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.

We propose a method for unsupervised reconstruction of a temporally-consistent sequence of surfaces from a sequence of time-evolving point clouds. It yields dense and semantically meaningful correspondences between frames. We represent the reconstructed su ...

Dynamic hand gesture recognition (HGR) is critical for real-time prosthetics and neural robotics applications, where high-density surface electromyography (HD-sEMG) signals provide valuable insights into muscle activity. However, adapting machine learning ...

Machine learning models, meticulously optimized for source data, often fail to predict target data when faced with distribution shifts (DSs). Previous benchmarking studies, though extensive, have mainly focused on simple DSs. Recognizing that DSs often occ ...

Lattice light-sheet microscopy provides a crucial observation window into intra- and intercellular physiology of living specimens but at the diffraction-limited resolution or anisotropic super-resolution with structured illumination. Here we present meta-l ...

This paper studies the problem of learning computable functions in the limit by extending Gold's inductive inference framework to incorporate computational observations and restricted input sources. Complimentary to the traditional Input-Output Observation ...

In the realm of point cloud scene understanding, particularly in indoor scenes, objects are arranged following human habits, resulting in objects of certain semantics being closely positioned and displaying notable inter-object correlations. This can creat ...

Machine learning (ML) enables artificial intelligent (AI) agents to learn autonomously from data obtained from their environment to perform tasks. Modern ML systems have proven to be extremely effective, reaching or even exceeding human intelligence. Altho ...

Modern neuroscience research is generating increasingly large datasets, from recording thousands of neurons over long timescales to behavioral recordings of animals spanning weeks, months, or even years. Despite a great variety in recording setups and expe ...

HOISDF: Constraining 3D Hand-Object Pose Estimation with Global Signed Distance Fields, CVPR 2024 Haozhe Qi, Chen Zhao, Mathieu Salzmann, Alexander Mathis. Affiliation: EPFL Date: June, 2024 Link to the CVPR article: https://openaccess.thecvf.com/conte ...

In the past few years, Machine Learning (ML) techniques have ushered in a paradigm shift, allowing the harnessing of ever more abundant sources of data to automate complex tasks. The technical workhorse behind these important breakthroughs arguably lies in ...

This thesis focuses on the development of advanced algorithmic techniques, primarily Markov Chain Monte Carlo (MCMC) methods, and message passing algorithms, to tackle high-dimensional optimization and inference problems. The algorithms used have a probabi ...

Recent advancements in deep learning have revolutionized 3D computer vision, enabling the extraction of intricate 3D information from 2D images and video sequences. This thesis explores the application of deep learning in three crucial challenges of 3D com ...

Denoising Diffusion Probabilistic Models (DDPMs) exhibit remarkable capabilities in image generation, with studies suggesting that they can generalize by composing latent factors learned from the training data. In this work, we go further and study DDPMs t ...

In fully supervised learning-based medical image classification, the robustness of a trained model depends on its exposure to various disease classes. Generalized Zero Shot Learning (GZSL) aims to predict both seen and novel unseen classes. While most GZSL ...

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 ...

Monitoring the health of complex industrial assets is crucial for safe and efficient operations. Health indicators that provide quantitative real-time insights into the health status of industrial assets over time serve as valuable tools for, e.g., fault d ...

Over the years, clinical institutes accumulated large amounts of digital slides from resected tissue specimens. These digital images, called whole slide images (WSIs), are high-resolution tissue snapshots that depict the complex interaction of cells at the ...

We introduce robust principal component analysis from a data matrix in which the entries of its columns have been corrupted by permutations, termed Unlabeled Principal Component Analysis (UPCA). Using algebraic geometry, we establish that UPCA is a well-de ...

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 ...

Objective. Many psychiatric disorders involve excessive avoidant or defensive behavior, such as avoidance in anxiety and trauma disorders or defensive rituals in obsessive-compulsive disorders. Developing algorithms to predict these behaviors from local fi ...

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

Chat with Graph Search

Temporally-Consistent Surface Reconstruction Using Metrically-Consistent Atlases

Low-Rank Adaptation for Transformers in Dynamic Hand Gesture Recognition Using High-Density Surface Electromyography

An Analysis of Model Robustness across Concurrent Distribution Shifts

Fast-adaptive super-resolution lattice light-sheet microscopy for rapid, long-term, near-isotropic subcellular imaging

Learning Algorithms in the Limit

Mitigating Object Dependencies: Improving Point Cloud Self-Supervised Learning through Object Exchange

Few-shot Learning for Efficient and Effective Machine Learning Model Adaptation

Robust machine learning for neuroscientific inference

HOISDF: Constraining 3D Hand-Object Pose Estimation with Global Signed Distance Fields: Processed data and trained models

Topics in statistical physics of high-dimensional machine learning

Advances in Algorithms for Sampling, Optimization and Inference in Disordered Systems

Advancing Self-Supervised Deep Learning for 3D Scene Understanding

Going beyond Compositions, DDPMs Can Produce Zero-Shot Interpolations

Multi-Label Generalized Zero Shot Chest X-Ray Classification by Combining Image-Text Information With Feature Disentanglement

Aggregating Spatial and Photometric Context for Photometric Stereo

Learning Informative Health Indicators Through Unsupervised Contrastive Learning

Self-Supervised Learning for Patient Stratification and Survival Analysis in Computational Pathology: An Application to Colorectal Cancer

Unlabeled Principal Component Analysis and Matrix Completion

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

Neural decoding and feature selection methods for closed-loop control of avoidance behavior