paper-with-me

Papers

WeightNet: Revisiting the Design Space of Weight Networks

2020-07-23 · ECCV 2020 8 · Ningning Ma, Xiangyu Zhang, Jiawei Huang, Jian Sun

We present a conceptually simple, flexible and effective framework for weight generating networks. Our approach is general that unifies two current distinct and extremely effective SENet and CondConv into the same framework on weight space. The method, called WeightNet, generalizes the two methods by simply adding one more grouped fully-connected layer to the attention activation layer. We use the WeightNet, composed entirely of (grouped) fully-connected layers, to directly output the convolutional weight. WeightNet is easy and memory-conserving to train, on the kernel space instead of the feature space. Because of the flexibility, our method outperforms existing approaches on both ImageNet and COCO detection tasks, achieving better Accuracy-FLOPs and Accuracy-Parameter trade-offs. The framework on the flexible weight space has the potential to further improve the performance. Code is available at https://github.com/megvii-model/WeightNet.

📄 PDF Abstract BibTeX arXiv:2007.11823

Code (2)

megvii-model/WeightNet 공식 구현
DequanWang/weightnet.pytorch pytorch

Methods 이 논문이 사용한 방법론

Batch Normalization 설명 없음
Kaiming Initialization 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Global Average Pooling Global Average Pooling is a pooling operation designed to replace fully connected layers in classical CNNs. The idea is to generate one feature map for each corresponding…
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Max Pooling Max Pooling is a pooling operation that calculates the maximum value for patches of a feature map, and uses it to create a downsampled (pooled) feature map. It is usually…

Similar Papers 제목 키워드 기반

Med-K2N: Flexible K-to-N Modality Translation for Medical Image Synthesis

2025-10-03 · Feng Yuan, Yifan Gao, Yuehua Ye, Haoyue Li 외 arxiv

Cross-modal medical image synthesis research focuses on reconstructing missing imaging modalities from available ones to support clinical diagnosis. Driven by clinical necessities for flexible modality reconstruction, we…

Revisiting Lightweight Low-Light Image Enhancement: From a YUV Color Space Perspective

2026-01-24 · Hailong Yan, Shice Liu, Xiangtao Zhang, Lujian Yao 외 arxiv

In the current era of mobile internet, Lightweight Low-Light Image Enhancement (L3IE) is critical for mobile devices, which faces a persistent trade-off between visual quality and model compactness. While recent methods …

Low-Light Image Enhancement

Revisiting Transformer Layer Parameterization Through Causal Energy Minimization

2026-05-08 · Jin Xu, Camille Couturier, Victor Rühle, Saravan Rajmohan 외 arxiv

Transformer blocks typically combine multi-head attention (MHA) for token mixing with gated MLPs for token-wise feature transformation, yet many choices in their parameterization remain largely empirical. We introduce Ca…

Revisiting CHAMPAGNE: Sparse Bayesian Learning as Reweighted Sparse Coding

2025-06-25 · Dylan Sechet, Matthieu Kowalski, Samy Mokhtari, Bruno Torrésani

This paper revisits the CHAMPAGNE algorithm within the Sparse Bayesian Learning (SBL) framework and establishes its connection to reweighted sparse coding. We demonstrate that the SBL objective can be reformulated as a r…

Computational Efficiency

Revisiting Hierarchical Text Classification: Inference and Metrics

2024-10-02 · Roman Plaud, Matthieu Labeau, Antoine Saillenfest, Thomas Bonald

Hierarchical text classification (HTC) is the task of assigning labels to a text within a structured space organized as a hierarchy. Recent works treat HTC as a conventional multilabel classification problem, therefore e…

Classificationtext-classificationText Classification