Search Results for author:
Found 65 papers, 36 papers with code
What Looks Good with my Sofa: Multimodal Search Engine for Interior Design
In this paper, we propose a multi-modal search engine for interior design that combines visual and textual queries.
Speaker Diarization using Deep Recurrent Convolutional Neural Networks for Speaker Embeddings
In this paper we propose a new method of speaker diarization that employs a deep learning architecture to learn speaker embeddings.
Neural Comic Style Transfer: Case Study
The work by Gatys et al. [1] recently showed a neural style algorithm that can produce an image in the style of another image.
Adversarial Autoencoders for Compact Representations of 3D Point Clouds
Deep generative architectures provide a way to model not only images but also complex, 3-dimensional objects, such as point clouds.
Comixify: Transform video into a comics
In this paper, we propose a solution to transform a video into a comics.
Estimation of preterm birth markers with U-Net segmentation network
To achieve this goal, we propose to first use a deep neural network architecture for segmenting prenatal ultrasound images and then automatically extract two biophysical ultrasound markers, cervical length (CL) and anterior cervical angle (ACA), from the resulting images.
Hypernetwork approach to generating point clouds
The main idea of our HyperCloud method is to build a hyper network that returns weights of a particular neural network (target network) trained to map points from a uniform unit ball distribution into a 3D shape.
Understanding the robustness of deep neural network classifiers for breast cancer screening
Deep neural networks (DNNs) show promise in breast cancer screening, but their robustness to input perturbations must be better understood before they can be clinically implemented.
End-to-end Sinkhorn Autoencoder with Noise Generator
To address these shortcomings, we introduce a novel method dubbed end-to-end Sinkhorn Autoencoder, that leverages sinkhorn algorithm to explicitly align distribution of encoded real data examples and generated noise.
HyperFlow: Representing 3D Objects as Surfaces
To that end, we devise a generative model that uses a hypernetwork to return the weights of a Continuous Normalizing Flows (CNF) target network.
Spontaneous preterm birth prediction using convolutional neural networks
Based on the conducted results and model efficiency, we decided to extend U-Net by adding a parallel branch for classification task.
Representing Point Clouds with Generative Conditional Invertible Flow Networks
To exploit similarities between same-class objects and to improve model performance, we turn to weight sharing: networks that model densities of points belonging to objects in the same family share all parameters with the exception of a small, object-specific embedding vector.
BinPlay: A Binary Latent Autoencoder for Generative Replay Continual Learning
We introduce a binary latent space autoencoder architecture to rehearse training samples for the continual learning of neural networks.
Modeling 3D Surface Manifolds with a Locally Conditioned Atlas
This way, we can sample a mesh quad on that sphere and project it back onto the object's manifold.
HyperPocket: Generative Point Cloud Completion
In this work, we reformulate the problem of point cloud completion into an object hallucination task.
TrajeVAE: Controllable Human Motion Generation from Trajectories
The creation of plausible and controllable 3D human motion animations is a long-standing problem that requires a manual intervention of skilled artists.
Convolutional Neural Networks in Orthodontics: a review
Convolutional neural networks (CNNs) are used in many areas of computer vision, such as object tracking and recognition, security, military, and biomedical image analysis.
Zero Time Waste: Recycling Predictions in Early Exit Neural Networks
The problem of reducing processing time of large deep learning models is a fundamental challenge in many real-world applications.
Visual Probing: Cognitive Framework for Explaining Self-Supervised Image Representations
Motivated by this observation, we introduce a novel visual probing framework for explaining the self-supervised models by leveraging probing tasks employed previously in natural language processing.
Multiband VAE: Latent Space Alignment for Knowledge Consolidation in Continual Learning
We propose a new method for unsupervised generative continual learning through realignment of Variational Autoencoder's latent space.
FetalNet: Multi-task Deep Learning Framework for Fetal Ultrasound Biometric Measurements
The main goal in fetal ultrasound scan video analysis is to find proper standard planes to measure the fetal head, abdomen and femur.
HyperColor: A HyperNetwork Approach for Synthesizing Auto-colored 3D Models for Game Scenes Population
In such a case, we have to ``understand'' the object's composition and coloring scheme of each part.
On robustness of generative representations against catastrophic forgetting
Catastrophic forgetting of previously learned knowledge while learning new tasks is a widely observed limitation of contemporary neural networks.
