations, and offer a unified lens for understanding rate-distortion performance in representation coding.

cs.LG↗

arXiv2026

Context Adaptive Extended Chain Coding for Semantic Map Compression

Semantic maps are increasingly utilized in areas such as robotics, autonomous systems, and extended reality, motivating the investigation of efficient compression methods that preserve structured semantic information. This paper studies lossless compression of semantic maps through a novel chain-coding-based framework that explicitly exploits contour topology and shared boundaries between adjacent semantic regions. We propose an extended chain code (ECC) to represent long-range contour transitions more compactly, while retaining a legacy three-orthogonal chain code (3OT) as a fallback mode for further efficiency. To efficiently encode sequences of ECC symbols, a context-adaptive entropy coding scheme based on Markov modeling is employed. Furthermore, a skip-coding mechanism is introduced to eliminate redundant representations of shared contours between adjacent semantic regions, supporting both complete and partial skips via run-length signaling. Experimental results demonstrate that the proposed method achieves an average bitrate reduction of 18\% compared with a state-of-the-art benchmark on semantic map datasets. In addition, the proposed encoder and decoder achieve up to 98\% and 50\% runtime reduction, respectively, relative to a modern generic lossless codec. Extended evaluations on occupancy maps further confirm consistent compression gains across the majority of tested scenarios. The source code is made publicly available at https://github.com/InterDigitalInc/LosslessSegmentationMapCompression.

eess.IV↗

arXiv2026

Differentiable Proxy Learning for Adaptive Quantization Control in H.264 Video Coding

H.264 has been the most widely used video coding format for the past two decades due to its relative simplicity, efficiency, and wide availability of software and hardware implementations. However, optimizing codec parameters such as the quantization parameter (QP) for specific objectives (e.g., perceptual quality or machine vision tasks) is challenging due to the non-differentiable nature of standard video codecs. While differentiable proxies have recently been used to enable gradient-based optimization around standard codecs, their fidelity to the target codec is rarely explicitly characterized. In this paper, we propose a differentiable proxy learning method for H.264 intra codec to enable adaptive quantization control. Built upon a variable-rate learned compression model, the proposed proxy is made differentiable with respect to codec QP through a soft-indexing mechanism. It is then trained to approximate the rate-distortion behavior of H.264 under two quantization settings: global-QP, which uses one QP per image, and spatial-QP, which assigns QPs at the macroblock level. Using the frozen trained proxy, we develop a proxy-based adaptive quantization (AQ) framework for both perceptual optimization and machine vision tasks. Experimental results demonstrate that the proposed proxies closely approximate the rate-distortion behavior of H.264 intra codec. The resulting proxy-based AQ framework consistently improves rate-task trade-offs over fixed-QP H.264 baselines, achieving BD-rate reduction of up to 17.12% for semantic segmentation and 15.30% for MS-SSIM.

eess.IV↗

arXiv2026

Lossy Common Information in a Learnable Gray-Wyner Network

Many computer vision tasks share substantial overlapping information, yet conventional codecs tend to ignore this, leading to redundant and inefficient representations. The Gray-Wyner network, a classical concept from information theory, offers a principled framework for separating common and task-specific information. Inspired by this idea, we develop a learnable three-channel codec that disentangles shared information from task-specific details across multiple vision tasks. We characterize the limits of this approach through the notion of lossy common information, and propose an optimization objective that balances inherent tradeoffs in learning such representations. Through comparisons of three codec architectures on two-task scenarios spanning six vision benchmarks, we demonstrate that our approach substantially reduces redundancy and consistently outperforms independent coding. These results highlight the practical value of revisiting Gray-Wyner theory in modern machine learning contexts, bridging classic information theory with task-driven representation learning.

