Related papers: TRAM: Bridging Trust Regions and Sharpness Aware M…
Due to the scarcity of annotated data and the substantial computational costs of model, conventional tuning methods in medical image segmentation face critical challenges. Current approaches to adapting pretrained models, including…
Adapter based fine-tuning has been studied for improving the performance of SAM on downstream tasks. However, there is still a significant performance gap between fine-tuned SAMs and domain-specific models. To reduce the gap, we propose…
The Segment Anything Model (SAM), a vision foundation model, exhibits impressive zero-shot capabilities in general tasks but struggles in specialized domains. Parameter-efficient fine-tuning (PEFT) is a promising approach to unleash the…
In the literature, coarse-to-fine or scale-recurrent approach i.e. progressively restoring a clean image from its low-resolution versions has been successfully employed for single image deblurring. However, a major disadvantage of existing…
The Segment Anything Model (SAM) serves as a fundamental model for semantic segmentation and demonstrates remarkable generalization capabilities across a wide range of downstream scenarios. In this empirical study, we examine SAM's…
Convolutional neural networks require numerous data for training. Considering the difficulties in data collection and labeling in some specific tasks, existing approaches generally use models pre-trained on a large source domain (e.g.…
Despite that the segment anything model (SAM) achieved impressive results on general-purpose semantic segmentation with strong generalization ability on daily images, its demonstrated performance on medical image segmentation is less…
Out-of-distribution (OOD) generalization is a challenging machine learning problem yet highly desirable in many high-stake applications. Existing methods suffer from overly pessimistic modeling with low generalization confidence. As…
Recent successes suggest that parameter-efficient fine-tuning of foundation models as the state-of-the-art method for transfer learning in vision, replacing the rich literature of alternatives such as meta-learning. In trying to harness the…
Neural machine translation often adopts the fine-tuning approach to adapt to specific domains. However, nonrestricted fine-tuning can easily degrade on the general domain and over-fit to the target domain. To mitigate the issue, we propose…
Feature-based transfer is one of the most effective methodologies for transfer learning. Existing studies usually assume that the learned new feature representation is \emph{domain-invariant}, and thus train a transfer model $\mathcal{M}$…
Prompt learning has emerged as a promising method for adapting pre-trained visual-language models (VLMs) to a range of downstream tasks. While optimizing the context can be effective for improving performance on specific tasks, it can often…
Domain adaptation aims to mitigate performance degradation caused by distribution shifts between a labeled source domain and an unlabeled or sparsely labeled target domain. Most existing approaches estimate domain discrepancy either in…
The increasing ubiquity of video content and the corresponding demand for efficient access to meaningful information have elevated video summarization and video highlights as a vital research area. However, many state-of-the-art methods…
The growing use of information hiding in network streaming media for covert communication poses a significant security threat, necessitating the development of robust detection technologies. However, existing steganalysis methods for…
With the proliferation of mobile devices, the need for an efficient model to restore any degraded image has become increasingly significant and impactful. Traditional approaches typically involve training dedicated models for each specific…
Recent studies showed that the generalization of neural networks is correlated with the sharpness of the loss landscape, and flat minima suggests a better generalization ability than sharp minima. In this paper, we propose a novel method…
We consider the minimization of non-convex functions that typically arise in machine learning. Specifically, we focus our attention on a variant of trust region methods known as cubic regularization. This approach is particularly attractive…
Methods for improving deep neural network training times and model generalizability consist of various data augmentation, regularization, and optimization approaches, which tend to be sensitive to hyperparameter settings and make…
Unsupervised domain adaptation (UDA) for semantic segmentation seeks to transfer models from a labeled source domain to an unlabeled target domain. While auxiliary self-supervised tasks such as contrastive learning have enhanced feature…