arXiv subjects

Ivan V. Bajic

Publications and source records attributed to Ivan V. Bajic.

At least 19 recordsLinked to original sources

arXiv2026

Prompt-Guided Prefiltering for VLM Image Compression

The rapid progress of large Vision-Language Models (VLMs) has enabled a wide range of applications, such as image understanding and Visual Question Answering (VQA). Query images are often uploaded to the cloud, where VLMs are typically hosted, hence efficient image compression becomes crucial. However, traditional human-centric codecs are suboptimal in this setting because they preserve many task-irrelevant details. Existing Image Coding for Machines (ICM) methods also fall short, as they assume a fixed set of downstream tasks and cannot adapt to prompt-driven VLMs with an open-ended variety of objectives. We propose a lightweight, plug-and-play, prompt-guided prefiltering module to identify image regions most relevant to the text prompt, and consequently to the downstream task. The module preserves important details while smoothing out less relevant areas to improve compression efficiency. It is codec-agnostic and can be applied before conventional and learned encoders. Experiments on several VQA benchmarks show that our approach achieves a 25-50% average bitrate reduction while maintaining the same task accuracy. Our source code is available at https://github.com/bardia-az/pgp-vlm-compression.

eess.IV↗

arXiv2026

Smart Split-Federated Learning over Noisy Channels for Embryo Image Segmentation

Split-Federated (SplitFed) learning is an extension of federated learning that places minimal requirements on the clients computing infrastructure, since only a small portion of the overall model is deployed on the clients hardware. In SplitFed learning, feature values, gradient updates, and model updates are transferred across communication channels. In this paper, we study the effects of noise in the communication channels on the learning process and the quality of the final model. We propose a smart averaging strategy for SplitFed learning with the goal of improving resilience against channel noise. Experiments on a segmentation model for embryo images shows that the proposed smart averaging strategy is able to tolerate two orders of magnitude stronger noise in the communication channels compared to conventional averaging, while still maintaining the accuracy of the final model.

cs.CV↗

arXiv2025

How Universal Are SAM2 Features?

The trade-off between general-purpose foundation vision models and their specialized counterparts is critical for efficient feature coding design and is not yet fully understood. We investigate this trade-off by comparing the feature versatility of the general-purpose Hiera encoder against the segmentation-specialized Segment Anything Model 2 (SAM2). Using a lightweight, trainable neck to probe the adaptability of their frozen features, we quantify the information-theoretic cost of specialization. Our results reveal that while SAM2's specialization is highly effective for spatially-related tasks like depth estimation, it comes at a cost. The specialized SAM2 encoder underperforms its generalist predecessor, Hiera, on conceptually distant tasks such as pose estimation and image captioning, demonstrating a measurable loss of broader semantic information. A novel cross-neck analysis on SAM2 reveals that each level of adaptation creates a further representational bottleneck. Our analysis illuminates these trade-offs in feature universality, providing a quantitative foundation for designing efficient feature coding and adaptation strategies for diverse downstream applications.

cs.CV↗

arXiv2025

Rate-Distortion Theory in Coding for Machines and its Application

Recent years have seen a tremendous growth in both the capability and popularity of automatic machine analysis of images and video. As a result, a growing need for efficient compression methods optimized for machine vision, rather than human vision, has emerged. To meet this growing demand, several methods have been developed for image and video coding for machines. Unfortunately, while there is a substantial body of knowledge regarding rate-distortion theory for human vision, the same cannot be said of machine analysis. In this paper, we extend the current rate-distortion theory for machines, providing insight into important design considerations of machine-vision codecs. We then utilize this newfound understanding to improve several methods for learnable image coding for machines. Our proposed methods achieve state-of-the-art rate-distortion performance on several computer vision tasks such as classification, instance segmentation, and object detection.

eess.IV↗

arXiv2024

Understanding Key Point Cloud Features for Development Three-dimensional Adversarial Attacks

