English
Related papers

Related papers: RefConv: Re-parameterized Refocusing Convolution f…

200 papers

Feed-forward convolutional neural networks (CNNs) are currently state-of-the-art for object classification tasks such as ImageNet. Further, they are quantitatively accurate models of temporally-averaged responses of neurons in the primate…

Neurons and Cognition · Quantitative Biology 2018-10-30 Aran Nayebi , Daniel Bear , Jonas Kubilius , Kohitij Kar , Surya Ganguli , David Sussillo , James J. DiCarlo , Daniel L. K. Yamins

Video frame interpolation involves the synthesis of new frames from existing ones. Convolutional neural networks (CNNs) have been at the forefront of the recent advances in this field. One popular CNN-based approach involves the application…

Computer Vision and Pattern Recognition · Computer Science 2022-05-16 Issa Khalifeh , Marc Gorriz Blanch , Ebroul Izquierdo , Marta Mrak

In this paper, we are committed to establishing an unified and end-to-end multi-modal network via exploring the language-guided visual recognition. To approach this target, we first propose a novel multi-modal convolution module called…

Computer Vision and Pattern Recognition · Computer Science 2023-09-15 Gen Luo , Yiyi Zhou , Xiaoshuai Sun , Yongjian Wu , Yue Gao , Rongrong Ji

Single domain generalization aims to train a generalizable model with only one source domain to perform well on arbitrary unseen target domains. Image augmentation based on Random Convolutions (RandConv), consisting of one convolution layer…

Computer Vision and Pattern Recognition · Computer Science 2023-04-04 Seokeon Choi , Debasmit Das , Sungha Choi , Seunghan Yang , Hyunsin Park , Sungrack Yun

While convolutional neural networks (CNNs) excel at clean image classification, they struggle to classify images corrupted with different common corruptions, limiting their real-world applicability. Recent work has shown that incorporating…

Computer Vision and Pattern Recognition · Computer Science 2024-10-15 Lucas Piper , Arlindo L. Oliveira , Tiago Marques

Over-fitting-based image compression requires weights compactness for compression and fast convergence for practical use, posing challenges for deep convolutional neural networks (CNNs) based methods. This paper presents a simple…

Image and Video Processing · Electrical Eng. & Systems 2023-10-13 Yun Ye , Yanjie Pan , Qually Jiang , Ming Lu , Xiaoran Fang , Beryl Xu

Referring image segmentation is an advanced semantic segmentation task where target is not a predefined class but is described in natural language. Most of existing methods for this task rely heavily on convolutional neural networks, which…

Computer Vision and Pattern Recognition · Computer Science 2022-04-01 Namyup Kim , Dongwon Kim , Cuiling Lan , Wenjun Zeng , Suha Kwak

Hyperparameters tuning is a time-consuming approach, particularly when the architecture of the neural network is decided as part of this process. For instance, in convolutional neural networks (CNNs), the selection of the number and the…

Machine Learning · Computer Science 2020-07-31 Roberto L. Castro , Diego Andrade , Basilio Fraguela

We describe the class of convexified convolutional neural networks (CCNNs), which capture the parameter sharing of convolutional neural networks in a convex manner. By representing the nonlinear convolutional filters as vectors in a…

Machine Learning · Computer Science 2016-09-06 Yuchen Zhang , Percy Liang , Martin J. Wainwright

This paper presents a new variational inference framework for image restoration and a convolutional neural network (CNN) structure that can solve the restoration problems described by the proposed framework. Earlier CNN-based image…

Image and Video Processing · Electrical Eng. & Systems 2022-07-20 Jae Woong Soh , Nam Ik Cho

Convolutional Neural Networks (ConvNets) are commonly developed at a fixed resource budget, and then scaled up for better accuracy if more resources are available. In this paper, we systematically study model scaling and identify that…

Machine Learning · Computer Science 2020-09-14 Mingxing Tan , Quoc V. Le

Spatial convolution is fundamental in constructing deep Convolutional Neural Networks (CNNs) for visual recognition. While dynamic convolution enhances model accuracy by adaptively combining static kernels, it incurs significant…

Computer Vision and Pattern Recognition · Computer Science 2025-03-25 Tianyu Zhang , Fan Wan , Haoran Duan , Kevin W. Tong , Jingjing Deng , Yang Long

The tradeoff between receptive field size and efficiency is a crucial issue in low level vision. Plain convolutional networks (CNNs) generally enlarge the receptive field at the expense of computational cost. Recently, dilated filtering has…

Computer Vision and Pattern Recognition · Computer Science 2018-05-23 Pengju Liu , Hongzhi Zhang , Kai Zhang , Liang Lin , Wangmeng Zuo

State-of-the-art rehearsal-free continual learning methods exploit the peculiarities of Vision Transformers to learn task-specific prompts, drastically reducing catastrophic forgetting. However, there is a tradeoff between the number of…

Computer Vision and Pattern Recognition · Computer Science 2023-08-21 Thomas De Min , Massimiliano Mancini , Karteek Alahari , Xavier Alameda-Pineda , Elisa Ricci

Filters in a Convolutional Neural Network (CNN) contain model parameters learned from enormous amounts of data. In this paper, we suggest to decompose convolutional filters in CNN as a truncated expansion with pre-fixed bases, namely the…

Machine Learning · Statistics 2018-07-31 Qiang Qiu , Xiuyuan Cheng , Robert Calderbank , Guillermo Sapiro

Image restoration (IR) is a long-standing task to recover a high-quality image from its corrupted observation. Recently, transformer-based algorithms and some attention-based convolutional neural networks (CNNs) have presented promising…

Computer Vision and Pattern Recognition · Computer Science 2025-05-19 Fangwei Hao , Ji Du , Weiyun Liang , Jing Xu , Xiaoxuan Xu

Recent works indicate that convolutional neural networks (CNN) need large receptive fields (RF) to compete with visual transformers and their attention mechanism. In CNNs, RFs can simply be enlarged by increasing the convolution kernel…

Computer Vision and Pattern Recognition · Computer Science 2023-05-12 Ismail Khalfaoui-Hassani , Thomas Pellegrini , Timothée Masquelier

Designing a module or mechanism that enables a network to maintain low parameters and FLOPs without sacrificing accuracy and throughput remains a challenge. To address this challenge and exploit the redundancy within feature map channels,…

Computer Vision and Pattern Recognition · Computer Science 2025-02-04 Haiduo Huang , Tian Xia , Wenzhe zhao , Pengju Ren

Designing an efficient model within the limited computational cost is challenging. We argue the accuracy of a lightweight model has been further limited by the design convention: a stage-wise configuration of the channel dimensions, which…

Computer Vision and Pattern Recognition · Computer Science 2021-06-09 Dongyoon Han , Sangdoo Yun , Byeongho Heo , YoungJoon Yoo

Despite several algorithmic advances in the training of convolutional neural networks (CNNs) over the years, their generalization capabilities are still subpar across several pertinent domains, particularly within open-set tasks often found…

Computer Vision and Pattern Recognition · Computer Science 2025-11-18 Colton R. Crum , Adam Czajka