333 citations · 694 across the 29 of their papers we have counts for
33 papers
LILAC: Layer-Wise Independent LoRAs and Cascaded Conditioning for Multi-Concept Customization of Diffusion Models
Marian Lupascu, Sebastian Ripa, Mihai Trascau +2
Personalizing text-to-image diffusion models to render several specific subjects in a coherent image remains challenging: the model must preserve each subject's identity while keep…
LaDe: Unified Multi-Layered Graphic Media Generation and Decomposition
Vlad-Constantin Lungu-Stan, Ionut Mironica, Mariana-Iuliana Georgescu
Media design layer generation enables the creation of fully editable, layered design documents such as posters, flyers, and logos using only natural language prompts. Existing meth…
X-Aligner: Composed Visual Retrieval without the Bells and Whistles
Yuqian Zheng, Mariana-Iuliana Georgescu
Composed Video Retrieval (CoVR) facilitates video retrieval by combining visual and textual queries. However, existing CoVR frameworks typically fuse multimodal inputs in a single…
Road Obstacle Video Segmentation
Shyam Nandan Rai, Shyamgopal Karthik, Mariana-Iuliana Georgescu +3
With the growing deployment of autonomous driving agents, the detection and segmentation of road obstacles have become critical to ensure safe autonomous navigation. However, exist…
Q-Former Autoencoder: A Modern Framework for Medical Anomaly Detection
Francesco Dalmonte, Emirhan Bayar, Emre Akbas +1
Anomaly detection in medical images is an important yet challenging task due to the diversity of possible anomalies and the practical impossibility of collecting comprehensively an…
Subspace-Boosted Model Merging
Ronald Skorobogat, Karsten Roth, Mariana-Iuliana Georgescu
Model merging enables the combination of multiple specialized expert models into a single model capable of performing multiple tasks. However, the benefits of merging an increasing…
FLAIR: VLM with Fine-grained Language-informed Image Representations
Rui Xiao, Sanghwan Kim, Mariana-Iuliana Georgescu +2
CLIP has shown impressive results in aligning images and texts at scale. However, its ability to capture detailed visual features remains limited because CLIP matches images and te…
COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training
Sanghwan Kim, Rui Xiao, Mariana-Iuliana Georgescu +2
Vision-Language Models (VLMs) trained with contrastive loss have achieved significant advancements in various vision and language tasks. However, the global nature of the contrasti…
EgoCVR: An Egocentric Benchmark for Fine-Grained Composed Video Retrieval
Thomas Hummel, Shyamgopal Karthik, Mariana-Iuliana Georgescu +1
In Composed Video Retrieval, a video and a textual description which modifies the video content are provided as inputs to the model. The aim is to retrieve the relevant video with…
Weight Copy and Low-Rank Adaptation for Few-Shot Distillation of Vision Transformers
Diana-Nicoleta Grigore, Mariana-Iuliana Georgescu, Jon Alvarez Justo +3
Few-shot knowledge distillation recently emerged as a viable approach to harness the knowledge of large-scale pre-trained models, using limited data and computational resources. In…
Semantic Segmentation in Satellite Hyperspectral Imagery by Deep Learning
Jon Alvarez Justo, Alexandru Ghita, Daniel Kovac +5
Satellites are increasingly adopting on-board AI to optimize operations and increase autonomy through in-orbit inference. The use of Deep Learning (DL) models for segmentation in h…
Learning Using Generated Privileged Information by Text-to-Image Diffusion Models
Rafael-Edy Menadil, Mariana-Iuliana Georgescu, Radu Tudor Ionescu
Learning Using Privileged Information is a particular type of knowledge distillation where the teacher model benefits from an additional data representation during training, called…
Masked Autoencoders for Unsupervised Anomaly Detection in Medical Images
Mariana-Iuliana Georgescu
Pathological anomalies exhibit diverse appearances in medical imaging, making it difficult to collect and annotate a representative amount of data required to train deep learning m…
Audiovisual Masked Autoencoders
Mariana-Iuliana Georgescu, Eduardo Fonseca, Radu Tudor Ionescu +3
Can we leverage the audiovisual information already present in video to improve self-supervised representation learning? To answer this question, we study various pretraining archi…
Diversity-Promoting Ensemble for Medical Image Segmentation
Mariana-Iuliana Georgescu, Radu Tudor Ionescu, Andreea-Iuliana Miron
Medical image segmentation is an actively studied task in medical imaging, where the precision of the annotations is of utter importance towards accurate diagnosis and treatment. I…
SSMTL++: Revisiting Self-Supervised Multi-Task Learning for Video Anomaly Detection
Antonio Barbalau, Radu Tudor Ionescu, Mariana-Iuliana Georgescu +6
A self-supervised multi-task learning (SSMTL) framework for video anomaly detection was recently introduced in literature. Due to its highly accurate results, the method attracted…
Multimodal Multi-Head Convolutional Attention with Various Kernel Sizes for Medical Image Super-Resolution
Mariana-Iuliana Georgescu, Radu Tudor Ionescu, Andreea-Iuliana Miron +4
Super-resolving medical images can help physicians in providing more accurate diagnostics. In many situations, computed tomography (CT) or magnetic resonance imaging (MRI) techniqu…
Feature-level augmentation to improve robustness of deep neural networks to affine transformations
Adrian Sandru, Mariana-Iuliana Georgescu, Radu Tudor Ionescu
Recent studies revealed that convolutional neural networks do not generalize well to small image transformations, e.g. rotations by a few degrees or translations of a few pixels. T…
Teacher-Student Training and Triplet Loss to Reduce the Effect of Drastic Face Occlusion
Mariana-Iuliana Georgescu, Georgian Duta, Radu Tudor Ionescu
We study a series of recognition tasks in two realistic scenarios requiring the analysis of faces under strong occlusion. On the one hand, we aim to recognize facial expressions of…
UBnormal: New Benchmark for Supervised Open-Set Video Anomaly Detection
Andra Acsintoae, Andrei Florescu, Mariana-Iuliana Georgescu +5
Detecting abnormal events in video is commonly framed as a one-class classification task, where training videos contain only normal events, while test videos encompass both normal…
A realistic approach to generate masked faces applied on two novel masked face recognition data sets
Tudor Mare, Georgian Duta, Mariana-Iuliana Georgescu +4
The COVID-19 pandemic raises the problem of adapting face recognition systems to the new reality, where people may wear surgical masks to cover their noses and mouths. Traditional…
CyTran: A Cycle-Consistent Transformer with Multi-Level Consistency for Non-Contrast to Contrast CT Translation
Nicolae-Catalin Ristea, Andreea-Iuliana Miron, Olivian Savencu +4
We propose a novel approach to translate unpaired contrast computed tomography (CT) scans to non-contrast CT scans and the other way around. Solving this task has two important app…
Contextual Convolutional Neural Networks
Ionut Cosmin Duta, Mariana Iuliana Georgescu, Radu Tudor Ionescu
We propose contextual convolution (CoConv) for visual recognition. CoConv is a direct replacement of the standard convolution, which is the core component of convolutional neural n…
SuPEr-SAM: Using the Supervision Signal from a Pose Estimator to Train a Spatial Attention Module for Personal Protective Equipment Recognition
Adrian Sandru, Georgian-Emilian Duta, Mariana-Iuliana Georgescu +1
We propose a deep learning method to automatically detect personal protective equipment (PPE), such as helmets, surgical masks, reflective vests, boots and so on, in images of peop…