English
Related papers

Related papers: Faster ISNet for Background Bias Mitigation on Dee…

200 papers

The paper systematically studies the impact of a range of recent advances in CNN architectures and learning methods on the object categorization (ILSVRC) problem. The evalution tests the influence of the following choices of the…

Neural and Evolutionary Computing · Computer Science 2017-06-02 Dmytro Mishkin , Nikolay Sergievskiy , Jiri Matas

Deep image prior (DIP) is a recently proposed technique for solving imaging inverse problems by fitting the reconstructed images to the output of an untrained convolutional neural network. Unlike pretrained feedforward neural networks, the…

Computer Vision and Pattern Recognition · Computer Science 2022-09-20 Kevin Zhang , Mingyang Xie , Maharshi Gor , Yi-Ting Chen , Yvonne Zhou , Christopher A. Metzler

End-to-end autonomous driving has emerged as a dominant paradigm, yet its highly entangled black-box models pose significant challenges in terms of interpretability and safety assurance. To improve model transparency and training…

Computer Vision and Pattern Recognition · Computer Science 2025-06-10 Ni Ding , Lei He , Shengbo Eben Li , Keqiang Li

Neural Radiance Fields (NeRF) have become an increasingly popular representation to capture high-quality appearance and shape of scenes and objects. However, learning generalizable NeRF priors over categories of scenes or objects has been…

Computer Vision and Pattern Recognition · Computer Science 2023-12-27 Bipasha Sen , Gaurav Singh , Aditya Agarwal , Rohith Agaram , K Madhava Krishna , Srinath Sridhar

The Residual Network (ResNet), proposed in He et al. (2015), utilized shortcut connections to significantly reduce the difficulty of training, which resulted in great performance boosts in terms of both training and generalization error. It…

Neural and Evolutionary Computing · Computer Science 2017-05-23 Sihan Li , Jiantao Jiao , Yanjun Han , Tsachy Weissman

Implicit Neural Representations (INRs) parameterize continuous signals via multilayer perceptrons (MLPs), enabling compact, resolution-independent modeling for tasks like image, audio, and 3D reconstruction. However, fitting high-resolution…

Machine Learning · Computer Science 2026-02-26 Chen Zhang , Wei Zuo , Bingyang Cheng , Yikun Wang , Wei-Bin Kou , Yik Chung WU , Ngai Wong

We implement a visual interpretability method Layer-wise Relevance Propagation (LRP) on top of 3D U-Net trained to perform lesion segmentation on the small dataset of multi-modal images provided by ISLES 2017 competition. We demonstrate…

Image and Video Processing · Electrical Eng. & Systems 2020-01-14 Erico Tjoa , Guo Heng , Lu Yuhao , Cuntai Guan

Neural Radiance Fields (NeRF) has gained significant attention for its prominent implicit 3D representation and realistic novel view synthesis capabilities. Available works unexceptionally employ straight-line volume rendering, which…

Graphics · Computer Science 2025-08-20 Nan Luo , Chenglin Ye , Jiaxu Li , Gang Liu , Bo Wan , Di Wang , Lupeng Liu , Jun Xiao

MR imaging techniques are of great benefit to disease diagnosis. However, due to the limitation of MR devices, significant intensity inhomogeneity often exists in imaging results, which impedes both qualitative and quantitative medical…

Image and Video Processing · Electrical Eng. & Systems 2025-07-03 Dong Liang , Xingyu Qiu , Yuzhen Li , Wei Wang , Kuanquan Wang , Suyu Dong , Gongning Luo

Deep deraining networks consistently encounter substantial generalization issues when deployed in real-world applications, although they are successful in laboratory benchmarks. A prevailing perspective in deep learning encourages using…

Computer Vision and Pattern Recognition · Computer Science 2023-10-27 Jinjin Gu , Xianzheng Ma , Xiangtao Kong , Yu Qiao , Chao Dong

Dataset bias and spurious correlations can significantly impair generalization in deep neural networks. Many prior efforts have addressed this problem using either alternative loss functions or sampling strategies that focus on rare…

Machine Learning · Computer Science 2024-04-16 Robik Shrestha , Kushal Kafle , Christopher Kanan

Adaptive learning rate algorithms such as RMSProp are widely used for training deep neural networks. RMSProp offers efficient training since it uses first order gradients to approximate Hessian-based preconditioning. However, since the…

Machine Learning · Computer Science 2017-09-29 Yasutoshi Ida , Yasuhiro Fujiwara , Sotetsu Iwamura

In deep learning, it is common to use more network parameters than training points. In such scenarioof over-parameterization, there are usually multiple networks that achieve zero training error so that thetraining algorithm induces an…

Machine Learning · Computer Science 2023-08-22 Hung-Hsu Chou , Carsten Gieshoff , Johannes Maly , Holger Rauhut

Within the last decade, neural network based predictors have demonstrated impressive - and at times super-human - capabilities. This performance is often paid for with an intransparent prediction process and thus has sparked numerous…

Stochastic gradient descent with a large initial learning rate is widely used for training modern neural net architectures. Although a small initial learning rate allows for faster training and better test performance initially, the large…

Machine Learning · Computer Science 2020-04-28 Yuanzhi Li , Colin Wei , Tengyu Ma

For computer vision applications, prior works have shown the efficacy of reducing the numeric precision of model parameters (network weights) in deep neural networks but also that reducing the precision of activations hurts model accuracy…

Machine Learning · Computer Science 2017-04-12 Asit Mishra , Jeffrey J Cook , Eriko Nurvitadhi , Debbie Marr

Curriculum Learning emphasizes the order of training instances in a computational learning setup. The core hypothesis is that simpler instances should be learned early as building blocks to learn more complex ones. Despite its usefulness,…

Computation and Language · Computer Science 2016-11-21 Volkan Cirik , Eduard Hovy , Louis-Philippe Morency

Back-propagation is a popular machine learning algorithm that uses gradient descent in training neural networks for supervised learning, but can be very slow. A number of algorithms have been developed to speed up convergence and improve…

Neural and Evolutionary Computing · Computer Science 2020-09-29 Ho Ling Li

The phenomenon of implicit regularization has attracted interest in recent years as a fundamental aspect of the remarkable generalizing ability of neural networks. In a nutshell, it entails that gradient descent dynamics in many neural…

Machine Learning · Computer Science 2024-02-28 Hong T. M. Chu , Subhro Ghosh , Chi Thanh Lam , Soumendu Sundar Mukherjee

A widely believed explanation for the remarkable generalization capacities of overparameterized neural networks is that the optimization algorithms used for training induce an implicit bias towards benign solutions. To grasp this…

Machine Learning · Computer Science 2025-12-19 Maria Matveev , Vit Fojtik , Hung-Hsu Chou , Gitta Kutyniok , Johannes Maly