Search Results for author:
Found 62 papers, 18 papers with code
persoDA: Personalized Data Augmentation forPersonalized ASR
persoDA aims to augment training with data specifically tuned towards acoustic characteristics of the end-user, as opposed to standard augmentation based on Multi-Condition Training (MCT) that applies random reverberation and noises.
LoRA.rar: Learning to Merge LoRAs via Hypernetworks for Subject-Style Conditioned Image Generation
Recent advancements in image generation models have enabled personalized image creation with both user-defined subjects (content) and styles.
DreamCache: Finetuning-Free Lightweight Personalized Image Generation via Feature Caching
Personalized image generation requires text-to-image generative models that capture the core features of a reference subject to allow for controlled generation across different contexts.
Randomized Asymmetric Chain of LoRA: The First Meaningful Theoretical Framework for Low-Rank Adaptation
One of the most widely used methods is Low-Rank Adaptation (LoRA), with adaptation update expressed as the product of two low-rank matrices.
Swiss DINO: Efficient and Versatile Vision Framework for On-device Personal Object Search
In this paper, we address a recent trend in robotic home appliances to include vision systems on personal devices, capable of personalizing the appliances on the fly.
Enhanced Model Robustness to Input Corruptions by Per-corruption Adaptation of Normalization Statistics
In this paper, we introduce Per-corruption Adaptation of Normalization statistics (PAN) to enhance the model robustness of vision systems.
LoRA-Guard: Parameter-Efficient Guardrail Adaptation for Content Moderation of Large Language Models
Guardrails have emerged as an alternative to safety alignment for content moderation of large language models (LLMs).
Cross-Architecture Auxiliary Feature Space Translation for Efficient Few-Shot Personalized Object Detection
We introduce a conditional coarse-to-fine few-shot learner to refine the coarse predictions made by an efficient object detector, showing that using an off-the-shelf model leads to poor personalization due to neural collapse.
Model Merging and Safety Alignment: One Bad Model Spoils the Bunch
Our experiments illustrate the effectiveness of integrating alignment-related data during merging, resulting in models that excel in both domain expertise and alignment.
DP-DyLoRA: Fine-Tuning Transformer-Based Models On-Device under Differentially Private Federated Learning using Dynamic Low-Rank Adaptation
The randomness makes it infeasible to train large transformer-based models, common in modern federated learning systems.
Object-conditioned Bag of Instances for Few-Shot Personalized Instance Recognition
Nowadays, users demand for increased personalization of vision systems to localize and identify personal instances of objects (e. g., my dog rather than dog) from a few-shot dataset only.
FFT-based Selection and Optimization of Statistics for Robust Recognition of Severely Corrupted Images
Improving model robustness in case of corrupted images is among the key challenges to enable robust vision systems on smart devices, such as robotic agents.
Deep Neural Network Models Trained With A Fixed Random Classifier Transfer Better Across Domains
Inspired by NC properties, we explore in this paper the transferability of DNN models trained with their last layer weight fixed according to ETF.
A Modular System for Enhanced Robustness of Multimedia Understanding Networks via Deep Parametric Estimation
To this end, we design a small, modular, and efficient (just 2GFLOPs to process a Full HD image) system to enhance input data for robust downstream multimedia understanding with minimal computational cost.
HOP to the Next Tasks and Domains for Continual Learning in NLP
Continual Learning (CL) aims to learn a sequence of problems (i. e., tasks and domains) by transferring knowledge acquired on previous problems, whilst avoiding forgetting of past ones.
On-Device Speaker Anonymization of Acoustic Embeddings for ASR based onFlexible Location Gradient Reversal Layer
Our paper proposes a privacy-enhancing framework that targets speaker identity anonymization while preserving speech recognition accuracy for our downstream task~-~Automatic Speech Recognition (ASR).
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Online Continual Learning in Keyword Spotting for Low-Resource Devices via Pooling High-Order Temporal Statistics
Keyword Spotting (KWS) models on embedded devices should adapt fast to new user-defined words without forgetting previous ones.
A Model for Every User and Budget: Label-Free and Personalized Mixed-Precision Quantization
Recent advancement in Automatic Speech Recognition (ASR) has produced large AI models, which become impractical for deployment in mobile devices.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Online Continual Learning for Robust Indoor Object Recognition
Vision systems mounted on home robots need to interact with unseen classes in changing environments.
