Related papers: Training-Free Model Ensemble for Single-Image Supe…

Multi-frame depth estimation improves over single-frame approaches by also leveraging geometric relationships between images via feature matching, in addition to learning appearance-based features. In this paper we revisit feature matching…

Efficiency of gradient propagation in intermediate layers of convolutional neural networks is of key importance for super-resolution task. To this end, we propose a deep architecture for single image super-resolution (SISR), which is built…

The precise reconstruction of 3D objects from a single RGB image in complex scenes presents a critical challenge in virtual reality, autonomous driving, and robotics. Existing neural implicit 3D representation methods face significant…

This paper proposes a deep neural network structure that exploits edge information in addressing representative low-level vision tasks such as layer separation and image filtering. Unlike most other deep learning strategies applied in this…

Integrated Computational Materials Engineering (ICME) aims to accelerate optimal design of complex material systems by integrating material science and design automation. For tractable ICME, it is required that (1) a structural feature…

In this paper, we propose a novel ensembling technique for deep neural networks, which is able to drastically reduce the required memory compared to alternative approaches. In particular, we propose to extract multiple sub-networks from a…

Background: High-resolution MRI is critical for diagnosis, but long acquisition times limit clinical use. Super-resolution (SR) can enhance resolution post-scan, yet existing deep learning methods face fidelity-efficiency trade-offs.…

High-quality whole-slide scanning is expensive, complex, and time-consuming, thus limiting the acquisition and utilization of high-resolution histopathology images in daily clinical work. Deep learning-based single-image super-resolution…

Single-model ensembles (SMEs) have attracted attention as a way to approximate some of the benefits of deep ensembles within a single network. However, under an approximately matched parameter budget, it remains unclear whether model…

Multi-modal image segmentation faces real-world deployment challenges from incomplete/corrupted modalities degrading performance. While existing methods address training-inference modality gaps via specialized per-combination models, they…

Image-based learning methods for autonomous vehicle perception tasks require large quantities of labelled, real data in order to properly train without overfitting, which can often be incredibly costly. While leveraging the power of…

Existing instruction-based image editing models perform well with simple, single-step instructions but degrade in realistic scenarios that involve multiple, lengthy, and interdependent directives. A main cause is the scarcity of training…

Window-based transformers have demonstrated outstanding performance in super-resolution tasks due to their adaptive modeling capabilities through local self-attention (SA). However, they exhibit higher computational complexity and inference…

Ensembling has proven to be a powerful technique for boosting model performance, uncertainty estimation, and robustness in supervised learning. Advances in self-supervised learning (SSL) enable leveraging large unlabeled corpora for…

The evolution of quantization and mixed-precision techniques has unlocked new possibilities for enhancing the speed and energy efficiency of NNs. Several recent studies indicate that adapting precision levels across different parameters can…

Weak spectral responses in hyperspectral images are often obscured by dominant endmembers and sensor noise, resulting in inaccurate abundance estimation. This paper introduces WS-Net, a deep unmixing framework specifically designed to…

We develop a novel transfer learning framework to tackle the challenge of limited training data in image reconstruction problems. The proposed framework consists of two training steps, both of which are formed as bi-level optimizations. In…

Self-supervised vision-language pretraining from pure images and text with a contrastive loss is effective, but ignores fine-grained alignment due to a dual-stream architecture that aligns image and text representations only on a global…

Modern deep learning usually treats models as separate artifacts: trained independently, specialized for particular purposes, and replaced when improved versions appear. This thesis studies model merging as an alternative paradigm:…

Hyperspectral single image super-resolution (SISR) aims to enhance spatial resolution while preserving the rich spectral information of hyperspectral images. Most existing methods rely on supervised learning with high-resolution ground…