Related papers: Bridging Modalities via Progressive Re-alignment f…
Graph-based learning excels at capturing interaction patterns in diverse domains like recommendation, fraud detection, and particle physics. However, its performance often degrades under distribution shifts, especially those altering…
Deep learning models often struggle under natural distribution shifts, a common challenge in real-world deployments. Test-Time Adaptation (TTA) addresses this by adapting models during inference without labeled source data. We present the…
Multi-modal learning aims to enhance performance by unifying models from various modalities but often faces the "modality imbalance" problem in real data, leading to a bias towards dominant modalities and neglecting others, thereby limiting…
Model-based reinforcement learning is attractive for sequential decision-making because it explicitly estimates reward and transition models and then supports planning through simulated rollouts. In offline settings with hidden confounding,…
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…
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…
We consider the problem of improving the human instance segmentation mask quality for a given test image using keypoints estimation. We compare two alternative approaches. The first approach is a test-time adaptation (TTA) method, where we…
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…
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…
Currently, pre-trained language models (PLMs) do not cope well with the distribution shift problem, resulting in models trained on the training set failing in real test scenarios. To address this problem, the test-time adaptation (TTA)…
Integrating heterogeneous modalities such as histopathology and genomics is central to advancing survival analysis, yet most existing methods prioritize cross-modal alignment through attention-based fusion mechanisms, often at the expense…
Unsupervised Domain Adaptation transfers knowledge from a labeled source domain to an unlabeled target domain. Directly deploying Vision-Language Models (VLMs) with prompt tuning in downstream UDA tasks faces the signifi cant challenge of…
Test-time adaptation (TTA) aims to fine-tune a trained model online using unlabeled testing data to adapt to new environments or out-of-distribution data, demonstrating broad application potential in real-world scenarios. However, in this…
Deep learning-based medical image segmentation models often face performance degradation when deployed across various medical centers, largely due to the discrepancies in data distribution. Test Time Adaptation (TTA) methods, which adapt…
In this technical report, we present our submission to the VisDA Challenge in ECCV 2020 and we achieved one of the top-performing results on the leaderboard. Our solution is based on Structured Domain Adaptation (SDA) and Mutual…
Although open-vocabulary classification models like Contrastive Language Image Pretraining (CLIP) have demonstrated strong zero-shot learning capabilities, their robustness to common image corruptions remains poorly understood. Through…
Continual Test-Time Adaptation (CTTA) involves adapting a pre-trained source model to continually changing unsupervised target domains. In this paper, we systematically analyze the challenges of this task: online environment, unsupervised…
Multivariate time-series anomaly detection (MTSAD) aims to identify deviations from normality in multivariate time-series and is critical in real-world applications. However, in real-world deployments, distribution shifts are ubiquitous and…
In this work, we propose a novel complementary learning approach to enhance test-time adaptation (TTA), which has been proven to exhibit good performance on testing data with distribution shifts such as corruptions. In test-time adaptation…
Action Quality Assessment (AQA) aims to score how well an action is performed and is widely used in sports analysis, rehabilitation assessment, and human skill evaluation. Multi-modal AQA has recently achieved strong progress by leveraging…