Related papers: Mixup for Test-Time Training
Multilingual proficiency presents a significant challenge for large language models (LLMs). English-centric models are usually suboptimal in other languages, particularly those that are linguistically distant from English. This performance…
While deep neural networks can attain good accuracy on in-distribution test points, many applications require robustness even in the face of unexpected perturbations in the input, changes in the domain, or other sources of distribution…
Mixup is the latest data augmentation technique that linearly interpolates input examples and the corresponding labels. It has shown strong effectiveness in image classification by interpolating images at the pixel level. Inspired by this…
Continual Test Time Adaptation (CTTA) has emerged as a critical approach for bridging the domain gap between the controlled training environments and the real-world scenarios, enhancing model adaptability and robustness. Existing CTTA…
Contemporary Video Instance Segmentation (VIS) methods typically adhere to a pre-train then fine-tune regime, where a segmentation model trained on images is fine-tuned on videos. However, the lack of temporal knowledge in the pre-trained…
Test-Time Adaptation (TTA) addresses domain shifts between training and testing. However, existing methods assume a homogeneous target domain (e.g., single domain) at any given time. They fail to handle the dynamic nature of real-world…
Domain generalization (DG) aims to learn a generalizable model from multiple training domains such that it can perform well on unseen target domains. A popular strategy is to augment training data to benefit generalization through methods…
Given a model trained on source data, Test-Time Adaptation (TTA) enables adaptation and inference in test data streams with domain shifts from the source. Current methods predominantly optimize the model for each incoming test data batch…
In this paper, we explore alternative ways to train a neural machine translation system in a multi-domain scenario. We investigate data concatenation (with fine tuning), model stacking (multi-level fine tuning), data selection and…
Nowadays, deep neural networks outperform humans in many tasks. However, if the input distribution drifts away from the one used in training, their performance drops significantly. Recently published research has shown that adapting the…
Mixup is a highly successful technique to improve generalization of neural networks by augmenting the training data with combinations of random pairs. Selective mixup is a family of methods that apply mixup to specific pairs, e.g. only…
Domain adaptation becomes more challenging with increasing gaps between source and target domains. Motivated from an empirical analysis on the reliability of labeled source data for the use of distancing target domains, we propose…
Adversarial training is one of the predominant techniques for training classifiers that are robust to adversarial attacks. Recent work, however has found that adversarial training, which makes the overall classifier robust, it does not…
Multi-task model training has been adopted to enable a single deep neural network model (often a large language model) to handle multiple tasks (e.g., question answering and text summarization). Multi-task training commonly receives input…
Test-time augmentation -- the aggregation of predictions across transformed examples of test inputs -- is an established technique to improve the performance of image classification models. Importantly, TTA can be used to improve model…
Test-time adaptation (TTA) intends to adapt the pretrained model to test distributions with only unlabeled test data streams. Most of the previous TTA methods have achieved great success on simple test data streams such as independently…
Existing trajectory prediction methods exhibit significant performance degradation under distribution shifts during test time. Although test-time training techniques have been explored to enable adaptation, current approaches rely on an…
Mixup is a data-dependent regularization technique that consists in linearly interpolating input samples and associated outputs. It has been shown to improve accuracy when used to train on standard machine learning datasets. However,…
The ability for robots to transfer their learned knowledge to new tasks -- where data is scarce -- is a fundamental challenge for successful robot learning. While fine-tuning has been well-studied as a simple but effective transfer approach…
While scaling test-time compute can substantially improve model performance, existing approaches either rely on static compute allocation or sample from fixed generation distributions. In this work, we introduce a test-time compute…