Related papers: VISTA: Variance-Gated Inter-Sequence Test-Time Ada…

Test-time adaptation (TTA) enables online model adaptation using only unlabeled test data, aiming to bridge the gap between source and target distributions. However, in multimodal scenarios, varying degrees of distribution shift across…

Vision Transformer (ViT) is becoming more popular in image processing. Specifically, we investigate the effectiveness of test-time adaptation (TTA) on ViT, a technique that has emerged to correct its prediction during test-time by itself.…

Continual Test-Time Adaptation (CTTA) enables pre-trained models to adapt to continuously evolving domains. Existing methods have improved robustness but typically rely on fixed or batch-level thresholds, which cannot account for varying…

The advances in multi-modal foundation models (FMs) (e.g., CLIP and LLaVA) have facilitated the auto-labeling of large-scale datasets, enhancing model performance in challenging downstream tasks such as open-vocabulary object detection and…

Global localization is critical for autonomous navigation, particularly in scenarios where an agent must localize within a map generated in a different session or by another agent, as agents often have no prior knowledge about the…

Large-scale Vision-Language Models (VLMs) exhibit strong zero-shot recognition, yet their real-world deployment is challenged by distribution shifts. While Test-Time Adaptation (TTA) can mitigate this, existing VLM-based TTA methods operate…

Learning causal structures from observational data remains a fundamental yet computationally intensive task, particularly in high-dimensional settings where existing methods face challenges such as the super-exponential growth of the search…

Continual Test-Time Adaptation (CTTA) aims to empower perception systems to handle dynamic distribution shifts encountered after deployment. Existing methods predominantly follow a backward-alignment paradigm, which rigidly aligns incoming…

Test-Time Adaptation (TTA) has emerged as a promising paradigm for enhancing the generalizability of models. However, existing mainstream TTA methods, predominantly operating at batch level, often exhibit suboptimal performance in complex…

Test-time adaptation (TTA) methods have gained significant attention for enhancing the performance of vision-language models (VLMs) such as CLIP during inference, without requiring additional labeled data. However, current TTA researches…

Pre-trained vision-language models provide a robust foundation for efficient transfer learning across various downstream tasks. In the field of video action recognition, mainstream approaches often introduce additional modules to capture…

Recently, test-time adaptation has attracted wide interest in the context of vision-language models for image classification. However, to the best of our knowledge, the problem is completely overlooked in dense prediction tasks such as…

Time Series Anomaly Detection (TSAD) is essential for uncovering rare and potentially harmful events in unlabeled time series data. Existing methods are highly dependent on clean, high-quality inputs, making them susceptible to noise and…

Current multimodal large language models (MLLMs) face a critical challenge in modality alignment, often exhibiting a bias towards textual information at the expense of other modalities like vision. This paper conducts a systematic…

Test-time adaptation (TTA) has gained increasing popularity due to its efficacy in addressing ``distribution shift'' issue while simultaneously protecting data privacy. However, most prior methods assume that a paired source domain model…

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 -…

Pretrained vision-language models (VLMs) like CLIP show strong zero-shot performance but struggle with generalization under distribution shifts. Test-Time Adaptation (TTA) addresses this by adapting VLMs to unlabeled test data in new…

Fully supervised Video Semantic Segmentation (VSS) relies heavily on densely annotated video data, limiting practical applicability. Alternatively, applying pre-trained Image Semantic Segmentation (ISS) models frame-by-frame avoids…

Reliable brain tumor segmentation in MRI is indispensable for treatment planning and outcome monitoring, yet models trained on curated benchmarks often fail under domain shifts arising from scanner and protocol variability as well as…

Multimodal sentiment analysis (MSA) is an emerging research topic that aims to understand and recognize human sentiment or emotions through multiple modalities. However, in real-world dynamic scenarios, the distribution of target data is…