Related papers: MetaDAT: Generalizable Trajectory Prediction via M…

The goal of optimization-based meta-learning is to find a single initialization shared across a distribution of tasks to speed up the process of learning new tasks. Conditional meta-learning seeks task-specific initialization to better…

Human mesh recovery from single images remains challenging due to inherent depth ambiguity and limited generalization across domains. While recent methods combine regression and optimization approaches, they struggle with poor…

Autonomous navigation in off-road conditions requires an accurate estimation of terrain traversability. However, traversability estimation in unstructured environments is subject to high uncertainty due to the variability of numerous…

Fully test-time adaptation aims at adapting a pre-trained model to the test stream during real-time inference, which is urgently required when the test distribution differs from the training distribution. Several efforts have been devoted…

The high sample complexity of reinforcement learning challenges its use in practice. A promising approach is to quickly adapt pre-trained policies to new environments. Existing methods for this policy adaptation problem typically rely on…

Accumulating substantial volumes of real-world driving data proves pivotal in the realm of trajectory forecasting for autonomous driving. Given the heavy reliance of current trajectory forecasting models on data-driven methodologies, we aim…

Prior to deployment, an object detector is trained on a dataset compiled from a previous data collection campaign. However, the environment in which the object detector is deployed will invariably evolve, particularly in outdoor settings…

Self-supervised learning has garnered increasing attention in time series analysis for benefiting various downstream tasks and reducing reliance on labeled data. Despite its effectiveness, existing methods often struggle to comprehensively…

Adaptive gradient methods are the method of choice for optimization in machine learning and used to train the largest deep models. In this paper we study the problem of learning a local preconditioner, that can change as the data is…

As deep neural networks are increasingly deployed in dynamic, real-world environments, relying on a single static model is often insufficient. Changes in input data distributions caused by sensor drift or lighting variations necessitate…

We consider the problem of online fine tuning the parameters of a language model at test time, also known as dynamic evaluation. While it is generally known that this approach improves the overall predictive performance, especially when…

Over the past decade, the field of machine learning has experienced remarkable advancements. While image recognition systems have achieved impressive levels of accuracy, they continue to rely on extensive training datasets. Additionally, a…

In this work, we tackle the problem of online adaptation for stereo depth estimation, that consists in continuously adapting a deep network to a target video recordedin an environment different from that of the source training set. To…

The exponential growth of volume, variety and velocity of data is raising the need for investigations of automated or semi-automated ways to extract useful patterns from the data. It requires deep expert knowledge and extensive…

Forecasting future trajectories of agents in complex traffic scenes requires reliable and efficient predictions for all agents in the scene. However, existing methods for trajectory prediction are either inefficient or sacrifice accuracy.…

Test-time adaptation (TTA) enhances the zero-shot robustness under distribution shifts by leveraging unlabeled test data during inference. Despite notable advances, several challenges still limit its broader applicability. First, most…

Accurate dynamics models are critical for the design of predictive controller for autonomous mobile robots. Physics-based models are often too simple to capture relevant real-world effects, while data-driven models are data-intensive and…

Many methods have been proposed to detect concept drift, i.e., the change in the distribution of streaming data, due to concept drift causes a decrease in the prediction accuracy of algorithms. However, the most of current detection methods…

Training on test-time data enables deep learning models to adapt to dynamic environmental changes, enhancing their practical applicability. Online adaptation from source to target domains is promising but it remains highly reliant on the…

Deep learning-based weather prediction models have advanced significantly in recent years. However, data-driven models based on deep learning are difficult to apply to real-world applications because they are vulnerable to spatial-temporal…