相关论文: Harmonizing and Merging Source Models for CLIP-bas…

While vision-language models like CLIP have advanced zero-shot surgical phase recognition, they struggle with fine-grained surgical activities, especially action triplets. This limitation arises because current CLIP formulations rely on…

Merging Large Language Models (LLMs) is a cost-effective technique for combining multiple expert LLMs into a single versatile model, retaining the expertise of the original ones. However, current approaches often overlook the importance of…

To address the performance limitations of the Segment Anything Model (SAM) in specific domains, existing works primarily adopt adapter-based one-step adaptation paradigms. However, some of these methods are specific developed for specific…

Deep neural networks, trained with large amount of labeled data, can fail to generalize well when tested with examples from a \emph{target domain} whose distribution differs from the training data distribution, referred as the \emph{source…

Domain generalization aims to learn a model with good generalization ability, that is, the learned model should not only perform well on several seen domains but also on unseen domains with different data distributions. State-of-the-art…

Unsupervised domain adaptation studies the problem of utilizing a relevant source domain with abundant labels to build predictive modeling for an unannotated target domain. Recent work observe that the popular adversarial approach of…

The goal of domain generalization (DG) is to enhance the generalization capability of the model learned from a source domain to other unseen domains. The recently developed Sharpness-Aware Minimization (SAM) method aims to achieve this goal…

Contrastive Language--Image Pre-training (CLIP) has manifested remarkable improvements in zero-shot classification and cross-modal vision-language tasks. Yet, from a geometrical point of view, the CLIP embedding space has been found to have…

Unsupervised domain adaptation in person re-identification resorts to labeled source data to promote the model training on target domain, facing the dilemmas caused by large domain shift and large camera variations. The non-overlapping…

Vision-language models (VLMs) like CLIP have demonstrated impressive zero-shot ability in image classification tasks by aligning text and images but suffer inferior performance compared with task-specific expert models. On the contrary,…

Current mainstream post-training quantization methods for large language models typically apply a uniform quantization strategy across all network layers, overlooking the substantial differences in algorithmic suitability among layers. To…

Model merging provides a scalable alternative to multi-task training by combining specialized finetuned models through parameter arithmetic, enabling efficient deployment without the need for joint training or access to all task data. While…

Change detection is widely applied in remote sensing image analysis. Existing methods require training models separately for each dataset, which leads to poor domain generalization. Moreover, these methods rely heavily on large amounts of…

Clinical machine learning models experience significantly degraded performance in datasets not seen during training, e.g., new hospitals or populations. Recent developments in domain generalization offer a promising solution to this problem…

Medical image segmentation of anatomical structures and pathology is crucial in modern clinical diagnosis, disease study, and treatment planning. To date, great progress has been made in deep learning-based segmentation techniques, but most…

Model merging has achieved significant success, with numerous innovative methods proposed to enhance capabilities by combining multiple models. However, challenges persist due to the lack of a unified framework for classification and…

Recent advancements in large-scale visual-language pre-trained models have led to significant progress in zero-/few-shot anomaly detection within natural image domains. However, the substantial domain divergence between natural and medical…

Source-Free Domain Adaptation (SFDA) tackles the problem of adapting a pre-trained source model to an unlabeled target domain without accessing any source data, which is quite suitable for the field of data security. Although recent…

In this paper, we study multi-target domain adaptation of scene understanding models. While previous methods achieved commendable results through inter-domain consistency losses, they often assumed unrealistic simultaneous access to images…

Contrastive Language-Image Pretraining (CLIP) has emerged as a novel paradigm to learn visual models from language supervision. While researchers continue to push the frontier of CLIP, reproducing these works remains challenging. This is…