Search Results for author:
Found 63 papers, 19 papers with code
Learning Video Representations by Transforming Time
Our representations can be learned from data without human annotation and provide a substantial boost to the training of neural networks on small labeled data sets for tasks such as action recognition, which require to accurately distinguish the motion of objects.
Masked and Shuffled Blind Spot Denoising for Real-World Images
We introduce a novel approach to single image denoising based on the Blind Spot Denoising principle, which we call MAsked and SHuffled Blind Spot Denoising (MASH).
Two Tricks to Improve Unsupervised Segmentation Learning
We present two practical improvement techniques for unsupervised segmentation learning.
Enabling Visual Composition and Animation in Unsupervised Video Generation
We call our model CAGE for visual Composition and Animation for video GEneration.
A Quantitative Evaluation of Score Distillation Sampling Based Text-to-3D
However, the SDS method is also the source of several artifacts, such as the Janus problem, the misalignment between the text prompt and the generated 3D model, and 3D model inaccuracies.
Multi-View Unsupervised Image Generation with Cross Attention Guidance
The growing interest in novel view synthesis, driven by Neural Radiance Field (NeRF) models, is hindered by scalability issues due to their reliance on precisely annotated multi-view images.
SemiGPC: Distribution-Aware Label Refinement for Imbalanced Semi-Supervised Learning Using Gaussian Processes
We show that SemiGPC improves performance when paired with different Semi-Supervised methods such as FixMatch, ReMixMatch, SimMatch and FreeMatch and different pre-training strategies including MSN and Dino.
Denoising and Selecting Pseudo-Heatmaps for Semi-Supervised Human Pose Estimation
First, we introduce a denoising scheme to generate reliable pseudo-heatmaps as targets for learning from unlabeled data.
Sparse 3D Reconstruction via Object-Centric Ray Sampling
This sampling scheme relies on the mesh representation to ensure also that samples are well-distributed along its normals.
Benchmarking Zero-Shot Recognition with Vision-Language Models: Challenges on Granularity and Specificity
This paper introduces innovative benchmarks to evaluate Vision-Language Models (VLMs) in real-world zero-shot recognition tasks, focusing on the granularity and specificity of prompting text.
Fast light-field 3D microscopy with out-of-distribution detection and adaptation through Conditional Normalizing Flows
Real-time 3D fluorescence microscopy is crucial for the spatiotemporal analysis of live organisms, such as neural activity monitoring.
ScaleDet: A Scalable Multi-Dataset Object Detector
Our results show that ScaleDet achieves compelling strong model performance with an mAP of 50. 7 on LVIS, 58. 8 on COCO, 46. 8 on Objects365, 76. 2 on OpenImages, and 71. 8 on ODinW, surpassing state-of-the-art detectors with the same backbone.
Ranked #1 on
Object Detection
on OpenImages-v6
(using extra training data)
Learn the Force We Can: Enabling Sparse Motion Control in Multi-Object Video Generation
We propose a novel unsupervised method to autoregressively generate videos from a single frame and a sparse motion input.
A Meta-Learning Approach to Predicting Performance and Data Requirements
The PPL improves the performance estimation on average by 37% across 16 classification and 33% across 10 detection datasets, compared to the power law.
Spatio-Temporal Crop Aggregation for Video Representation Learning
We propose Spatio-temporal Crop Aggregation for video representation LEarning (SCALE), a novel method that enjoys high scalability at both training and inference time.
Efficient Video Prediction via Sparsely Conditioned Flow Matching
We call our model Random frame conditioned flow Integration for VidEo pRediction, or, in short, RIVER.
MOVE: Unsupervised Movable Object Segmentation and Detection
We introduce MOVE, a novel method to segment objects without any form of supervision.
Ranked #2 on
Unsupervised Saliency Detection
on DUTS
U-Sleep's resilience to AASM guidelines
Specifically, we demonstrate that U-Sleep, a state-of-the-art sleep scoring algorithm, can be strong enough to solve the scoring task even using clinically non-recommended or non-conventional derivations, and with no need to exploit information about the chronological age of the subjects.