cs.LG↗

arXiv2025

Bit Allocation Transfer for Perceptual Quality Enhancement of VVC Intra Coding

Mainstream image and video coding standards -- including state-of-the-art codecs like H.266/VVC, AVS3, and AV1 -- adopt a block-based hybrid coding framework. While this framework facilitates straightforward optimization for Peak Signal-to-Noise Ratio (PSNR), it struggles to effectively optimize perceptually-aligned metrics such as Multi-Scale Structural Similarity (MS-SSIM). To address this challenge, this paper proposes a low-complexity method to enhance perceptual quality in VVC intra coding by transferring bit allocation knowledge from end-to-end image compression. We introduce a lightweight model trained with perceptual losses to generate a quantization step map. This map implicitly captures block-level perceptual importance, enabling efficient derivation of a QP map for VVC. Experiments on Kodak and CLIC datasets demonstrate significant advantages, both in execution time and perceptual metric performance, with more than 11% BD-rate reduction in terms of MS-SSIM. Our scheme provides an efficient, practical pathway for perceptual enhancement of traditional codecs.

eess.IV↗

arXiv2025

Rate-Accuracy Bounds in Visual Coding for Machines

Increasingly, visual signals such as images, videos and point clouds are being captured solely for the purpose of automated analysis by computer vision models. Applications include traffic monitoring, robotics, autonomous driving, smart home, and many others. This trend has led to the need to develop compression strategies for these signals for the purpose of analysis rather than reconstruction, an area often referred to as "coding for machines." By drawing parallels with lossy coding of a discrete memoryless source, in this paper we derive rate-accuracy bounds on several popular problems in visual coding for machines, and compare these with state-of-the-art results from the literature. The comparison shows that the current results are at least an order of magnitude -- and in some cases two or three orders of magnitude -- away from the theoretical bounds in terms of the bitrate needed to achieve a certain level of accuracy. This, in turn, means that there is much room for improvement in the current methods for visual coding for machines.

eess.IV↗

arXiv2025

Semantics-Guided Generative Image Compression

Advancements in text-to-image generative AI with large multimodal models are spreading into the field of image compression, creating high-quality representation of images at extremely low bit rates. This work introduces novel components to the existing multimodal image semantic compression (MISC) approach, enhancing the quality of the generated images in terms of PSNR and perceptual metrics. The new components include semantic segmentation guidance for the generative decoder, as well as content-adaptive diffusion, which controls the number of diffusion steps based on image characteristics. The results show that our newly introduced methods significantly improve the baseline MISC model while also decreasing the complexity. As a result, both the encoding and decoding time are reduced by more than 36%. Moreover, the proposed compression framework outperforms mainstream codecs in terms of perceptual similarity and quality. The code and visual examples are available.

eess.IV↗

arXiv2024

SplitFedZip: Learned Compression for Data Transfer Reduction in Split-Federated Learning

Federated Learning (FL) enables multiple clients to train a collaborative model without sharing their local data. Split Learning (SL) allows a model to be trained in a split manner across different locations. Split-Federated (SplitFed) learning is a more recent approach that combines the strengths of FL and SL. SplitFed minimizes the computational burden of FL by balancing computation across clients and servers, while still preserving data privacy. This makes it an ideal learning framework across various domains, especially in healthcare, where data privacy is of utmost importance. However, SplitFed networks encounter numerous communication challenges, such as latency, bandwidth constraints, synchronization overhead, and a large amount of data that needs to be transferred during the learning process. In this paper, we propose SplitFedZip -- a novel method that employs learned compression to reduce data transfer in SplitFed learning. Through experiments on medical image segmentation, we show that learned compression can provide a significant data communication reduction in SplitFed learning, while maintaining the accuracy of the final trained model. The implementation is available at: \url{https://github.com/ChamaniS/SplitFedZip}.

