Related papers: Dynamic Prompt Allocation and Tuning for Continual…

Since distribution shifts are likely to occur during test-time and can drastically decrease the model's performance, online test-time adaptation (TTA) continues to update the model after deployment, leveraging the current test data.…

Fully test-time adaptation (FTTA) adapts a model that is trained on a source domain to a target domain during the testing phase, where the two domains follow different distributions and source data is unavailable during the training phase.…

Recent continual test-time adaptation (CTTA) methods adopt masked image modeling to stabilize learning under distribution shift, yet each treats its masking family $F$ as a fixed design choice and innovates exclusively along the selection…

Test-time adaptation (TTA) aims to adapt a pre-trained model to the target domain in a batch-by-batch manner during inference. While label distributions often exhibit imbalances in real-world scenarios, most previous TTA approaches…

It has been demonstrated that the art of prompt tuning is highly effective in efficiently extracting knowledge from pretrained foundation models, encompassing pretrained language models (PLMs), vision pretrained models, and vision-language…

We study test-time domain adaptation for audio deepfake detection (ADD), addressing three challenges: (i) source-target domain gaps, (ii) limited target dataset size, and (iii) high computational costs. We propose an ADD method using prompt…

Visual prompt tuning (VPT) is a promising solution incorporating learnable prompt tokens to customize pre-trained models for downstream tasks. However, VPT and its variants often encounter challenges like prompt initialization, prompt…

Recent works on domain adaptation exploit adversarial training to obtain domain-invariant feature representations from the joint learning of feature extractor and domain discriminator networks. However, domain adversarial methods render…

Most standard learning approaches lead to fragile models which are prone to drift when sequentially trained on samples of a different nature - the well-known "catastrophic forgetting" issue. In particular, when a model consecutively learns…

Existing prompt-tuning methods have demonstrated impressive performances in continual learning (CL), by selecting and updating relevant prompts in the vision-transformer models. On the contrary, this paper aims to learn each task by tuning…

This paper presents a simple yet effective approach that improves continual test-time adaptation (TTA) in a memory-efficient manner. TTA may primarily be conducted on edge devices with limited memory, so reducing memory is crucial but has…

Pre-trained language models (LM) such as BERT, DistilBERT, and RoBERTa can be tuned for different domains (domain-tuning) by continuing the pre-training phase on a new target domain corpus. This simple domain tuning (SDT) technique has been…

Continual Test-Time Adaptation (CTTA), which aims to adapt the pre-trained model to ever-evolving target domains, emerges as an important task for vision models. As current vision models appear to be heavily biased towards texture,…

Conventional continual pretraining (CPT) for large language model (LLM) domain adaptation often suffers from catastrophic forgetting and limited domain capacity. Existing strategies adopt layer expansion, introducing additional trainable…

Although unsupervised domain adaptation methods have achieved remarkable performance in semantic scene segmentation in visual perception for self-driving cars, these approaches remain impractical in real-world use cases. In practice, the…

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…

Test-time adaptation (TTA) aims to mitigate performance degradation under distribution shifts by updating model parameters during inference. Existing approaches have primarily framed adaptation around affine modulation, focusing on…

Domain adaptation refers to the problem of leveraging labeled data in a source domain to learn an accurate model in a target domain where labels are scarce or unavailable. A recent approach for finding a common representation of the two…

The creation of large-scale open domain reading comprehension data sets in recent years has enabled the development of end-to-end neural comprehension models with promising results. To use these models for domains with limited training…

Prompt tuning has been an extremely effective tool to adapt a pre-trained model to downstream tasks. However, standard prompt-based methods mainly consider the case of sufficient data of downstream tasks. It is still unclear whether the…