Semi-supervised Vision Transformers at Scale
We study semi-supervised learning (SSL) for vision transformers (ViT), an under-explored topic despite the wide adoption of the ViT architectures to different tasks.
Towards Sleep Scoring Generalization Through Self-Supervised Meta-Learning
In this work we introduce a novel meta-learning method for sleep scoring based on self-supervised learning.
Multi-Scored Sleep Databases: How to Exploit the Multiple-Labels in Automated Sleep Scoring
Results: The performance of the models improves on all the databases when we train the models with our LSSC.
Controllable Video Generation through Global and Local Motion Dynamics
We present GLASS, a method for Global and Local Action-driven Sequence Synthesis.
Representation Learning by Detecting Incorrect Location Embeddings
We represent object parts with image tokens and train a ViT to detect which token has been combined with an incorrect positional embedding.
Ranked #91 on
Image Classification
on ObjectNet
(using extra training data)
Learning to Deblur and Rotate Motion-Blurred Faces
Our method handles the complexity of face blur by implicitly learning the geometry and motion of faces through the joint training on three large datasets: FFHQ and 300VW, which are publicly available, and a new Bern Multi-View Face Dataset (BMFD) that we built.
DeepSleepNet-Lite: A Simplified Automatic Sleep Stage Scoring Model with Uncertainty Estimates
We exploit, for the first time in sleep scoring, the Monte Carlo dropout technique to enhance the performance of the architecture and to also detect the uncertain instances.
Generative Adversarial Learning via Kernel Density Discrimination
We show a boost in the quality of generated samples with respect to FID from 10% to 40% compared to the baseline.
KOALA: A Kalman Optimization Algorithm with Loss Adaptivity
Moreover, we show that the Kalman Filter dynamical model for the evolution of the unknown parameters can be used to capture the gradient dynamics of advanced methods such as Momentum and Adam.
A Unified Generative Adversarial Network Training via Self-Labeling and Self-Attention
However, because the classifier might still make mistakes, especially at the beginning of the training, we also refine the labels through self-attention, by using the labeling of real data samples only when the classifier outputs a high classification probability score.
Optical Flow Dataset Synthesis from Unpaired Images
In the case of synthetic data, the ground truth provides an exact and explicit description of what optical flow to assign to a given scene.
ISD: Self-Supervised Learning by Iterative Similarity Distillation
Hence, we introduce a self supervised learning algorithm where we use a soft similarity for the negative images rather than a binary distinction between positive and negative pairs.
Self-Supervised Multi-View Synchronization Learning for 3D Pose Estimation
Current state-of-the-art methods cast monocular 3D human pose estimation as a learning problem by training neural networks on large data sets of images and corresponding skeleton poses.
Boosting Generalization in Bio-Signal Classification by Learning the Phase-Amplitude Coupling
Various hand-crafted features representations of bio-signals rely primarily on the amplitude or power of the signal in specific frequency bands.
Video Representation Learning by Recognizing Temporal Transformations
Our representations can be learned from data without human annotation and provide a substantial boost to the training of neural networks on small labeled data sets for tasks such as action recognition, which require to accurately distinguish the motion of objects.
Learning to Model and Calibrate Optics via a Differentiable Wave Optics Simulator
We present a novel learning-based method to build a differentiable computational model of a real fluorescence microscope.
Steering Self-Supervised Feature Learning Beyond Local Pixel Statistics
Based on this criterion, we introduce a novel image transformation that we call limited context inpainting (LCI).
Learning to Reconstruct Confocal Microscopy Stacks from Single Light Field Images
To train our network, we built a data set of 362 light field images of mouse brain blood vessels and the corresponding aligned set of 3D confocal scans, which we use as ground truth.
Unsupervised Generative 3D Shape Learning from Natural Images
In this paper we present, to the best of our knowledge, the first method to learn a generative model of 3D shapes from natural images in a fully unsupervised way.
Learning to Have an Ear for Face Super-Resolution
To combine the aural and visual modalities, we propose a method to first build the latent representations of a face from the lone audio track and then from the lone low-resolution image.
On Stabilizing Generative Adversarial Training with Noise
We notice that the distributions of real and generated data should match even when they undergo the same filtering.
