DISK: learning local features with policy gradient

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

Facial paralysis is a highly burdening condition, resulting in a patient's inability to move his musculature on one or both sides of the mouth. The restoration of facial movement is crucial for enhancing the overall patients' quality of life. The use of DE ...

We propose a test -time adaptation for 6D object pose tracking that learns to adapt a pre -trained model to track the 6D pose of novel objects. We consider the problem of 6D object pose tracking as a 3D keypoint detection and matching task and present a mo ...

Now is an exciting time for the domain of Earth observation (EO), with a multitude of diverse sensors looking at the planet from satellites, airplanes or drones. The volume of imagery acquired is massive, and hold great potential for a variety of applicati ...

Photometric stereo, a computer vision technique for estimating the 3D shape of objects through images captured under varying illumination conditions, has been a topic of research for nearly four decades. In its general formulation, photometric stereo is an ...

As one of the major threats to women's health worldwide, breast cancer requires early diagnosis and accurate classification, since they are key to optimizing therapeutic interventions and ensuring precise prognosis. Recently, deep learning has demonstrated ...

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 ...

Deploying energy-efficient deep neural networks on energy-constrained edge devices is an important research topic in both machine learning and circuit design communities. Both artificial neural networks (ANNs) and spiking neural networks (SNNs) have been p ...

Blood pressure (BP) is a crucial indicator of cardiovascular health. Hypertension is a common life-threatening condition and a key factor of cardiovascular diseases (CVDs). Identifying abnormal BP fluctuations can allow for early detection and management o ...

We present a reinforcement learning framework for constructing assemblies composed of rigid parts, which are commonly seen in many historical masonry buildings and bridges. Traditional construction methods for such structures often depend on dense scaffold ...

State-of-the-art object detection and segmentation methods for microscopy images rely on supervised machine learning, which requires laborious manual annotation of training data. Here we present a self-supervised method based on time arrow prediction pre-t ...

Current machine learning models for vision are often highly specialized and limited to a single modality and task. In contrast, recent large language models exhibit a wide range of capabilities, hinting at a possibility for similarly versatile models in co ...

Self-supervised learning (SSL) is a machine learning approach where the data itself provides supervision, eliminating the need for external labels. The model is forced to learn about the data's inherent structure or context by solving a pretext task. With ...

High-dimensional data must be highly structured to be learnable. Although the compositional and hierarchical nature of data is often put forward to explain learnability, quantitative measurements establishing these properties are scarce. Likewise, accessin ...

Sign Language conveys information through multiple channels composed of manual (handshape, hand movement) and non-manual (facial expression, mouthing, body posture) components. Sign language assessment involves giving granular feedback to a learner, in ter ...

The way biological brains carry out advanced yet extremely energy efficient signal processing remains both fascinating and unintelligible. It is known however that at least some areas of the brain perform fast and low-cost processing relying only on a smal ...

Differences in acquisition protocols or hardware result in measurable changes in image characteristics. These differences affect distributional properties and can also affect the spatial and temporal characteristics of the images. Likewise, the distributio ...

Many empirical studies have provided evidence for the emergence of algorithmic mechanisms (abilities) in the learning of language models, that lead to qualitative improvements in the model capabilities. Yet, a theoretical characterization of how such mecha ...

In this paper, we propose and compare personalized models for Productive Engagement (PE) recognition. PE is defined as the level of engagement that maximizes learning. Previously, in the context of robot-mediated collaborative learning, a framework of prod ...

Supervised and unsupervised kernel-based algorithms widely used in the physical sciences depend upon the notion of similarity. Their reliance on pre-defined distance metrics-e.g. the Euclidean or Manhattan distance-are problematic especially when used in c ...

This paper investigates the fundamental regression task of learning k neurons (a.k.a. teachers) from Gaussian input, using two-layer ReLU neural networks with width m (a.k.a. students) and m, k = O(1), trained via gradient descent under proper initializati ...

DISK: learning local features with policy gradient

Chat with Graph Search

DEMO: Dielectric elastomer actuators (DEAs) for the restoration of facial movements

Test-time adaptation for 6D pose tracking

Interact with Earth Observation Images using AI: Transparent Methods and Evaluation for Visual Question Answering

Aggregating Spatial and Photometric Context for Photometric Stereo

Mspo: a Machine Learning Hyperparameter Optimization Method for Enhanced Breast Cancer Image Classification

Understanding generalization and robustness in modern deep learning

Eflop: a Sparsity-aware Metric for Evaluating Computational Cost in Spiking and Non-spiking Neural Networks

Data-driven approaches for non-invasive cuffless blood pressure monitoring

Learning to Assemble with Alternative Plans

Self-supervised Dense Representation Learning for Live-Cell Microscopy with Time Arrow Prediction

4M: Massively Multimodal Masked Modeling

A Closer Look at Benchmarking Self-supervised Pre-training with Image Classification

Probing the latent hierarchical structure of data via diffusion models

Posterior-Based Analysis of Spatio-Temporal Features for Sign Language Assessment

Supervised learning and inference of spiking neural networks with temporal coding

Domain shift, domain adaptation, and generalization: A focus on MRI

A phase transition between positional and semantic learning in a solvable model of dot-product attention

Personalized Productive Engagement Recognition in Robot-Mediated Collaborative Learning

Metric learning for kernel ridge regression: assessment of molecular similarity

How Gradient Descent Balances Features: A Dynamical Analysis For Two-Layer Neural Networks