Related papers: Early Stopping for Deep Image Prior

Early stopping based on the validation set performance is a popular approach to find the right balance between under- and overfitting in the context of supervised learning. However, in reinforcement learning, even for supervised…

Learning a good image prior is a long-term goal for image restoration and manipulation. While existing methods like deep image prior (DIP) capture low-level image statistics, there are still gaps toward an image prior that captures rich…

Diffusion models face a fundamental trade-off between generation quality and computational efficiency. Latent Diffusion Models (LDMs) offer an efficient solution but suffer from potential information loss and non-end-to-end training. In…

Fine-tuning a visual pre-trained model can leverage the semantic information from large-scale pre-training data and mitigate the over-fitting problem on downstream vision tasks with limited training examples. While the problem of…

Masked image modeling (MIM) as pre-training is shown to be effective for numerous vision downstream tasks, but how and where MIM works remain unclear. In this paper, we compare MIM with the long-dominant supervised pre-trained models from…

While image-text representation learning has become very popular in recent years, existing models tend to lack spatial awareness and have limited direct applicability for dense understanding tasks. For this reason, self-supervised…

Exploiting light field data makes it possible to obtain dense and accurate depth map. However, synthetic scenes with limited disparity range cannot contain the diversity of real scenes. By training in synthetic data, current learning-based…

The absence of an algorithm that effectively monitors deep learning models used in side-channel attacks increases the difficulty of evaluation. If the attack is unsuccessful, the question is if we are dealing with a resistant implementation…

Conventional techniques to establish dense correspondences across visually or semantically similar images focused on designing a task-specific matching prior, which is difficult to model. To overcome this, recent learning-based methods have…

Synthetic aperture sonar (SAS) requires precise positional and environmental information to produce well-focused output during the image reconstruction step. However, errors in these measurements are commonly present resulting in defocused…

Dynamic MRI reconstruction from undersampled measurements is a challenging inverse problem that requires preserving both spatial reconstruction quality and temporal consistency across the frames of the cine series. While recent…

Deep Neural Networks (DNNs) are well-known to act as over-parameterized deep image priors (DIP) that regularize various image inverse problems. Meanwhile, researchers also proposed extremely compact, under-parameterized image priors (e.g.,…

Recently, Segment Anything Model (SAM) has become a research hotspot in the fields of multimedia and computer vision, which exhibits powerful yet versatile capabilities on various (un) conditional image segmentation tasks. Although SAM can…

Deep learning has demonstrated its power in image rectification by leveraging the representation capacity of deep neural networks via supervised training based on a large-scale synthetic dataset. However, the model may overfit the synthetic…

Seismic images often contain both coherent and random artifacts which complicate their interpretation. To mitigate these artifacts, we introduce a novel unsupervised deep-learning method based on Deep Image Prior (DIP) which uses…

Early stopping is a widely used technique to prevent poor generalization performance when training an over-expressive model by means of gradient-based optimization. To find a good point to halt the optimizer, a common practice is to split…

Existing deep-learning based tomographic image reconstruction methods do not provide accurate estimates of reconstruction uncertainty, hindering their real-world deployment. This paper develops a method, termed as the linearised deep image…

In Inverse Synthetic Aperture Radar (ISAR), random missing entries of the received radar echo matrix deteriorate the imaging quality, compromising target distinction from the background. Compressive sensing techniques or matrix completion…

Assisted by the availability of data and high performance computing, deep learning techniques have achieved breakthroughs and surpassed human performance empirically in difficult tasks, including object recognition, speech recognition, and…

Cardiovascular magnetic resonance imaging is a powerful diagnostic tool for assessing cardiac structure and function. However, traditional breath-held imaging protocols pose challenges for patients with arrhythmias or limited breath-holding…