Related papers: Segmentation Assisted Incremental Test Time Adapta…

Large pre-trained vision-language models (VLMs), such as CLIP, have shown unprecedented zero-shot performance across a wide range of tasks. Nevertheless, these models may be unreliable under distributional shifts, as their performance is…

Open world image segmentation aims to achieve precise segmentation and semantic understanding of targets within images by addressing the infinitely open set of object categories encountered in the real world. However, traditional closed-set…

Segmentation models are typically constrained by the categories defined during training. To address this, researchers have explored two independent approaches: adapting Vision-Language Models (VLMs) and leveraging synthetic data. However,…

Change detection is a fundamental task in remote sensing, aiming to quantify the impacts of human activities and ecological dynamics on land-cover changes. Existing change detection methods are limited to predefined classes in training…

In-context learning (ICL) with Large Vision Models (LVMs) presents a promising avenue in medical image segmentation by reducing the reliance on extensive labeling. However, the ICL performance of LVMs highly depends on the choices of visual…

Deep learning models have demonstrated exceptional performance across a wide range of computer vision tasks. However, their performance often degrades significantly when faced with distribution shifts, such as domain or dataset changes.…

Although significant progress has been made in few-shot learning, most of existing few-shot image classification methods require supervised pre-training on a large amount of samples of base classes, which limits their generalization ability…

One fascinating aspect of pre-trained Audio-Language Models (ALMs) learning is their impressive zero-shot generalization capability and test-time adaptation (TTA) methods aiming to improve domain performance without annotations. However,…

In the context of supervised statistical learning, it is typically assumed that the training set comes from the same distribution that draws the test samples. When this is not the case, the behavior of the learned model is unpredictable and…

Land-cover understanding in remote sensing increasingly demands class-agnostic systems that generalize across datasets while remaining spatially precise and interpretable. We study a geometry-first discovery-and-interpretation setting under…

Test-time adaptation (TTA) has emerged as a promising paradigm for vision-language models (VLMs) to bridge the distribution gap between pre-training and test data. Recent works have focused on backpropagation-free TTA methods that rely on…

Increasingly advanced data augmentation techniques have greatly aided clinical medical research, increasing data diversity and improving model generalization capabilities. Although most current basic models exhibit strong generalization…

Domain adaptation helps generalizing object detection models to target domain data with distribution shift. It is often achieved by adapting with access to the whole target domain data. In a more realistic scenario, target distribution is…

Although the current different types of SAM adaptation methods have achieved promising performance for various downstream tasks, such as prompt-based ones and adapter-based ones, most of them belong to the one-step adaptation paradigm. In…

Test time adaptation (TTA) aims to adapt deep neural networks when receiving out of distribution test domain samples. In this setting, the model can only access online unlabeled test samples and pre-trained models on the training domains.…

Tactile-vision-language (TVL) models are increasingly deployed in real-world robotic and multimodal perception tasks, where test-time distribution shifts are unavoidable. Existing test-time adaptation (TTA) methods provide filtering in…

We introduce a new image segmentation task, called Entity Segmentation (ES), which aims to segment all visual entities (objects and stuffs) in an image without predicting their semantic labels. By removing the need of class label…

Vision-Language Models (VLMs) such as CLIP have yielded unprecedented performance for zero-shot image classification, yet their generalization capability may still be seriously challenged when confronted to domain shifts. In response, we…

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…

Training deep networks for semantic segmentation requires large amounts of labeled training data, which presents a major challenge in practice, as labeling segmentation masks is a highly labor-intensive process. To address this issue, we…