Emergence of Object Segmentation in Perturbed Generative Models
To force the generator to learn a representation where the foreground layer corresponds to an object, we perturb the output of the generative model by introducing a random shift of both the foreground image and mask relative to the background.
Smart, Deep Copy-Paste
In this work, we propose a novel system for smart copy-paste, enabling the synthesis of high-quality results given a masked source image content and a target image context as input.
Learning to Take Directions One Step at a Time
Because items in an image can be animated in arbitrarily many different ways, we introduce as control signal a sequence of motion strokes.
Unsupervised 3D Shape Learning from Image Collections in the Wild
To achieve realism, the generative model is trained adversarially against a discriminator that tries to distinguish between the output of the renderer and real images from the given data set.
Deep Bilevel Learning
Our approach is based on the principles of cross-validation, where a validation set is used to limit the model overfitting.
Understanding Degeneracies and Ambiguities in Attribute Transfer
We study the problem of building models that can transfer selected attributes from one image to another without affecting the other attributes.
Normalized Blind Deconvolution
We introduce a family of novel approaches to single-image blind deconvolution, ie , the problem of recovering a sharp image and a blur kernel from a single blurry input.
Self-Supervised Feature Learning by Learning to Spot Artifacts
To generate images with artifacts, we pre-train a high-capacity autoencoder and then we use a damage and repair strategy: First, we freeze the autoencoder and damage the output of the encoder by randomly dropping its entries.
Boosting Self-Supervised Learning via Knowledge Transfer
We use this framework to design a novel self-supervised task, which achieves state-of-the-art performance on the common benchmarks in PASCAL VOC 2007, ILSVRC12 and Places by a significant margin.
FaceShop: Deep Sketch-based Face Image Editing
We present a novel system for sketch-based face image editing, enabling users to edit images intuitively by sketching a few strokes on a region of interest.
Learning to Extract a Video Sequence from a Single Motion-Blurred Image
We present a method to extract a video sequence from a single motion-blurred image.
Motion deblurring of faces
Notwithstanding, a much less standing mode of variation is motion deblurring, which however presents substantial challenges in face analysis.
Disentangling Factors of Variation by Mixing Them
We learn our representation without any labeling or knowledge of the data domain, using an autoencoder architecture with two novel training objectives: first, we propose an invariance objective to encourage that encoding of each attribute, and decoding of each chunk, are invariant to changes in other attributes and chunks, respectively; second, we include a classification objective, which ensures that each chunk corresponds to a consistently discernible attribute in the represented image, hence avoiding degenerate feature mappings where some chunks are completely ignored.
Challenges in Disentangling Independent Factors of Variation
Such models could be used to encode features that can efficiently be used for classification and to transfer attributes between different images in image synthesis.
Deep Mean-Shift Priors for Image Restoration
We show that the gradient of our prior corresponds to the mean-shift vector on the natural image distribution.
Ranked #77 on
Image Super-Resolution
on Set14 - 4x upscaling
Reflection Separation and Deblurring of Plenoptic Images
In this paper, we address the problem of reflection removal and deblurring from a single image captured by a plenoptic camera.
Representation Learning by Learning to Count
In this paper, we use two image transformations in the context of counting: scaling and tiling.
Noise-Blind Image Deblurring
We present a novel approach to noise-blind deblurring, the problem of deblurring an image with known blur, but unknown noise level.
Motion Deblurring in the Wild
The task of image deblurring is a very ill-posed problem as both the image and the blur are unknown.
Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles
By following the principles of self-supervision, we build a convolutional neural network (CNN) that can be trained to solve Jigsaw puzzles as a pretext task, which requires no manual labeling, and then later repurposed to solve object classification and detection.
A Clearer Picture of Blind Deconvolution
Our analysis reveals the very reason why an algorithm based on total variation works.
Motion Deblurring for Plenoptic Images
We address for the first time the issue of motion blur in light field images captured from plenoptic cameras.
Total Variation Blind Deconvolution: The Devil is in the Details
This then results in a procedure that eludes the no-blur solution, despite it being a global minimum of the original energy.
A New Perspective on Uncalibrated Photometric Stereo
We show that in the perspective projection case the solution is unique.