Efficient GPU implementation of randomized SVD and its applications
In this work, we leverage efficient processing operations that can be run in parallel on modern Graphical Processing Units (GPUs), predominant computing architecture used e. g. in deep learning, to reduce the computational burden of computing matrix decompositions.
HyperCube: Implicit Field Representations of Voxelized 3D Models
Recently introduced implicit field representations offer an effective way of generating 3D object shapes.
Non-Gaussian Gaussian Processes for Few-Shot Regression
This makes the GP posterior locally non-Gaussian, therefore we name our method Non-Gaussian Gaussian Processes (NGGPs).
CoNeRF: Controllable Neural Radiance Fields
We extend neural 3D representations to allow for intuitive and interpretable user control beyond novel view rendering (i. e. camera control).
Logarithmic Continual Learning
Our approach leverages allocation of past data in a~set of generative models such that most of them do not require retraining after a~task.
POTHER: Patch-Voted Deep Learning-Based Chest X-ray Bias Analysis for COVID-19 Detection
We show that our proposed method is more robust than previous attempts to counter confounding factors such as ECG leads in chest X-rays that often influence model classification decisions.
Continual learning on 3D point clouds with random compressed rehearsal
By using rehearsal and reconstruction as regularization methods of the learning process, our approach achieves a significant decrease of catastrophic forgetting compared to the existing solutions on several most popular point cloud datasets considering two continual learning settings: when a task is known beforehand, and in the challenging scenario of when task information is unknown to the model.
BabyNet: Residual Transformer Module for Birth Weight Prediction on Fetal Ultrasound Video
Predicting fetal weight at birth is an important aspect of perinatal care, particularly in the context of antenatal management, which includes the planned timing and the mode of delivery.
Deep Learning Fetal Ultrasound Video Model Match Human Observers in Biometric Measurements
We found that automated fetal biometric measurements obtained by FUVAI were comparable to the measurements performed by experienced sonographers The observed differences in measurement values were within the range of inter- and intra-observer variability.
On Analyzing Generative and Denoising Capabilities of Diffusion-based Deep Generative Models
Their main strength comes from their unique setup in which a model (the backward diffusion process) is trained to reverse the forward diffusion process, which gradually adds noise to the input signal.
Continual Learning with Guarantees via Weight Interval Constraints
We introduce a new training paradigm that enforces interval constraints on neural network parameter space to control forgetting.
Progressive Latent Replay for efficient Generative Rehearsal
We introduce a new method for internal replay that modulates the frequency of rehearsal based on the depth of the network.
Selectively increasing the diversity of GAN-generated samples
Especially prone to mode collapse are conditional GANs, which tend to ignore the input noise vector and focus on the conditional information.
HyperSound: Generating Implicit Neural Representations of Audio Signals with Hypernetworks
Implicit neural representations (INRs) are a rapidly growing research field, which provides alternative ways to represent multimedia signals.
Emergency action termination for immediate reaction in hierarchical reinforcement learning
In this paper, we address this gap in the state-of-the-art approaches and propose a method in which the validity of higher-level actions (thus lower-level goals) is constantly verified at the higher level.
Hierarchical Reinforcement Learning
reinforcement-learning
+1
Towards Unsupervised Visual Reasoning: Do Off-The-Shelf Features Know How to Reason?
Recent advances in visual representation learning allowed to build an abundance of powerful off-the-shelf features that are ready-to-use for numerous downstream tasks.
Can gamification reduce the burden of self-reporting in mHealth applications? A feasibility study using machine learning from smartwatch data to estimate cognitive load
The effectiveness of digital treatments can be measured by requiring patients to self-report their state through applications, however, it can be overwhelming and causes disengagement.
Hypernetworks build Implicit Neural Representations of Sounds
Implicit Neural Representations (INRs) are nowadays used to represent multimedia signals across various real-life applications, including image super-resolution, image compression, or 3D rendering.
Active Visual Exploration Based on Attention-Map Entropy
Active visual exploration addresses the issue of limited sensor capabilities in real-world scenarios, where successive observations are actively chosen based on the environment.
Exploring Continual Learning of Diffusion Models
Diffusion models have achieved remarkable success in generating high-quality images thanks to their novel training procedures applied to unprecedented amounts of data.
BlendFields: Few-Shot Example-Driven Facial Modeling
Generating faithful visualizations of human faces requires capturing both coarse and fine-level details of the face geometry and appearance.