cs.LG↗

arXiv2024

Learned Scalable Video Coding For Humans and Machines

Video coding has traditionally been developed to support services such as video streaming, videoconferencing, digital TV, and so on. The main intent was to enable human viewing of the encoded content. However, with the advances in deep neural networks (DNNs), encoded video is increasingly being used for automatic video analytics performed by machines. In applications such as automatic traffic monitoring, analytics such as vehicle detection, tracking and counting, would run continuously, while human viewing could be required occasionally to review potential incidents. To support such applications, a new paradigm for video coding is needed that will facilitate efficient representation and compression of video for both machine and human use in a scalable manner. In this manuscript, we introduce an end-to-end learnable video codec that supports a machine vision task in its base layer, while its enhancement layer, together with the base layer, supports input reconstruction for human viewing. The proposed system is constructed based on the concept of conditional coding to achieve better compression gains. Comprehensive experimental evaluations conducted on four standard video datasets demonstrate that our framework outperforms both state-of-the-art learned and conventional video codecs in its base layer, while maintaining comparable performance on the human vision task in its enhancement layer. Implementation of the proposed system is available at https://github.com/hadipardis/svc

eess.IV↗

arXiv2024

Learned Multimodal Compression for Autonomous Driving

Autonomous driving sensors generate an enormous amount of data. In this paper, we explore learned multimodal compression for autonomous driving, specifically targeted at 3D object detection. We focus on camera and LiDAR modalities and explore several coding approaches. One approach involves joint coding of fused modalities, while others involve coding one modality first, followed by conditional coding of the other modality. We evaluate the performance of these coding schemes on the nuScenes dataset. Our experimental results indicate that joint coding of fused modalities yields better results compared to the alternatives.

eess.IV↗

arXiv2024

Learned Compression of Encoding Distributions

The entropy bottleneck introduced by Ballé et al. is a common component used in many learned compression models. It encodes a transformed latent representation using a static distribution whose parameters are learned during training. However, the actual distribution of the latent data may vary wildly across different inputs. The static distribution attempts to encompass all possible input distributions, thus fitting none of them particularly well. This unfortunate phenomenon, sometimes known as the amortization gap, results in suboptimal compression. To address this issue, we propose a method that dynamically adapts the encoding distribution to match the latent data distribution for a specific input. First, our model estimates a better encoding distribution for a given input. This distribution is then compressed and transmitted as an additional side-information bitstream. Finally, the decoder reconstructs the encoding distribution and uses it to decompress the corresponding latent data. Our method achieves a Bjøntegaard-Delta (BD)-rate gain of -7.10% on the Kodak test dataset when applied to the standard fully-factorized architecture. Furthermore, considering computational complexity, the transform used by our method is an order of magnitude cheaper in terms of Multiply-Accumulate (MAC) operations compared to related side-information methods such as the scale hyperprior.

eess.IV↗

arXiv2024

Optimizing Split Points for Error-Resilient SplitFed Learning

Recent advancements in decentralized learning, such as Federated Learning (FL), Split Learning (SL), and Split Federated Learning (SplitFed), have expanded the potentials of machine learning. SplitFed aims to minimize the computational burden on individual clients in FL and parallelize SL while maintaining privacy. This study investigates the resilience of SplitFed to packet loss at model split points. It explores various parameter aggregation strategies of SplitFed by examining the impact of splitting the model at different points-either shallow split or deep split-on the final global model performance. The experiments, conducted on a human embryo image segmentation task, reveal a statistically significant advantage of a deeper split point.

cs.AI↗

arXiv2024

Mutual Information Analysis in Multimodal Learning Systems

In recent years, there has been a significant increase in applications of multimodal signal processing and analysis, largely driven by the increased availability of multimodal datasets and the rapid progress in multimodal learning systems. Well-known examples include autonomous vehicles, audiovisual generative systems, vision-language systems, and so on. Such systems integrate multiple signal modalities: text, speech, images, video, LiDAR, etc., to perform various tasks. A key issue for understanding such systems is the relationship between various modalities and how it impacts task performance. In this paper, we employ the concept of mutual information (MI) to gain insight into this issue. Taking advantage of the recent progress in entropy modeling and estimation, we develop a system called InfoMeter to estimate MI between modalities in a multimodal learning system. We then apply InfoMeter to analyze a multimodal 3D object detection system over a large-scale dataset for autonomous driving. Our experiments on this system suggest that a lower MI between modalities is beneficial for detection accuracy. This new insight may facilitate improvements in the development of future multimodal learning systems.

