4 citations · 10 across the 13 of their papers we have counts for
16 papers
Saliency Diversified Deep Ensemble for Robustness to Adversaries
Alex Bogun, Dimche Kostadinov, Damian Borth
Deep learning models have shown incredible performance on numerous image recognition, classification, and reconstruction tasks. Although very appealing and valuable due to their pr…
Hyper-Representations: Self-Supervised Representation Learning on Neural Network Weights for Model Characteristic Prediction
Konstantin Schürholt, Dimche Kostadinov, Damian Borth
Self-Supervised Learning (SSL) has been shown to learn useful and information-preserving representations. Neural Networks (NNs) are widely applied, yet their weight space is still…
Zero-shot Voice Conversion via Self-supervised Prosody Representation Learning
Shijun Wang, Dimche Kostadinov, Damian Borth
Voice Conversion (VC) for unseen speakers, also known as zero-shot VC, is an attractive research topic as it enables a range of applications like voice customizing, animation produ…
Privacy-Preserving Near Neighbor Search via Sparse Coding with Ambiguation
Behrooz Razeghi, Sohrab Ferdowsi, Dimche Kostadinov +2
In this paper, we propose a framework for privacy-preserving approximate near neighbor search via stochastic sparsifying encoding. The core of the framework relies on sparse coding…
Unsupervised Feature Learning for Event Data: Direct vs Inverse Problem Formulation
Dimche Kostadinov, Davide Scaramuzza
Event-based cameras record an asynchronous stream of per-pixel brightness changes. As such, they have numerous advantages over the standard frame-based cameras, including high temp…
Online Weight-adaptive Nonlinear Model Predictive Control
Dimche Kostadinov, Davide Scaramuzza
Nonlinear Model Predictive Control (NMPC) is a powerful and widely used technique for nonlinear dynamic process control under constraints. In NMPC, the state and control weights of…
Network Parameter Learning Using Nonlinear Transforms, Local Representation Goals and Local Propagation Constraints
Dimche Kostadinov, Behrooz Razdehi, Slava Voloshynovskiy
In this paper, we introduce a novel concept for learning of the parameters in a neural network. Our idea is grounded on modeling a learning problem that addresses a trade-off betwe…
Clustering with Jointly Learned Nonlinear Transforms Over Discriminating Min-Max Similarity/Dissimilarity Assignment
Dimche Kostadinov, Behrooz Razeghi, Taras Holotyak +1
This paper presents a novel clustering concept that is based on jointly learned nonlinear transforms (NTs) with priors on the information loss and the discrimination. We introduce…
Privacy-Preserving Identification via Layered Sparse Code Design: Distributed Servers and Multiple Access Authorization
Behrooz Razeghi, Slava Voloshynovskiy, Sohrab Ferdowsi +1
We propose a new computationally efficient privacy-preserving identification framework based on layered sparse coding. The key idea of the proposed framework is a sparsifying trans…
Network Learning with Local Propagation
Dimche Kostadinov, Behrooz Razeghi, Sohrab Ferdowsi +1
This paper presents a locally decoupled network parameter learning with local propagation. Three elements are taken into account: (i) sets of nonlinear transforms that describe the…
A multi-layer network based on Sparse Ternary Codes for universal vector compression
Sohrab Ferdowsi, Slava Voloshynovskiy, Dimche Kostadinov
We present the multi-layer extension of the Sparse Ternary Codes (STC) for fast similarity search where we focus on the reconstruction of the database vectors from the ternary code…
Privacy Preserving Identification Using Sparse Approximation with Ambiguization
Behrooz Razeghi, Slava Voloshynovskiy, Dimche Kostadinov +1
In this paper, we consider a privacy preserving encoding framework for identification applications covering biometrics, physical object security and the Internet of Things (IoT). T…
A multi-layer image representation using Regularized Residual Quantization: application to compression and denoising
Sohrab Ferdowsi, Slava Voloshynovskiy, Dimche Kostadinov
A learning-based framework for representation of domain-specific images is proposed where joint compression and denoising can be done using a VQ-based multi-layer network. While it…
Regularized Residual Quantization: a multi-layer sparse dictionary learning approach
Sohrab Ferdowsi, Slava Voloshynovskiy, Dimche Kostadinov
The Residual Quantization (RQ) framework is revisited where the quantization distortion is being successively reduced in multi-layers. Inspired by the reverse-water-filling paradig…
Sparse Ternary Codes for similarity search have higher coding gain than dense binary codes
Sohrab Ferdowsi, Slava Voloshynovskiy, Dimche Kostadinov +1
This paper addresses the problem of Approximate Nearest Neighbor (ANN) search in pattern recognition where feature vectors in a database are encoded as compact codes in order to sp…
Sparse Multi-layer Image Approximation: Facial Image Compression
Sohrab Ferdowsi, Svyatoslav Voloshynovskiy, Dimche Kostadinov
We propose a scheme for multi-layer representation of images. The problem is first treated from an information-theoretic viewpoint where we analyze the behavior of different source…