Conceptual and Hierarchical Latent Space Decomposition for Face Editing
For this purpose, a novel latent space decomposition pipeline is introduced using transformer networks and generative models.
Progressive Self-Distillation for Ground-to-Aerial Perception Knowledge Transfer
In this paper, we introduce the ground-to-aerial perception knowledge transfer and propose a progressive semi-supervised learning framework that enables drone perception using only labeled data of ground viewpoint and unlabeled data of flying viewpoints.
Dense Depth Distillation with Out-of-Distribution Simulated Images
We study data-free knowledge distillation (KD) for monocular depth estimation (MDE), which learns a lightweight model for real-world depth perception tasks by compressing it from a trained teacher model while lacking training data in the target domain.
pMCT: Patched Multi-Condition Training for Robust Speech Recognition
For analyses on robust ASR, we employed pMCT on the VOiCES dataset which is a noisy reverberant dataset created using utterances from LibriSpeech.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
FedNST: Federated Noisy Student Training for Automatic Speech Recognition
To this end, we propose FedNST, a novel method for training distributed ASR models using private and unlabelled user data.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Deep Depth Completion from Extremely Sparse Data: A Survey
Depth completion aims at predicting dense pixel-wise depth from an extremely sparse map captured from a depth sensor, e. g., LiDARs.
A Mixed Quantization Network for Computationally Efficient Mobile Inverse Tone Mapping
Recovering a high dynamic range (HDR) image from a single low dynamic range (LDR) image, namely inverse tone mapping (ITM), is challenging due to the lack of information in over- and under-exposed regions.
Adversarial Attacks and Defense Methods for Power Quality Recognition
To this end, we first propose a signal-specific method and a universal signal-agnostic method to attack power systems using generated adversarial examples.
Bring Evanescent Representations to Life in Lifelong Class Incremental Learning
In Class Incremental Learning (CIL), a classification model is progressively trained at each incremental step on an evolving dataset of new classes, while at the same time, it is required to preserve knowledge of all the classes observed so far.
Feature Kernel Distillation
Trained Neural Networks (NNs) can be viewed as data-dependent kernel machines, with predictions determined by the inner product of last-layer representations across inputs, referred to as the feature kernel.
Task Guided Compositional Representation Learning for ZDA
To this end, we propose a method for task-guided ZDA (TG-ZDA) which employs multi-branch deep neural networks to learn feature representations exploiting their domain invariance and shareability properties.
Prototype Guided Federated Learning of Visual Feature Representations
Federated Learning (FL) is a framework which enables distributed model training using a large corpus of decentralized training data.
A New Neural Network Architecture Invariant to the Action of Symmetry Subgroups
We propose a computationally efficient $G$-invariant neural network that approximates functions invariant to the action of a given permutation subgroup $G \leq S_n$ of the symmetric group on input data.
Learning from Experience for Rapid Generation of Local Car Maneuvers
Being able to rapidly respond to the changing scenes and traffic situations by generating feasible local paths is of pivotal importance for car autonomy.
A Computationally Efficient Neural Network Invariant to the Action of Symmetry Subgroups
The key element of the proposed network architecture is a new $G$-invariant transformation module, which produces a $G$-invariant latent representation of the input data.
Fine-grained Optimization of Deep Neural Networks
In this work, we conjecture that if we can impose multiple constraints on weights of DNNs to upper bound the norms of the weights, and train the DNNs with these weights, then we can attain empirical generalization errors closer to the derived theoretical bounds, and improve accuracy of the DNNs.
Improving Head Pose Estimation with a Combined Loss and Bounding Box Margin Adjustment
We address a problem of estimating pose of a person's head from its RGB image.
Feature Quantization for Defending Against Distortion of Images
In this work, we address the problem of improving robustness of convolutional neural networks (CNNs) to image distortion.
Revisiting Single Image Depth Estimation: Toward Higher Resolution Maps with Accurate Object Boundaries
Experimental results show that these two improvements enable to attain higher accuracy than the current state-of-the-arts, which is given by finer resolution reconstruction, for example, with small objects and object boundaries.
Ranked #64 on
Monocular Depth Estimation
on NYU-Depth V2
(RMSE metric)
Exploiting the Potential of Standard Convolutional Autoencoders for Image Restoration by Evolutionary Search
Researchers have applied deep neural networks to image restoration tasks, in which they proposed various network architectures, loss functions, and training methods.
Deep Structured Energy-Based Image Inpainting
In this paper, we propose a structured image inpainting method employing an energy based model.