Towards More Realistic Membership Inference Attacks on Large Diffusion Models
In this paper, we examine whether it is possible to determine if a specific image was used in the training set, a problem known in the cybersecurity community and referred to as a membership inference attack.
Machine Learning methods for simulating particle response in the Zero Degree Calorimeter at the ALICE experiment, CERN
In particular, we examine the performance of variational autoencoders and generative adversarial networks, expanding the GAN architecture by an additional regularisation network and a simple, yet effective postprocessing step.
Adapt Your Teacher: Improving Knowledge Distillation for Exemplar-free Continual Learning
In this work, we investigate exemplar-free class incremental learning (CIL) with knowledge distillation (KD) as a regularization strategy, aiming to prevent forgetting.
Generalized Continual Category Discovery
However, these settings are not well aligned with real-life scenarios, where a learning agent has access to a vast amount of unlabeled data encompassing both novel (entirely unlabeled) classes and examples from known classes.
AR-TTA: A Simple Method for Real-World Continual Test-Time Adaptation
Test-time adaptation is a promising research direction that allows the source model to adapt itself to changes in data distribution without any supervision.
Looking through the past: better knowledge retention for generative replay in continual learning
We notice that in VAE-based generative replay, this could be attributed to the fact that the generated features are far from the original ones when mapped to the latent space.
Beyond Grids: Exploring Elastic Input Sampling for Vision Transformers
Vision transformers have excelled in various computer vision tasks but mostly rely on rigid input sampling using a fixed-size grid of patches.
CLIP-DIY: CLIP Dense Inference Yields Open-Vocabulary Semantic Segmentation For-Free
The emergence of CLIP has opened the way for open-world image perception.
Bayesian Flow Networks in Continual Learning
Bayesian Flow Networks (BFNs) has been recently proposed as one of the most promising direction to universal generative modelling, having ability to learn any of the data type.
TabAttention: Learning Attention Conditionally on Tabular Data
In this paper, we introduce TabAttention, a novel module that enhances the performance of Convolutional Neural Networks (CNNs) with an attention mechanism that is trained conditionally on tabular data.
On consequences of finetuning on data with highly discriminative features
In the era of transfer learning, training neural networks from scratch is becoming obsolete.
Revisiting Supervision for Continual Representation Learning
In the field of continual learning, models are designed to learn tasks one after the other.
CLIP-DINOiser: Teaching CLIP a few DINO tricks for open-vocabulary semantic segmentation
We propose to locally improve dense MaskCLIP features, which are computed with a simple modification of CLIP's last pooling layer, by integrating localization priors extracted from self-supervised features.
Adapt & Align: Continual Learning with Generative Models Latent Space Alignment
In this work, we introduce Adapt & Align, a method for continual learning of neural networks by aligning latent representations in generative models.
Infinite dSprites for Disentangled Continual Learning: Separating Memory Edits from Generalization
In a simple setting with direct supervision on the generative factors, we show how learning class-agnostic transformations offers a way to circumvent catastrophic forgetting and improve classification accuracy over time.
MISS: Multiclass Interpretable Scoring Systems
In this work, we present a novel, machine-learning approach for constructing Multiclass Interpretable Scoring Systems (MISS) - a fully data-driven methodology for generating single, sparse, and user-friendly scoring systems for multiclass classification problems.
Divide and not forget: Ensemble of selectively trained experts in Continual Learning
Class-incremental learning is becoming more popular as it helps models widen their applicability while not forgetting what they already know.
Overestimation, Overfitting, and Plasticity in Actor-Critic: the Bitter Lesson of Reinforcement Learning
We tested these agents across 14 diverse tasks from 2 simulation benchmarks.
GUIDE: Guidance-based Incremental Learning with Diffusion Models
We introduce GUIDE, a novel continual learning approach that directs diffusion models to rehearse samples at risk of being forgotten.
Accelerated Inference and Reduced Forgetting: The Dual Benefits of Early-Exit Networks in Continual Learning
We assess the accuracy and computational cost of various continual learning techniques enhanced with early-exits and TLC across standard class-incremental learning benchmarks such as 10 split CIFAR100 and ImageNetSubset and show that TLC can achieve the accuracy of the standard methods using less than 70\% of their computations.
AdaGlimpse: Active Visual Exploration with Arbitrary Glimpse Position and Scale
Active Visual Exploration (AVE) is a task that involves dynamically selecting observations (glimpses), which is critical to facilitate comprehension and navigation within an environment.
