paper-with-me

Papers

MSP-Former: Multi-Scale Projection Transformer for Single Image Desnowing

2022-07-12 · Sixiang Chen, Tian Ye, Yun Liu, Taodong Liao, Jingxia Jiang, ErKang Chen, Peng Chen

Snow removal causes challenges due to its characteristic of complex degradations. To this end, targeted treatment of multi-scale snow degradations is critical for the network to learn effective snow removal. In order to handle the diverse scenes, we propose a multi-scale projection transformer (MSP-Former), which understands and covers a variety of snow degradation features in a multi-path manner, and integrates comprehensive scene context information for clean reconstruction via self-attention operation. For the local details of various snow degradations, the local capture module is introduced in parallel to assist in the rebuilding of a clean image. Such design achieves the SOTA performance on three desnowing benchmark datasets while costing the low parameters and computational complexity, providing a guarantee of practicality.

📄 PDF Abstract BibTeX arXiv:2207.05621

Code (0)

등록된 구현이 없습니다.

Tasks

Image RestorationSingle Image DesnowingSnow RemovalSSIM

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
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 $x$…
Residual Connection 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Vision Transformer The Vision Transformer, or ViT, is a model for image classification that employs a Transformer-like architecture over…

Similar Papers 제목 키워드 기반

Multi-granularity Backprojection Transformer for Remote Sensing Image Super-Resolution

2023-10-19 · Jinglei Hao, Wukai Li, Binglu Wang, Shunzhou Wang 외

Backprojection networks have achieved promising super-resolution performance for nature images but not well be explored in the remote sensing image super-resolution (RSISR) field due to the high computation costs. In thi…

Image ReconstructionImage Super-ResolutionSuper-Resolution

Projection-Free Transformers via Gaussian Kernel Attention

2026-05-04 · Debarshi Kundu, Archisman Ghosh, Swaroop Ghosh, Vasant Honavar arxiv

Self-attention in Transformers is typically implemented as $\mathrm{softmax}(QK^\top/\sqrt{d})V$, where $Q=XW_Q$, $K=XW_K$, and $V=XW_V$ are learned linear projections of the input $X$. We ask whether these learned proje…

FourierQK: Spectral Preprocessing of Query-Key Projections Improves Transformer Attention

2026-07-08 · Athanasios Zeris arxiv

FFT-based spectral preprocessing of learned query-key (Q/K) projections substantially improves transformer attention on character-level language modelling. On TinyShakespeare: a fixed random spectral filter achieves val=…

Language Modelling

ViTransPAD: Video Transformer using convolution and self-attention for Face Presentation Attack Detection

2022-03-03 · Zuheng Ming, Zitong Yu, Musab Al-Ghadi, Muriel Visani 외

Face Presentation Attack Detection (PAD) is an important measure to prevent spoof attacks for face biometric systems. Many works based on Convolution Neural Networks (CNNs) for face PAD formulate the problem as an image-…

Binary ClassificationFace Presentation Attack Detection

Do Transformers Need Three Projections? Systematic Study of QKV Variants

2026-06-01 · Ali Kayyam, Anusha Madan Gopal, M Anthony Lewis arxiv

Transformers have become the standard solution for various AI tasks, with the query, key, and value (QKV) attention formulation playing a central role. However, the individual contribution of these three projections and …