Related papers: Self-Validation: Early Stopping for Single-Instanc…

The challenges inherent in long-horizon tasks in robotics persist due to the typical inefficient exploration and sparse rewards in traditional reinforcement learning approaches. To address these challenges, we have developed a novel…

Self-supervised learning (SSL) holds promise in leveraging large amounts of unlabeled data. However, the success of popular SSL methods has limited on single-centric-object images like those in ImageNet and ignores the correlation among the…

RGB-Infrared person re-identification (RGB-IR ReID) aims to associate people across disjoint RGB and IR camera views. Currently, state-of-the-art performance of RGB-IR ReID is not as impressive as that of conventional ReID. Much of that is…

Single image super-resolution (SISR) is the process of obtaining one high-resolution version of a low-resolution image by increasing the number of pixels per unit area. This method has been actively investigated by the research community,…

Learning robust and effective representations of visual data is a fundamental task in computer vision. Traditionally, this is achieved by training models with labeled data which can be expensive to obtain. Self-supervised learning attempts…

Despite the extensive literature on training loss functions, the evaluation of generalization on the validation set remains underexplored. In this work, we conduct a systematic empirical and statistical study of how the validation criterion…

Single-image super-resolution (SISR) is an important task in image processing, which aims to enhance the resolution of imaging systems. Recently, SISR has made a huge leap and has achieved promising results with the help of deep learning…

In recent years, attention mechanisms have been exploited in single image super-resolution (SISR), achieving impressive reconstruction results. However, these advancements are still limited by the reliance on simple training strategies and…

Masked Autoregressive (MAR) models promise better efficiency in visual generation than autoregressive (AR) models for the ability of parallel generation, yet their acceleration potential remains constrained by the modeling complexity of…

Recent advances in Image Restoration (IR) have been largely driven by generative methods such as Diffusion Models and Flow Matching, which excel in synthesizing realistic textures while suffering from slow multi-step inference and…

Seismic data frequently exhibits missing traces, substantially affecting subsequent seismic processing and interpretation. Deep learning-based approaches have demonstrated significant advancements in reconstructing irregularly missing…

Recent advances in large pretrained text-to-image models have shown unprecedented capabilities for high-quality human-centric generation, however, customizing face identity is still an intractable problem. Existing methods cannot ensure…

In this work, we investigate the application of deep learning methods for computed tomography in the context of having a low-data regime. As motivation, we review some of the existing approaches and obtain quantitative results after…

In this work, we propose Prologue, an approach to bridging the reconstruction-generation gap in autoregressive (AR) image generation. Instead of modifying visual tokens to satisfy both reconstruction and generation, Prologue generates a…

Our examination of existing deep generative models (DGMs), including VAEs and GANs, reveals two problems. First, their capability in handling discrete observations and latent codes is unsatisfactory, though there are interesting efforts.…

The rapid advancement of generative models has introduced serious risks, including deepfake techniques for facial synthesis and editing. Traditional approaches rely on training classifiers and enhancing generalizability through various…

Accelerated 3D late gadolinium enhancement (LGE) MRI requires robust reconstruction methods to recover thin atrial structures from undersampled k-space data. While unrolled model-based networks effectively integrate physics-driven data…

Automatic radiology report generation is essential to computer-aided diagnosis. Through the success of image captioning, medical report generation has been achievable. However, the lack of annotated disease labels is still the bottleneck of…

State-of-the-art lidar-based 3D object detection methods rely on supervised learning and large labeled datasets. However, annotating lidar data is resource-consuming, and depending only on supervised learning limits the applicability of…

The ability to automatically estimate the quality and coverage of the samples produced by a generative model is a vital requirement for driving algorithm research. We present an evaluation metric that can separately and reliably measure…