Adversarial attacks pose serious challenges for deep neural network (DNN)-based analysis of various input signals. In the case of three-dimensional point clouds, methods have been developed to identify points that play a key role in network decision, and these become crucial in generating existing adversarial attacks. For example, a saliency map approach is a popular method for identifying adversarial drop points, whose removal would significantly impact the network decision. This paper seeks to enhance the understanding of three-dimensional adversarial attacks by exploring which point cloud features are most important for predicting adversarial points. Specifically, Fourteen key point cloud features such as edge intensity and distance from the centroid are defined, and multiple linear regression is employed to assess their predictive power for adversarial points. Based on critical feature selection insights, a new attack method has been developed to evaluate whether the selected features can generate an attack successfully. Unlike traditional attack methods that rely on model-specific vulnerabilities, this approach focuses on the intrinsic characteristics of the point clouds themselves. It is demonstrated that these features can predict adversarial points across four different DNN architectures, Point Network (PointNet), PointNet++, Dynamic Graph Convolutional Neural Networks (DGCNN), and Point Convolutional Network (PointConv) outperforming random guessing and achieving results comparable to saliency map-based attacks. This study has important engineering applications, such as enhancing the security and robustness of three-dimensional point cloud-based systems in fields like robotics and autonomous driving.

cs.CV↗

arXiv2024

Privacy-Preserving Autoencoder for Collaborative Object Detection

Privacy is a crucial concern in collaborative machine vision where a part of a Deep Neural network (DNN) model runs on the edge, and the rest is executed on the cloud. In such applications, the machine vision model does not need the exact visual content to perform its task. Taking advantage of this potential, private information could be removed from the data insofar as it does not significantly impair the accuracy of the machine vision system. In this paper, we present an autoencoder-style network integrated within an object detection pipeline, which generates a latent representation of the input image that preserves task-relevant information while removing private information. Our approach employs an adversarial training strategy that not only removes private information from the bottleneck of the autoencoder but also promotes improved compression efficiency for feature channels coded by conventional codecs like VVC-Intra. We assess the proposed system using a realistic evaluation framework for privacy, directly measuring face and license plate recognition accuracy. Experimental results show that our proposed method is able to reduce the bitrate significantly at the same object detection accuracy compared to coding the input images directly, while keeping the face and license plate recognition accuracy on the images recovered from the bottleneck features low, implying strong privacy protection. Our code is available at https://github.com/bardia-az/ppa-code.

eess.IV↗

arXiv2023

VVC+M: Plug and Play Scalable Image Coding for Humans and Machines

Compression for machines is an emerging field, where inputs are encoded while optimizing the performance of downstream automated analysis. In scalable coding for humans and machines, the compressed representation used for machines is further utilized to enable input reconstruction. Often performed by jointly optimizing the compression scheme for both machine task and human perception, this results in sub-optimal rate-distortion (RD) performance for the machine side. We focus on the case of images, proposing to utilize the pre-existing residual coding capabilities of video codecs such as VVC to create a scalable codec from any image compression for machines (ICM) scheme. Using our approach we improve an existing scalable codec to achieve superior RD performance on the machine task, while remaining competitive for human perception. Moreover, our approach can be trained post-hoc for any given ICM scheme, and without creating a coupling between the quality of the machine analysis and human vision.

eess.IV↗

arXiv2023

Efficient Signed Graph Sampling via Balancing & Gershgorin Disc Perfect Alignment

A basic premise in graph signal processing (GSP) is that a graph encoding pairwise (anti-)correlations of the targeted signal as edge weights is exploited for graph filtering. However, existing fast graph sampling schemes are designed and tested only for positive graphs describing positive correlations. In this paper, we show that for datasets with strong inherent anti-correlations, a suitable graph contains both positive and negative edge weights. In response, we propose a linear-time signed graph sampling method centered on the concept of balanced signed graphs. Specifically, given an empirical covariance data matrix $\bar{\bf{C}}$, we first learn a sparse inverse matrix (graph Laplacian) $\mathcal{L}$ corresponding to a signed graph $\mathcal{G}$. We define the eigenvectors of Laplacian $\mathcal{L}_B$ for a balanced signed graph $\mathcal{G}_B$ -- approximating $\mathcal{G}$ via edge weight augmentation -- as graph frequency components. Next, we choose samples to minimize the low-pass filter reconstruction error in two steps. We first align all Gershgorin disc left-ends of Laplacian $\mathcal{L}_B$ at smallest eigenvalue $λ_{\min}(\mathcal{L}_B)$ via similarity transform $\mathcal{L}_p = §\mathcal{L}_B §^{-1}$, leveraging a recent linear algebra theorem called Gershgorin disc perfect alignment (GDPA). We then perform sampling on $\mathcal{L}_p$ using a previous fast Gershgorin disc alignment sampling (GDAS) scheme. Experimental results show that our signed graph sampling method outperformed existing fast sampling schemes noticeably on various datasets.

