Related papers: Tackling Device Data Distribution Real-time Shift …
Domain Adaptation (DA) is a method for enhancing a model's performance on a target domain with inadequate annotated data by applying the information the model has acquired from a related source domain with sufficient labeled data. The…
The performance of deep learning models depends heavily on test samples at runtime, and shifts from the training data distribution can significantly reduce accuracy. Test-time adaptation (TTA) addresses this by adapting models during…
Personalization in Large Language Models (LLMs) often relies on user-specific soft prompts. However, these prompts become obsolete when the foundation model is upgraded, necessitating costly, full-scale retraining. To overcome this…
Personalizing visual generative models to meet specific user needs has gained increasing attention, yet current methods like Low-Rank Adaptation (LoRA) remain impractical due to their demand for task-specific data and lengthy optimization.…
Data-driven approaches to modeling physical systems fail to generalize to unseen systems that share the same general dynamics with the learning domain, but correspond to different physical contexts. We propose a new framework for this key…
Policies often fail due to distribution shift -- changes in the state and reward that occur when a policy is deployed in new environments. Data augmentation can increase robustness by making the model invariant to task-irrelevant changes in…
Fashion image editing aims to modify a person's appearance based on a given instruction. Existing methods require auxiliary tools like segmenters and keypoint extractors, lacking a flexible and unified framework. Moreover, these methods are…
While deep learning has significantly improved ReID model accuracy under the independent and identical distribution (IID) assumption, it has also become clear that such models degrade notably when applied to an unseen novel domain due to…
Recent advances in diffusion models have enabled high-quality synthesis of specific subjects, such as identities or objects. This capability, while unlocking new possibilities in content creation, also introduces significant privacy risks,…
In practice, environments constantly change over time and space, posing significant challenges for object detectors trained based on a closed-set assumption, i.e., training and test data share the same distribution. To this end, continual…
Large-scale diffusion models like Stable Diffusion are powerful and find various real-world applications while customizing such models by fine-tuning is both memory and time inefficient. Motivated by the recent progress in natural language…
In recent years, researchers have been paying increasing attention to the threats brought by deep learning models to data security and privacy, especially in the field of domain adaptation. Existing unsupervised domain adaptation (UDA)…
Test-time domain adaptation aims to adapt a source pre-trained model to a target domain without using any source data. Existing works mainly consider the case where the target domain is static. However, real-world machine perception systems…
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,…
Personas are crucial in software development processes, particularly in agile settings. However, no effective tools are available for generating personas from user feedback in agile software development processes. To fill this gap, we…
Parameter-efficient fine-tuning (PEFT) has shown its effectiveness in adapting the pre-trained language models to downstream tasks while only updating a small number of parameters. Despite the success, most existing methods independently…
Distribution shifts between sites can seriously degrade model performance since models are prone to exploiting unstable correlations. Thus, many methods try to find features that are stable across sites and discard unstable features.…
After developer adjustments to a machine learning (ML) algorithm, how can the results of an old hyperparameter optimization (HPO) automatically be used to speedup a new HPO? This question poses a challenging problem, as developer…
Unsupervised cross-domain person re-identification (Re-ID) faces two key issues. One is the data distribution discrepancy between source and target domains, and the other is the lack of labelling information in target domain. They are…
Although person re-identification has achieved an impressive improvement in recent years, the common occlusion case caused by different obstacles is still an unsettled issue in real application scenarios. Existing methods mainly address…