Related papers: Deep Model Reassembly
Exploring the transferability between heterogeneous tasks sheds light on their intrinsic interconnections, and consequently enables knowledge transfer from one task to another so as to reduce the training effort of the latter. In this…
Depth completion, which aims to generate high-quality dense depth maps from sparse depth maps, has attracted increasing attention in recent years. Previous work usually employs RGB images as guidance, and introduces iterative spatial…
Imaging Cherenkov detectors are largely used for particle identification (PID) in nuclear and particle physics experiments, where developing fast reconstruction algorithms is becoming of paramount importance to allow for near real time…
Traditional machine learning approaches may fail to perform satisfactorily when dealing with complex data. In this context, the importance of data mining evolves w.r.t. building an efficient knowledge discovery and mining framework.…
Purpose: To develop a deep-learning-based image reconstruction framework for reproducible research in MRI. Methods: The BART toolbox offers a rich set of implementations of calibration and reconstruction algorithms for parallel imaging and…
Model merging enables the reuse of fine-tuned models without joint training or access to original data. Dynamic merging further improves flexibility by selectively activating task-relevant parameters and efficiently composing experts across…
Deep convolutional neural networks (CNNs) have obtained remarkable performance in single image super-resolution (SISR). However, very deep networks can suffer from training difficulty and hardly achieve further performance gain. There are…
Scaling network depth has been a central driver behind the success of modern foundation models, yet recent investigations suggest that deep layers are often underutilized. This paper revisits the default mechanism for deepening neural…
Mix-based augmentation has been proven fundamental to the generalization of deep vision models. However, current augmentations only mix samples at the current data batch during training, which ignores the possible knowledge accumulated in…
Models based on convolutional neural networks (CNN) and transformers have steadily been improved. They also have been applied in various computer vision downstream tasks. However, in object detection tasks, accurately localizing and…
Based on its great successes in inference and denosing tasks, Dictionary Learning (DL) and its related sparse optimization formulations have garnered a lot of research interest. While most solutions have focused on single layer…
We introduce a model-based image reconstruction framework with a convolution neural network (CNN) based regularization prior. The proposed formulation provides a systematic approach for deriving deep architectures for inverse problems with…
Neural network based models have achieved impressive results on various specific tasks. However, in previous works, most models are learned separately based on single-task supervised objectives, which often suffer from insufficient training…
Frameworks for writing, compiling, and optimizing deep learning (DL) models have recently enabled progress in areas like computer vision and natural language processing. Extending these frameworks to accommodate the rapidly diversifying…
Reassembly tasks play a fundamental role in many fields and multiple approaches exist to solve specific reassembly problems. In this context, we posit that a general unified model can effectively address them all, irrespective of the input…
This paper proposes a novel approach to person re-identification, a fundamental task in distributed multi-camera surveillance systems. Although a variety of powerful algorithms have been presented in the past few years, most of them usually…
Deep convolutional neural networks (DCNN) have been widely adopted for research on super resolution recently, however previous work focused mainly on stacking as many layers as possible in their model, in this paper, we present a new…
Deep learning (DL) methods have achieved state-of-the-art performance in the task of single image rain removal. Most of current DL architectures, however, are still lack of sufficient interpretability and not fully integrated with physical…
Although deep networks have recently emerged as the model of choice for many computer vision problems, in order to yield good results they often require time-consuming architecture search. To combat the complexity of design choices, prior…
Deepfake generators evolve quickly, making exhaustive data collection and repeated retraining impractical. We argue that model merging is a natural fit for deepfake detection: unlike generic multi-task settings with disjoint labels,…