eess.SP↗

arXiv2022

Rate-Distortion in Image Coding for Machines

In recent years, there has been a sharp increase in transmission of images to remote servers specifically for the purpose of computer vision. In many applications, such as surveillance, images are mostly transmitted for automated analysis, and rarely seen by humans. Using traditional compression for this scenario has been shown to be inefficient in terms of bit-rate, likely due to the focus on human based distortion metrics. Thus, it is important to create specific image coding methods for joint use by humans and machines. One way to create the machine side of such a codec is to perform feature matching of some intermediate layer in a Deep Neural Network performing the machine task. In this work, we explore the effects of the layer choice used in training a learnable codec for humans and machines. We prove, using the data processing inequality, that matching features from deeper layers is preferable in the sense of rate-distortion. Next, we confirm our findings empirically by re-training an existing model for scalable human-machine coding. In our experiments we show the trade-off between the human and machine sides of such a scalable model, and discuss the benefit of using deeper layers for training in that regard.

cs.CV↗

arXiv2022

Collaborative Inference for AI-Empowered IoT Devices

Artificial intelligence (AI) technologies, and particularly deep learning systems, are traditionally the domain of large-scale cloud servers, which have access to high computational and energy resources. Nonetheless, in Internet-of-Things (IoT) networks, the interface with the real-world is carried out using edge devices that are limited in hardware and can communicate. The conventional approach to provide AI processing to data collected by edge devices involves sending samples to the cloud, at the cost of latency, communication, connectivity, and privacy concerns. Consequently, recent years have witnessed a growing interest in enabling AI-aided inference on edge devices by leveraging their communication capabilities to establish collaborative inference. This article reviews candidate strategies for facilitating the transition of AI to IoT devices via collaboration. We identify the need to operate in different mobility and connectivity constraints as a motivating factor to consider multiple schemes, which can be roughly divided into methods where inference is done remotely, i.e., on the cloud, and those that infer on the edge. We identify the key characteristics of each strategy in terms of inference accuracy, communication latency, privacy, and connectivity requirements, providing a systematic comparison between existing approaches. We conclude by presenting future research challenges and opportunities arising from the concept of collaborative inference.

eess.SP↗

arXiv2022

Scalable Image Coding for Humans and Machines

At present, and increasingly so in the future, much of the captured visual content will not be seen by humans. Instead, it will be used for automated machine vision analytics and may require occasional human viewing. Examples of such applications include traffic monitoring, visual surveillance, autonomous navigation, and industrial machine vision. To address such requirements, we develop an end-to-end learned image codec whose latent space is designed to support scalability from simpler to more complicated tasks. The simplest task is assigned to a subset of the latent space (the base layer), while more complicated tasks make use of additional subsets of the latent space, i.e., both the base and enhancement layer(s). For the experiments, we establish a 2-layer and a 3-layer model, each of which offers input reconstruction for human vision, plus machine vision task(s), and compare them with relevant benchmarks. The experiments show that our scalable codecs offer 37%-80% bitrate savings on machine vision tasks compared to best alternatives, while being comparable to state-of-the-art image codecs in terms of input reconstruction.

eess.IV↗

arXiv2021

Latent-space scalability for multi-task collaborative intelligence

We investigate latent-space scalability for multi-task collaborative intelligence, where one of the tasks is object detection and the other is input reconstruction. In our proposed approach, part of the latent space can be selectively decoded to support object detection while the remainder can be decoded when input reconstruction is needed. Such an approach allows reduced computational resources when only object detection is required, and this can be achieved without reconstructing input pixels. By varying the scaling factors of various terms in the training loss function, the system can be trained to achieve various trade-offs between object detection accuracy and input reconstruction quality. Experiments are conducted to demonstrate the adjustable system performance on the two tasks compared to the relevant benchmarks.

eess.IV↗

arXiv2020

Exploring Bayesian Surprise to Prevent Overfitting and to Predict Model Performance in Non-Intrusive Load Monitoring

Non-Intrusive Load Monitoring (NILM) is a field of research focused on segregating constituent electrical loads in a system based only on their aggregated signal. Significant computational resources and research time are spent training models, often using as much data as possible, perhaps driven by the preconception that more data equates to more accurate models and better performing algorithms. When has enough prior training been done? When has a NILM algorithm encountered new, unseen data? This work applies the notion of Bayesian surprise to answer these questions which are important for both supervised and unsupervised algorithms. We quantify the degree of surprise between the predictive distribution (termed postdictive surprise), as well as the transitional probabilities (termed transitional surprise), before and after a window of observations. We compare the performance of several benchmark NILM algorithms supported by NILMTK, in order to establish a useful threshold on the two combined measures of surprise. We validate the use of transitional surprise by exploring the performance of a popular Hidden Markov Model as a function of surprise threshold. Finally, we explore the use of a surprise threshold as a regularization technique to avoid overfitting in cross-dataset performance. Although the generality of the specific surprise threshold discussed herein may be suspect without further testing, this work provides clear evidence that a point of diminishing returns of model performance with respect to dataset size exists. This has implications for future model development, dataset acquisition, as well as aiding in model flexibility during deployment.