eess.IV↗

arXiv2024

Compressive Feature Selection for Remote Visual Multi-Task Inference

Deep models produce a number of features in each internal layer. A key problem in applications such as feature compression for remote inference is determining how important each feature is for the task(s) performed by the model. The problem is especially challenging in the case of multi-task inference, where the same feature may carry different importance for different tasks. In this paper, we examine how effective is mutual information (MI) between a feature and a model's task output as a measure of the feature's importance for that task. Experiments involving hard selection and soft selection (unequal compression) based on MI are carried out to compare the MI-based method with alternative approaches. Multi-objective analysis is provided to offer further insight.

eess.IV↗

arXiv2024

Scalable Human-Machine Point Cloud Compression

Due to the limited computational capabilities of edge devices, deep learning inference can be quite expensive. One remedy is to compress and transmit point cloud data over the network for server-side processing. Unfortunately, this approach can be sensitive to network factors, including available bitrate. Luckily, the bitrate requirements can be reduced without sacrificing inference accuracy by using a machine task-specialized codec. In this paper, we present a scalable codec for point-cloud data that is specialized for the machine task of classification, while also providing a mechanism for human viewing. In the proposed scalable codec, the "base" bitstream supports the machine task, and an "enhancement" bitstream may be used for better input reconstruction performance for human viewing. We base our architecture on PointNet++, and test its efficacy on the ModelNet40 dataset. We show significant improvements over prior non-specialized codecs.

cs.CV↗

arXiv2023

Adversarial Attacks and Defenses on 3D Point Cloud Classification: A Survey

Deep learning has successfully solved a wide range of tasks in 2D vision as a dominant AI technique. Recently, deep learning on 3D point clouds is becoming increasingly popular for addressing various tasks in this field. Despite remarkable achievements, deep learning algorithms are vulnerable to adversarial attacks. These attacks are imperceptible to the human eye but can easily fool deep neural networks in the testing and deployment stage. To encourage future research, this survey summarizes the current progress on adversarial attack and defense techniques on point cloud classification.This paper first introduces the principles and characteristics of adversarial attacks and summarizes and analyzes adversarial example generation methods in recent years. Additionally, it provides an overview of defense strategies, organized into data-focused and model-focused methods. Finally, it presents several current challenges and potential future research directions in this domain.

cs.CV↗

arXiv2023

Learned Point Cloud Compression for Classification

Deep learning is increasingly being used to perform machine vision tasks such as classification, object detection, and segmentation on 3D point cloud data. However, deep learning inference is computationally expensive. The limited computational capabilities of end devices thus necessitate a codec for transmitting point cloud data over the network for server-side processing. Such a codec must be lightweight and capable of achieving high compression ratios without sacrificing accuracy. Motivated by this, we present a novel point cloud codec that is highly specialized for the machine task of classification. Our codec, based on PointNet, achieves a significantly better rate-accuracy trade-off in comparison to alternative methods. In particular, it achieves a 94% reduction in BD-bitrate over non-specialized codecs on the ModelNet40 dataset. For low-resource end devices, we also propose two lightweight configurations of our encoder that achieve similar BD-bitrate reductions of 93% and 92% with 3% and 5% drops in top-1 accuracy, while consuming only 0.470 and 0.048 encoder-side kMACs/point, respectively. Our codec demonstrates the potential of specialized codecs for machine analysis of point clouds, and provides a basis for extension to more complex tasks and datasets in the future.

eess.IV↗