A vision based system for underwater docking
In the experiments, we first evaluate performance of the proposed detection module on UDID and its deformed variations.
HyperNetworks with statistical filtering for defending adversarial examples
This problem was addressed by employing several defense methods for detection and rejection of particular types of attacks.
Improving Robustness of Feature Representations to Image Deformations using Powered Convolution in CNNs
In this work, we address the problem of improvement of robustness of feature representations learned using convolutional neural networks (CNNs) to image deformation.
Linear Discriminant Generative Adversarial Networks
We develop a novel method for training of GANs for unsupervised and class conditional generation of images, called Linear Discriminant GAN (LD-GAN).
Information Potential Auto-Encoders
In order to estimate the entropy of the encoding variables and the mutual information, we propose a non-parametric method.
Truncating Wide Networks using Binary Tree Architectures
By employing the proposed architecture on a baseline wide network, we can construct and train a new network with same depth but considerably less number of parameters.
Optimization on Product Submanifolds of Convolution Kernels
The results show that geometric adaptive step size computation methods of G-SGD can improve training loss and convergence properties of CNNs.
Optimization on Submanifolds of Convolution Kernels in CNNs
Following our theoretical results, we propose a SGD algorithm with assurance of almost sure convergence of the methods to a solution at single minimum of classification loss of CNNs.
Encoding the Local Connectivity Patterns of fMRI for Cognitive State Classification
In this work, we propose a novel framework to encode the local connectivity patterns of brain, using Fisher Vectors (FV), Vector of Locally Aggregated Descriptors (VLAD) and Bag-of-Words (BoW) methods.
Hierarchical Multi-resolution Mesh Networks for Brain Decoding
We propose a new framework, called Hierarchical Multi-resolution Mesh Networks (HMMNs), which establishes a set of brain networks at multiple time resolutions of fMRI signal to represent the underlying cognitive process.
Modeling the Sequence of Brain Volumes by Local Mesh Models for Brain Decoding
The corresponding cognitive process, encoded in the brain, is then represented by these meshes each of which is estimated assuming a linear relationship among the voxel time series in a predefined locality.
Compositional Hierarchical Representation of Shape Manifolds for Classification of Non-Manifold Shapes
We represent the topological relationship between shape components using graphs, which are aggregated to construct a hierarchical graph structure for the shape vocabulary.
Design of Kernels in Convolutional Neural Networks for Image Classification
Despite the effectiveness of Convolutional Neural Networks (CNNs) for image classification, our understanding of the relationship between shape of convolution kernels and learned representations is limited.
Integrating Deep Features for Material Recognition
We propose a method for integration of features extracted using deep representations of Convolutional Neural Networks (CNNs) each of which is learned using a different image dataset of objects and materials for material recognition.
Machine Learning Methods for Attack Detection in the Smart Grid
The relationships between statistical and geometric properties of attack vectors employed in the attack scenarios and learning algorithms are analyzed to detect unobservable attacks using statistical learning methods.
A Hierarchical Approach for Joint Multi-view Object Pose Estimation and Categorization
We propose a joint object pose estimation and categorization approach which extracts information about object poses and categories from the object parts and compositions constructed at different layers of a hierarchical object representation algorithm, namely Learned Hierarchy of Parts (LHOP).
Fusion of Image Segmentation Algorithms using Consensus Clustering
A new segmentation fusion method is proposed that ensembles the output of several segmentation algorithms applied on a remotely sensed image.
Semi-supervised Segmentation Fusion of Multi-spectral and Aerial Images
A Semi-supervised Segmentation Fusion algorithm is proposed using consensus and distributed learning.
A Graph Theoretic Approach for Object Shape Representation in Compositional Hierarchies Using a Hybrid Generative-Descriptive Model
A graph theoretic approach is proposed for object shape representation in a hierarchical compositional architecture called Compositional Hierarchy of Parts (CHOP).
Discriminative Functional Connectivity Measures for Brain Decoding
The proposed method was tested on a recognition memory experiment, including data pertaining to encoding and retrieval of words belonging to ten different semantic categories.
Mesh Learning for Classifying Cognitive Processes
The arc weights of each mesh are estimated from the voxel intensity values by least squares method.
A New Fuzzy Stacked Generalization Technique and Analysis of its Performance
In this study, a new Stacked Generalization technique called Fuzzy Stacked Generalization (FSG) is proposed to minimize the difference between N -sample and large-sample classification error of the Nearest Neighbor classifier.
