English
Related papers

Related papers: Activation-Free Backbones for Image Recognition: P…

200 papers

Hybrid private inference (PI) protocol, which synergistically utilizes both multi-party computation (MPC) and homomorphic encryption, is one of the most prominent techniques for PI. However, even the state-of-the-art PI protocols are…

Cryptography and Security · Computer Science 2022-02-21 Jaiyoung Park , Michael Jaemin Kim , Wonkyung Jung , Jung Ho Ahn

SegBlocks reduces the computational cost of existing neural networks, by dynamically adjusting the processing resolution of image regions based on their complexity. Our method splits an image into blocks and downsamples blocks of low…

Computer Vision and Pattern Recognition · Computer Science 2022-08-08 Thomas Verelst , Tinne Tuytelaars

All-optical neural networks (AONNs) promise transformative gains in speed and energy efficiency for artificial intelligence (AI) by leveraging the intrinsic parallelism and wave nature of light. However, their scalability has been…

Optics · Physics 2025-12-09 Ruben Canora , Xinzhe Xu , Ziqi Niu , Hadiseh Alaeian , Shengwang Du

In this paper, we introduce the Hyperbolic Tangent Exponential Linear Unit (TeLU), a novel neural network activation function, represented as $f(x) = x{\cdot}tanh(e^x)$. TeLU is designed to overcome the limitations of conventional…

Machine Learning · Computer Science 2024-02-06 Alfredo Fernandez , Ankur Mali

We present polynomial time and sample efficient algorithms for learning an unknown depth-2 feedforward neural network with general ReLU activations, under mild non-degeneracy assumptions. In particular, we consider learning an unknown…

Machine Learning · Computer Science 2021-08-03 Pranjal Awasthi , Alex Tang , Aravindan Vijayaraghavan

Recent work has shown that purely quadratic functions can replace MLPs in transformers with no significant loss in performance, while enabling new methods of interpretability based on linear algebra. In this work, we theoretically derive…

Machine Learning · Computer Science 2025-02-04 Nora Belrose , Alice Rigg

Multimodal Transformers serve as the backbone for state-of-the-art vision-language models, yet their quadratic attention complexity remains a critical barrier to scalability. In this work, we investigate the viability of Linear Attention…

Computer Vision and Pattern Recognition · Computer Science 2026-04-14 Armin Gerami , Seyedehanita Madani , Ramani Duraiswami

Transformer-based low-light enhancement methods have yielded promising performance by effectively capturing long-range dependencies in a global context. However, their elevated computational demand limits the scalability of multiple…

Computer Vision and Pattern Recognition · Computer Science 2024-06-04 Xuanqi Zhang , Haijin Zeng , Jinwang Pan , Qiangqiang Shen , Yongyong Chen

Recently, MLP-based vision backbones have achieved promising performance in several visual recognition tasks. However, the existing MLP-based methods directly aggregate tokens with static weights, leaving the adaptability to different…

Computer Vision and Pattern Recognition · Computer Science 2023-09-18 Zhiqiang Hu , Tao Yu

Previous deep image registration methods that employ single homography, multi-grid homography, or thin-plate spline often struggle with real scenes containing depth disparities due to their inherent limitations. To address this, we propose…

Computer Vision and Pattern Recognition · Computer Science 2025-09-10 Haokai Zhu , Bo Qu , Si-Yuan Cao , Runmin Zhang , Shujie Chen , Bailin Yang , Hui-Liang Shen

Convolution and transposed convolution are fundamental operators widely used in neural networks. However, transposed convolution (a.k.a. deconvolution) does not serve as a true inverse of convolution due to inherent differences in their…

Computer Vision and Pattern Recognition · Computer Science 2025-08-18 Xuhong Huang , Shiqi Liu , Kai Zhang , Ying Tai , Jian Yang , Hui Zeng , Lei Zhang

The distinction between genuine and posed emotions represents a fundamental pattern recognition challenge with significant implications for data mining applications in social sciences, healthcare, and human-computer interaction. While…

Computer Vision and Pattern Recognition · Computer Science 2025-09-24 Mohammad Junayed Hasan , Nabeel Mohammed , Shafin Rahman , Philipp Koehn

Activation function is crucial to the recent successes of deep neural networks. In this paper, we first propose a new activation function, Multiple Parametric Exponential Linear Units (MPELU), aiming to generalize and unify the rectified…

Computer Vision and Pattern Recognition · Computer Science 2017-01-18 Yang Li , Chunxiao Fan , Yong Li , Qiong Wu , Yue Ming

The quadratic computation complexity of self-attention has been a persistent challenge when applying Transformer models to vision tasks. Linear attention, on the other hand, offers a much more efficient alternative with its linear…

Computer Vision and Pattern Recognition · Computer Science 2023-09-04 Dongchen Han , Xuran Pan , Yizeng Han , Shiji Song , Gao Huang

Nonlinear activation functions are widely recognized for enhancing the expressivity of neural networks, which is the primary reason for their widespread implementation. In this work, we focus on ReLU activation and reveal a novel and…

Machine Learning · Computer Science 2025-10-22 Chaoyue Liu , Han Bi , Like Hui , Xiao Liu

While MLLMs perform well on perceptual tasks, they lack precise multimodal alignment, limiting performance. To address this challenge, we propose Vision Dynamic Embedding-Guided Pretraining (VDEP), a hybrid autoregressive training paradigm…

Computer Vision and Pattern Recognition · Computer Science 2025-02-14 Mingxiao Li , Fang Qu , Zhanpeng Chen , Na Su , Zhizhou Zhong , Ziyang Chen , Nan Du , Xiaolong Li

Convolutional neural networks (CNNs) have been the de facto standard in a diverse set of computer vision tasks for many years. Especially, deep neural networks based on seminal architectures such as U-shaped models with skip-connections or…

Image and Video Processing · Electrical Eng. & Systems 2022-08-02 Reza Azad , Moein Heidari , Moein Shariatnia , Ehsan Khodapanah Aghdam , Sanaz Karimijafarbigloo , Ehsan Adeli , Dorit Merhof

The efficacy of deep neural networks is heavily reliant on the design of non-linear activation functions, yet existing approaches often struggle to balance optimization stability with computational efficiency. While piecewise linear…

Artificial Intelligence · Computer Science 2026-05-05 Wentao Zhang , Yutong Zhang , Yifan Zhu , Wentao Mo

We develop exact representations of training two-layer neural networks with rectified linear units (ReLUs) in terms of a single convex program with number of variables polynomial in the number of training samples and the number of hidden…

Machine Learning · Computer Science 2020-08-18 Mert Pilanci , Tolga Ergen

We introduce a framework for designing multi-scale, adaptive, shift-invariant frames and bi-frames for representing signals. The new framework, called AdaFrame, improves over dictionary learning-based techniques in terms of computational…

Computer Vision and Pattern Recognition · Computer Science 2015-07-20 Cheng Tai , Weinan E
‹ Prev 1 4 5 6 7 8 10 Next ›