paper-with-me

홈 › Papers

Hadaptive-Net: Efficient Vision Models via Adaptive Cross-Hadamard Synergy

2025-05-28 · Xuyang Zhang, Xi Zhang, Liang Chen, Hao Shi, Qingshan Guo

Recent studies have revealed the immense potential of Hadamard product in enhancing network representational capacity and dimensional compression. However, despite its theoretical promise, this technique has not been systematically explored or effectively applied in practice, leaving its full capabilities underdeveloped. In this work, we first analyze and identify the advantages of Hadamard product over standard convolutional operations in cross-channel interaction and channel expansion. Building upon these insights, we propose a computationally efficient module: Adaptive Cross-Hadamard (ACH), which leverages adaptive cross-channel Hadamard products for high-dimensional channel expansion. Furthermore, we introduce Hadaptive-Net (Hadamard Adaptive Network), a lightweight network backbone for visual tasks, which is demonstrated through experiments that it achieves an unprecedented balance between inference speed and accuracy through our proposed module.

📄 PDF Abstract BibTeX arXiv:2505.22226

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…

Similar Papers 제목 키워드 기반

Arbitrary-Shaped Text Detection withAdaptive Text Region Representation

2021-04-01 · Xiufeng Jiang, Shugong Xu, Shunqing Zhang, Shan Cao

Text detection/localization, as an important task in computer vision, has witnessed substantialadvancements in methodology and performance with convolutional neural networks. However, the vastmajority of popular methods …

Text Detection

Synergy and Diversity in CLIP: Enhancing Performance Through Adaptive Backbone Ensembling

2024-05-27 · Cristian Rodriguez-Opazo, Ehsan Abbasnejad, Damien Teney, Edison Marrese-Taylor 외

Contrastive Language-Image Pretraining (CLIP) stands out as a prominent method for image representation learning. Various architectures, from vision transformers (ViTs) to convolutional networks (ResNets) have been train…

DiversityRepresentation Learning

HARP: Hadamard-Preconditioned Adaptive Rotation Processor for Extreme LLM Quantization

2026-05-28 · Artur Zagitov, Gleb Molodtsov, Aleksandr Beznosikov arxiv

Post-training quantization (PTQ) is essential for deploying LLMs under memory and bandwidth constraints. However, extreme low-bit quantization remains highly sensitive to activation outliers and anisotropic weight curvat…

Modeling Cross-vision Synergy for Unified Large Vision Model

2026-03-03 · Shengqiong Wu, Lanhu Wu, Mingyang Bao, Wenhao Xu 외 arxiv

Recent advances in large vision models (LVMs) have shifted from modality-specific designs toward unified architectures that jointly process images, videos, and 3D data. However, existing unified LVMs primarily pursue fun…

Knowledge DistillationVisual Reasoning

AdaHOP: Fast and Accurate Low-Precision Training via Outlier-Pattern-Aware Rotation

2026-04-02 · Seonggon Kim, Alireza Khodamoradi, Pranathi Vasireddy, Kristof Denolf 외 arxiv

Hadamard transforms have become a key tool for stabilizing low-precision training, but existing methods apply them uniformly across tensors and computation paths. We show that this one-size-fits-all strategy is inherentl…