cs.AI↗

arXiv2020

PowerGAN: Synthesizing Appliance Power Signatures Using Generative Adversarial Networks

Non-intrusive load monitoring (NILM) allows users and energy providers to gain insight into home appliance electricity consumption using only the building's smart meter. Most current techniques for NILM are trained using significant amounts of labeled appliances power data. The collection of such data is challenging, making data a major bottleneck in creating well generalizing NILM solutions. To help mitigate the data limitations, we present the first truly synthetic appliance power signature generator. Our solution, PowerGAN, is based on conditional, progressively growing, 1-D Wasserstein generative adversarial network (GAN). Using PowerGAN, we are able to synthesise truly random and realistic appliance power data signatures. We evaluate the samples generated by PowerGAN in a qualitative way as well as numerically by using traditional GAN evaluation methods such as the Inception score.

eess.SP↗

arXiv2020

Back-and-Forth prediction for deep tensor compression

Recent AI applications such as Collaborative Intelligence with neural networks involve transferring deep feature tensors between various computing devices. This necessitates tensor compression in order to optimize the usage of bandwidth-constrained channels between devices. In this paper we present a prediction scheme called Back-and-Forth (BaF) prediction, developed for deep feature tensors, which allows us to dramatically reduce tensor size and improve its compressibility. Our experiments with a state-of-the-art object detector demonstrate that the proposed method allows us to significantly reduce the number of bits needed for compressing feature tensors extracted from deep within the model, with negligible degradation of the detection performance and without requiring any retraining of the network weights. We achieve a 62% and 75% reduction in tensor size while keeping the loss in accuracy of the network to less than 1% and 2%, respectively.

cs.LG↗

arXiv2020

Towards Automated Swimming Analytics Using Deep Neural Networks

Methods for creating a system to automate the collection of swimming analytics on a pool-wide scale are considered in this paper. There has not been much work on swimmer tracking or the creation of a swimmer database for machine learning purposes. Consequently, methods for collecting swimmer data from videos of swim competitions are explored and analyzed. The result is a guide to the creation of a comprehensive collection of swimming data suitable for training swimmer detection and tracking systems. With this database in place, systems can then be created to automate the collection of swimming analytics.

cs.CV↗

arXiv2019

3D Point Cloud Super-Resolution via Graph Total Variation on Surface Normals

Point cloud is a collection of 3D coordinates that are discrete geometric samples of an object's 2D surfaces. Using a low-cost 3D scanner to acquire data means that point clouds are often in lower resolution than desired for rendering on high-resolution displays. Building on recent advances in graph signal processing, we design a local algorithm for 3D point cloud super-resolution (SR). First, we initialize new points at centroids of local triangles formed using the low-resolution point cloud, and connect all points using a k-nearestneighbor graph. Then, to establish a linear relationship between surface normals and 3D point coordinates, we perform bipartite graph approximation to divide all nodes into two disjoint sets, which are optimized alternately until convergence. For each node set, to promote piecewise smooth (PWS) 2D surfaces, we design a graph total variation (GTV) objective for nearby surface normals, under the constraint that coordinates of the original points are preserved. We pursue an augmented Lagrangian approach to tackle the optimization, and solve the unconstrained equivalent using the alternating method of multipliers (ADMM). Extensive experiments show that our proposed point cloud SR algorithm outperforms competing schemes objectively and subjectively for a large variety of point clouds.

eess.SP↗

arXiv2019

Datasets for Face and Object Detection in Fisheye Images

We present two new fisheye image datasets for training face and object detection models: VOC-360 and Wider-360. The fisheye images are created by post-processing regular images collected from two well-known datasets, VOC2012 and Wider Face, using a model for mapping regular to fisheye images implemented in Matlab. VOC-360 contains 39,575 fisheye images for object detection, segmentation, and classification. Wider-360 contains 63,897 fisheye images for face detection. These datasets will be useful for developing face and object detectors as well as segmentation modules for fisheye images while the efforts to collect and manually annotate true fisheye images are underway.

cs.CV↗