Stochastic Frequency Masking to Improve Super-Resolution and Denoising Networks

Chattez avec Graph Search

Posez n’importe quelle question sur les cours, conférences, exercices, recherches, actualités, etc. de l’EPFL ou essayez les exemples de questions ci-dessous.

AVERTISSEMENT : Le chatbot Graph n'est pas programmé pour fournir des réponses explicites ou catégoriques à vos questions. Il transforme plutôt vos questions en demandes API qui sont distribuées aux différents services informatiques officiellement administrés par l'EPFL. Son but est uniquement de collecter et de recommander des références pertinentes à des contenus que vous pouvez explorer pour vous aider à répondre à vos questions.

While momentum-based accelerated variants of stochastic gradient descent (SGD) are widely used when training machine learning models, there is little theoretical understanding on the generalization error of such methods. In this work, we first show that th ...

The learning process depends on the nature of the learning environment, particularly in the case of open-ended learning environments, where the learning process is considered to be non-linear. In this paper, we report on the findings of employing a multimo ...

State-of-the-art 2D image compression schemes rely on the power of convolutional neural networks (CNNs). Although CNNs offer promising perspectives for 2D image compression, extending such models to omnidirectional images is not straightforward. First, omn ...

In this thesis, we study two closely related directions: robustness and generalization in modern deep learning. Deep learning models based on empirical risk minimization are known to be often non-robust to small, worst-case perturbations known as adversari ...

When enough annotated training data is available, supervised deep-learning. algorithms excel at estimating human body pose and shape using a single camera. The effects of too little such data being available can be mitigated by using other information sour ...

Advances in computing have enabled widespread access to pose estimation, creating new sources of data streams. Unlike mock set-ups for data collection, tapping into these data streams through on-device active learning allows us to directly sample from the ...

Water is a crucial resource for all forms of life, yet it is becoming increasingly scarce. A significant portion of water loss in urban and industrial areas is attributed to leaks. Addressing this issue is critical for enhancing efficiency, sustainability, ...

Noise is an intrinsic part of any sensor and is present, in various degrees, in any content that has been captured in real life environments. In imaging applications, several pre- and post-processing solutions have been proposed to cope with noise in captu ...

In this research, a generalized machine learning (ML) framework is proposed to estimate the fatigue life of epoxy polymers and additively manufactured AlSi10Mg alloy materials, leveraging their failure surface void characteristics. An extreme gradient boos ...

Machine learning models have been shown to leak sensitive information about their training datasets. Models are increasingly deployed on devices, raising concerns that white-box access to the model parameters increases the attack surface compared to black- ...

Image super-resolution is a classic ill-posed computer vision and image processing problem, addressing the question of how to reconstruct a high-resolution image from its low-resolution counterpart. Current state-of-the-art methods have improved the perfor ...

Optical microscopy, an invaluable tool in biology and medicine to observe and quantify cellular function, organ development, or disease mechanisms, requires constant trade-offs between spatial, temporal, and spectral resolution, invasiveness, acquisition t ...

Informative sample selection in an active learning (AL) setting helps a machine learning system attain optimum performance with minimum labeled samples, thus reducing annotation costs and boosting performance of computer-aided diagnosis systems in the pres ...

Computer simulations are often used as support material for science education, as they can engage students through inquiry-based learning, promote their active interaction in the experimentation phase, and help them visualize abstract concepts. For instanc ...

Orchestrating technology-enhanced learning is a difficult task, especially in demanding pedagogical approaches like inquiry-based learning (IBL). To foster effective teacher adoption, both the complexity of designing IBL activities and the uncertainty abou ...

Correspondence pruning aims to correctly remove false matches (outliers) from an initial set of putative correspondences. The pruning process is challenging since putative matches are typically extremely unbalanced, largely dominated by outliers, and the r ...

Auditory perception is an essential part of a robotic system in Human-Robot Interaction (HRI), and creating an artificial auditory perception system that is on par with human has been a long-standing goal for researchers. In fact, this is a challenging res ...

Deep learning has achieved remarkable success in various challenging tasks such as generating images from natural language or engaging in lengthy conversations with humans. The success in practice stems from the ability to successfully train massive neural ...

Image restoration reconstructs, as faithfully as possible, an original image from a potentially degraded version of it. Image degradations can be of various types, for instance haze, unwanted reflections, optical or spectral aberrations, or other physicall ...

Most self-supervised methods for representation learning leverage a cross-view consistency objective i.e. they maximize the representation similarity of a given image's augmented views. Recent work NNCLR goes beyond the cross- view paradigm and uses positi ...

Stochastic Frequency Masking to Improve Super-Resolution and Denoising Networks

Chattez avec Graph Search

On the Generalization of Stochastic Gradient Descent with Momentum

Temporal Pathways to Learning: How Learning Emerges in an Open-ended Collaborative Activity

OSLO: On-the-Sphere Learning for Omnidirectional Images and Its Application to 360-Degree Image Compression

Understanding generalization and robustness in modern deep learning

Using Motion Cues to Supervise Single-Frame Body Pose and Shape Estimation in Low Data Regimes

VL4Pose: Active Learning Through Out-Of-Distribution Detection For Pose Estimation

A two-phase approach for leak detection and localization in water distribution systems using wavelet decomposition and machine learning

On combining denoising with learning-based image decoding

A generalized machine learning framework to estimate fatigue life across materials with minimal data

Investigating the Effect of Misalignment on Membership Privacy in the White-box Setting

Context-Aware Image Super-Resolution Using Deep Neural Networks

Weakly Supervised Deep Learning Methods for Biomicroscopy

GANDALF: Graph-based transformer and Data Augmentation Active Learning Framework with interpretable features for multi-label chest Xray classification

Teacher-Mediated and Student-Led Interaction with a Physics Simulation: Effects on the Learning Experience

ADA for IBL: Lessons Learned in Aligning Learning Design and Analytics for Inquiry-Based Learning Orchestration

Progressive Correspondence Pruning by Consensus Learning

Deep Learning Approaches for Auditory Perception in Robotics

A Theory of Finite-Width Neural Networks: Generalization, Scaling Laws, and the Loss Landscape

Deep Image Restoration: Between Data Fidelity and Learned Priors

Adaptive Similarity Bootstrapping for Self-Distillation based Representation Learning