English
Related papers

Related papers: Deforming the Loss Surface

200 papers

As an integral component of blind image deblurring, non-blind deconvolution removes image blur with a given blur kernel, which is essential but difficult due to the ill-posed nature of the inverse problem. The predominant approach is based…

Computer Vision and Pattern Recognition · Computer Science 2020-02-18 Dong Gong , Zhen Zhang , Qinfeng Shi , Anton van den Hengel , Chunhua Shen , Yanning Zhang

Neural signed distance functions (SDFs) have shown powerful ability in fitting the shape geometry. However, inferring continuous signed distance fields from discrete unoriented point clouds still remains a challenge. The neural network…

Computer Vision and Pattern Recognition · Computer Science 2024-09-11 Shengtao Li , Ge Gao , Yudong Liu , Ming Gu , Yu-Shen Liu

Finding parameters in a deep neural network (NN) that fit training data is a nonconvex optimization problem, but a basic first-order optimization method (gradient descent) finds a global optimizer with perfect fit (zero-loss) in many…

Machine Learning · Computer Science 2025-03-07 Zhiyan Ding , Shi Chen , Qin Li , Stephen Wright

We introduce a neural implicit framework that exploits the differentiable properties of neural networks and the discrete geometry of point-sampled surfaces to approximate them as the level sets of neural implicit functions. To train a…

Graphics · Computer Science 2024-03-07 Tiago Novello , Guilherme Schardong , Luiz Schirmer , Vinicius da Silva , Helio Lopes , Luiz Velho

Deep convolutional networks (CNNs) have exhibited their potential in image inpainting for producing plausible results. However, in most existing methods, e.g., context encoder, the missing parts are predicted by propagating the surrounding…

Computer Vision and Pattern Recognition · Computer Science 2018-04-16 Zhaoyi Yan , Xiaoming Li , Mu Li , Wangmeng Zuo , Shiguang Shan

Implicit neural networks have emerged as a crucial technology in 3D surface reconstruction. To reconstruct continuous surfaces from discrete point clouds, encoding the input points into regular grid features (plane or volume) has been…

Computer Vision and Pattern Recognition · Computer Science 2024-01-05 Shengtao Li , Ge Gao , Yudong Liu , Yu-Shen Liu , Ming Gu

The task of automatically segmenting 3-D surfaces representing boundaries of objects is important for quantitative analysis of volumetric images, and plays a vital role in biomedical image analysis. Recently, graph-based methods with a…

Computer Vision and Pattern Recognition · Computer Science 2018-01-10 Abhay Shah , Michael Abramoff , Xiaodong Wu

While deep learning-based methods for blind face restoration have achieved unprecedented success, they still suffer from two major limitations. First, most of them deteriorate when facing complex degradations out of their training data.…

Computer Vision and Pattern Recognition · Computer Science 2024-07-23 Zongsheng Yue , Chen Change Loy

Solving electromagnetic inverse scattering problems (ISPs) is challenging due to the intrinsic nonlinearity, ill-posedness, and expensive computational cost. Recently, deep neural network (DNN) techniques have been successfully applied on…

Machine Learning · Computer Science 2021-11-18 Zicheng Liu , Mayank Roy , Dilip K. Prasad , Krishna Agarwal

We introduce Neural Deformation Graphs for globally-consistent deformation tracking and 3D reconstruction of non-rigid objects. Specifically, we implicitly model a deformation graph via a deep neural network. This neural deformation graph…

Computer Vision and Pattern Recognition · Computer Science 2020-12-04 Aljaž Božič , Pablo Palafox , Michael Zollhöfer , Justus Thies , Angela Dai , Matthias Nießner

Low-dose CT denoising is a challenging task that has been studied by many researchers. Some studies have used deep neural networks to improve the quality of low-dose CT images and achieved fruitful results. In this paper, we propose a deep…

Image and Video Processing · Electrical Eng. & Systems 2019-02-28 Maryam Gholizadeh-Ansari , Javad Alirezaie , Paul Babyn

In this work, we propose a disentangled latent optimization-based method for parameterizing grouped deforming 3D objects into shape and deformation factors in an unsupervised manner. Our approach involves the joint optimization of a…

Computer Vision and Pattern Recognition · Computer Science 2025-11-11 Mostofa Rafid Uddin , Jana Armouti , Umong Sain , Md Asib Rahman , Xingjian Li , Min Xu

The human visual system excels at detecting local blur of visual images, but the underlying mechanism is not well understood. Traditional views of blur such as reduction in energy at high frequencies and loss of phase coherence at localized…

Computer Vision and Pattern Recognition · Computer Science 2018-06-13 Kede Ma , Huan Fu , Tongliang Liu , Zhou Wang , Dacheng Tao

The cross-entropy softmax loss is the primary loss function used to train deep neural networks. On the other hand, the focal loss function has been demonstrated to provide improved performance when there is an imbalance in the number of…

Computer Vision and Pattern Recognition · Computer Science 2022-06-17 Leslie N. Smith

We develop regularization methods to find flat minima while training deep neural networks. These minima generalize better than sharp minima, yielding models outperforming baselines on real-world test data (which may be distributed…

Machine Learning · Computer Science 2025-07-04 Adam Sandler , Diego Klabjan , Yuan Luo

In deep learning, optimization plays a vital role. By focusing on image classification, this work investigates the pros and cons of the widely used optimizers, and proposes a new optimizer: Perturbated Unit Gradient Descent (PUGD) algorithm…

Machine Learning · Computer Science 2022-11-10 Ching-Hsun. Tseng , Liu-Hsueh. Cheng , Shin-Jye. Lee , Xiaojun Zeng

The choice of a loss function is an important factor when training neural networks for image restoration problems, such as single image super resolution. The loss function should encourage natural and perceptually pleasing results. A…

Image and Video Processing · Electrical Eng. & Systems 2021-10-19 Aamir Mustafa , Aliaksei Mikhailiuk , Dan Andrei Iliescu , Varun Babbar , Rafal K. Mantiuk

We propose a novel fine-tuning method to achieve multi-operator learning through training a distributed neural operator with diverse function data and then zero-shot fine-tuning the neural network using physics-informed losses for…

Machine Learning · Computer Science 2024-11-12 Zecheng Zhang , Christian Moya , Lu Lu , Guang Lin , Hayden Schaeffer

We develop a novel deep contour detection algorithm with a top-down fully convolutional encoder-decoder network. Our proposed method, named TD-CEDN, solves two important issues in this low-level vision problem: (1) learning multi-scale and…

Computer Vision and Pattern Recognition · Computer Science 2017-07-13 Yahui Liu , Jian Yao , Li Li , Xiaohu Lu , Jing Han

It is well known that (stochastic) gradient descent has an implicit bias towards flat minima. In deep neural network training, this mechanism serves to screen out minima. However, the precise effect that this has on the trained network is…

Machine Learning · Computer Science 2020-08-11 Rotem Mulayoff , Tomer Michaeli