TTT++: When Does Self-Supervised Test-Time Training Fail or Thrive?

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.

In this work, we tackle the task of estimating the 6D pose of an object from point cloud data. While recent learning-based approaches have shown remarkable success on synthetic datasets, we have observed them to fail in the presence of real-world data. We ...

Interactions are ubiquitous in our world, spanning from social interactions between human individuals to physical interactions between robots and objects to mechanistic interactions among different components of an intelligent system. Despite their prevale ...

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 ...

Self-supervised learning (SSL) models use only the intrinsic structure of a given signal, independent of its acoustic domain, to extract essential information from the input to an embedding space. This implies that the utility of such representations is no ...

Computing servers have played a key role in developing and processing emerging compute-intensive applications in recent years. Consolidating multiple virtual machines (VMs) inside one server to run various applications introduces severe competence for limi ...

The success of self-supervised learning in computer vision and natural language processing has motivated pretraining methods on tabular data. However, most existing tabular self-supervised learning models fail to leverage information across multiple data t ...

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 ...

Incomplete labels are common in multi-task learning for biomedical applications due to several practical difficulties, e.g., expensive annotation efforts by experts, limit of data collection, different sources of data. A naive approach to enable joint lear ...

This dataset contains images (TIFF image data) of brain juvenile rats Wistar Han (P14) scanned immunostained slides by using an automated slide scanner (Olympus, VS120-L100, GER) equipped with a UPLSAPO 20x/0.75 air objective (Olympus, GER) and a Pike F5 ...

Superresolution T2-weighted fetal-brain magnetic-resonance imaging (FBMRI) traditionally relies on the availability of several orthogonal low-resolution series of 2-dimensional thick slices (volumes). In practice, only a few low-resolution volumes are acqu ...

Background and Objective: Cough audio signal classification is a potentially useful tool in screening for respiratory disorders, such as COVID-19. Since it is dangerous to collect data from patients with contagious diseases, many research teams have turned ...

The field of biometrics, and especially face recognition, has seen a wide-spread adoption the last few years, from access control on personal devices such as phones and laptops, to automated border controls such as in airports. The stakes are increasingly ...

We propose a structured prediction approach for robot imitation learning from demonstrations. Among various tools for robot imitation learning, supervised learning has been observed to have a prominent role. Structured prediction is a form of supervised le ...

For Graph Neural Networks, oversmoothing denotes the homogenization of vertex embeddings as the number of layers increases. To better understand this phenomenon, we study community detection with a linearized Graph Convolutional Network on the Contextual S ...

Clustering in education, particularly in large-scale online environments like MOOCs, is essential for understanding and adapting to diverse student needs. However, the effectiveness of clustering depends on its interpretability, which becomes challenging w ...

Neural network approaches to approximate the ground state of quantum hamiltonians require the numerical solution of a highly nonlinear optimization problem. We introduce a statistical learning approach that makes the optimization trivial by using kernel me ...

Object detection plays a critical role in various computer vision applications, encompassing domains like autonomous vehicles, object tracking, and scene understanding. These applica- tions rely on detectors that generate bounding boxes around known object ...

Monitoring forests, in particular their response to climate and land use change, requires studying long time scales. While efficient deep learning methods have been developed to process short time series of satellite imagery, leveraging long time series of ...

Crop maps are crucial for agricultural monitoring and food management and can additionally support domain-specific applications, such as setting cold supply chain infrastructure in developing countries. Machine learning (ML) models, combined with freely-av ...

It is widely believed that the success of deep networks lies in their ability to learn a meaningful representation of the features of the data. Yet, understanding when and how this feature learning improves performance remains a challenge. For example, it ...

TTT++: When Does Self-Supervised Test-Time Training Fail or Thrive?

Chat with Graph Search

Match Normalization: Learning-Based Point Cloud Registration for 6D Object Pose Estimation in the Real World

Learning Robust and Adaptive Representations: from Interactions, for Interactions

Test-time adaptation for 6D pose tracking

Can Self-Supervised Neural Representations Pre-Trained on Human Speech distinguish Animal Callers?

CloudProphet: A Machine Learning-Based Performance Prediction for Public Clouds

XTab: Cross-table Pretraining for Tabular Transformers

Understanding generalization and robustness in modern deep learning

MULTI-TASK CURRICULUM LEARNING FOR PARTIALLY LABELED DATA

Nissl_1, Raw images for Machine learning for histological annotation and quantification of cortical layers

SELF-SUPERVISED ISOTROPIC SUPERRESOLUTION FETAL BRAIN MRI

A semi-supervised algorithm for improving the consistency of crowdsourced datasets: The COVID-19 case study on respiratory disorder classification

Performing and Detecting Backdoor Attacks on Face Recognition Algorithms

A structured prediction approach for robot imitation learning

Optimal performance of Graph Convolutional Networks on the Contextual Stochastic Block Model

Interpret3C: Interpretable Student Clustering Through Individualized Feature Selection

Learning ground states of gapped quantum Hamiltonians with Kernel Methods

Improving Object Detection under Domain Shifts

Multi-temporal forest monitoring in the Swiss Alps with knowledge-guided deep learning

Using machine learning to generate an open-access cropland map from satellite images time series in the Indian Himalayan region

Learning sparse features can lead to overfitting in neural networks