Related papers: FIESTA: Fisher Information-based Efficient Selecti…
Test Time Adaptation (TTA) addresses the problem of distribution shift by adapting a pretrained model to a new domain during inference. When faced with challenging shifts, most methods collapse and perform worse than the original pretrained…
In this study, we introduce an intelligent Test Time Augmentation (TTA) algorithm designed to enhance the robustness and accuracy of image classification models against viewpoint variations. Unlike traditional TTA methods that…
We introduce Ev-TTA, a simple, effective test-time adaptation algorithm for event-based object recognition. While event cameras are proposed to provide measurements of scenes with fast motions or drastic illumination changes, many existing…
Despite recent advancements in deep learning, deep neural networks continue to suffer from performance degradation when applied to new data that differs from training data. Test-time adaptation (TTA) aims to address this challenge by…
The goal of this paper is to enhance face recognition performance by augmenting head poses during the testing phase. Existing methods often rely on training on frontalised images or learning pose-invariant representations, yet both…
Test-time adaptation (TTA) is the problem of updating a pre-trained source model at inference time given test input(s) from a different target domain. Most existing TTA approaches assume the setting in which the target domain is stationary,…
Test-Time Adaptation (TTA) has emerged as a crucial solution to the domain shift challenge, wherein the target environment diverges from the original training environment. A prime exemplification is TTA for Automatic Speech Recognition…
Test-Time Adaptation (TTA) has emerged as a promising solution for adapting a source model to unseen medical sites using unlabeled test data, due to the high cost of data annotation. Existing TTA methods consider scenarios where data from…
Existing test-time adaptation (TTA) approaches often adapt models with the unlabeled testing data stream. A recent attempt relaxed the assumption by introducing limited human annotation, referred to as Human-In-the-Loop Test-Time Adaptation…
Source-free test-time adaptation (TTA) is appealing for mobile and wearable sensing because it enables on-device personalization from unlabeled test streams without centralizing private data. However, sensor-based human activity recognition…
Continual Test-time adaptation (CTTA) continuously adapts the deployed model on every incoming batch of data. While achieving optimal accuracy, existing CTTA approaches present poor real-world applicability on resource-constrained edge…
Speech emotion recognition (SER) with audio-language models (ALMs) remains vulnerable to distribution shifts at test time, leading to performance degradation in out-of-domain scenarios. Test-time adaptation (TTA) provides a promising…
Test-time adaptation (TTA) for large language models (LLMs) updates model parameters at inference time using signals available at deployment. This paper focuses on a common yet under-explored regime: unsupervised, sample-specific TTA, where…
Text-to-image retrieval is a critical task for managing diverse visual content, but common benchmarks for the task rely on small, single-domain datasets that fail to capture real-world complexity. Pre-trained vision-language models tend to…
Facial expression recognition (FER) models are widely used in video-based affective computing applications, such as human-computer interaction and healthcare monitoring. However, deep FER models often struggle with subtle expressions and…
Test-time adaptation (TTA) is a technique aimed at enhancing the generalization performance of models by leveraging unlabeled samples solely during prediction. Given the need for robustness in neural network systems when faced with…
Facial Expression Recognition (FER) plays a crucial role in human affective analysis and has been widely applied in computer vision tasks such as human-computer interaction and psychological assessment. The 8th Affective Behavior Analysis…
The goal of the challenge is to develop a test-time adaptation (TTA) method, which could adapt the model to gradually changing domains in video sequences for semantic segmentation task. It is based on a synthetic driving video dataset -…
Deep facial expression recognition faces two challenges that both stem from the large number of trainable parameters: long training times and a lack of interpretability. We propose a novel method based on evolutionary algorithms, that deals…
Federated Learning (FL) enables collaborative model training across distributed clients without sharing raw data, making it ideal for privacy-sensitive applications. However, FL models often suffer performance degradation due to…