Related papers: Efficient Diffusion-Driven Corruption Editor for T…
Deep learning-based diagnostic systems have demonstrated potential in skin disease diagnosis. However, their performance can easily degrade on test domains due to distribution shifts caused by input-level corruptions, such as imaging…
The advancements in generative modeling, particularly the advent of diffusion models, have sparked a fundamental question: how can these models be effectively used for discriminative tasks? In this work, we find that generative models can…
Real-world image recognition systems often face corrupted input images, which cause distribution shifts and degrade the performance of models. These systems often use a single prediction model in a central server and process images sent…
Diffusion models have achieved remarkable success in the domain of text-guided image generation and, more recently, in text-guided image editing. A commonly adopted strategy for editing real images involves inverting the diffusion process…
In this work, we study Source-Free Unsupervised Domain Adaptation under corruption-induced domain shifts, where performance degradation is caused by natural image corruptions that go beyond additive noise, including blur, weather effects,…
Test-time adaptation (TTA) of 3D point clouds is crucial for mitigating discrepancies between training and testing samples in real-world scenarios, particularly when handling corrupted point clouds. LiDAR data, for instance, can be affected…
Test-time adaptation (TTA) aims to correct performance degradation of deep models under distribution shifts by updating models or inputs using unlabeled test data. Input-only diffusion-based TTA methods improve robustness for classification…
Test-time adaptation harnesses test inputs to improve the accuracy of a model trained on source data when tested on shifted target data. Existing methods update the source model by (re-)training on each target domain. While effective,…
Recently, diffusion-based test-time adaptations (TTA) have shown great advances, which leverage a diffusion model to map the images in the unknown test domain to the training domain. The unseen and diverse test domains make diffusion-based…
Machine learning models struggle with generalization when encountering out-of-distribution (OOD) samples with unexpected distribution shifts. For vision tasks, recent studies have shown that test-time adaptation employing diffusion models…
Pretrained VLMs exhibit strong zero-shot classification capabilities, but their predictions degrade significantly under common image corruptions. To improve robustness, many test-time adaptation (TTA) methods adopt positive data…
While diffusion language models (DLMs) enable fine-grained refinement, their practical controllability remains fragile. We identify and formally characterize a central failure mode called update forgetting, in which uniform and context…
Test Time Adaptation (TTA) has emerged as a practical solution to mitigate the performance degradation of Deep Neural Networks (DNNs) in the presence of corruption/ noise affecting inputs. Existing approaches in TTA continuously adapt the…
Test-time adaptation (TTA) is a technique used to reduce distribution gaps between the training and testing sets by leveraging unlabeled test data during inference. In this work, we expand TTA to a more practical scenario, where the test…
Test-Time Adaptation (TTA) allows to update pre-trained models to changing data distributions at deployment time. While early work tested these algorithms for individual fixed distribution shifts, recent work proposed and applied methods…
Test-time adaptation (TTA) aims to improve the performance of source-domain pre-trained models on previously unseen, shifted target domains. Traditional TTA methods primarily adapt model weights based on target data streams, making model…
Recent advances in diffusion models enable many powerful instruments for image editing. One of these instruments is text-driven image manipulations: editing semantic attributes of an image according to the provided text description. %…
Test-time alignment (TTA) aims to adapt models to specific rewards during inference. However, existing methods tend to either under-optimise or over-optimise (reward hack) the target reward function. We propose Null-Text Test-Time Alignment…
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…
The tremendous progress in neural image generation, coupled with the emergence of seemingly omnipotent vision-language models has finally enabled text-based interfaces for creating and editing images. Handling generic images requires a…