paper-with-me

Papers

A Practical Gated Recurrent Transformer Network Incorporating Multiple Fusions for Video Denoising

2024-09-10 · Kai Guo, Seungwon Choi, Jongseong Choi, Lae-Hoon Kim

State-of-the-art (SOTA) video denoising methods employ multi-frame simultaneous denoising mechanisms, resulting in significant delays (e.g., 16 frames), making them impractical for real-time cameras. To overcome this limitation, we propose a multi-fusion gated recurrent Transformer network (GRTN) that achieves SOTA denoising performance with only a single-frame delay. Specifically, the spatial denoising module extracts features from the current frame, while the reset gate selects relevant information from the previous frame and fuses it with current frame features via the temporal denoising module. The update gate then further blends this result with the previous frame features, and the reconstruction module integrates it with the current frame. To robustly compute attention for noisy features, we propose a residual simplified Swin Transformer with Euclidean distance (RSSTE) in the spatial and temporal denoising modules. Comparative objective and subjective results show that our GRTN achieves denoising performance comparable to SOTA multi-frame delay networks, with only a single-frame delay.

📄 PDF Abstract BibTeX arXiv:2409.06603

Code (0)

등록된 구현이 없습니다.

Tasks

DenoisingVideo Denoising

Methods 이 논문이 사용한 방법론

Attention 설명 없음
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
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 $x$…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Position-Wise Feed-Forward Layer 설명 없음

Similar Papers 제목 키워드 기반

Recurrent Graph Transformer Network for Multiple Fault Localization in Naval Shipboard Systems

2024-09-16 · Quang-Ha Ngo, Isabel Barnola, Tuyen Vu, Jianhua Zhang 외

The integration of power electronics building blocks in modern MVDC 12kV Naval ship systems enhances energy management and functionality but also introduces complex fault detection and control challenges. These challenge…

Diagnosticenergy managementFault DetectionFault Diagnosis+3

Gated Slot Attention for Efficient Linear-Time Sequence Modeling

2024-09-11 · Yu Zhang, Songlin Yang, Ruijie Zhu, Yue Zhang 외

Linear attention Transformers and their gated variants, celebrated for enabling parallel training and efficient recurrent inference, still fall short in recall-intensive tasks compared to traditional Transformers and dem…

Universal In-Context Approximation By Prompting Fully Recurrent Models

2024-06-03 · Aleksandar Petrov, Tom A. Lamb, Alasdair Paren, Philip H. S. Torr 외

Zero-shot and in-context learning enable solving tasks without model fine-tuning, making them essential for developing generative model solutions. Therefore, it is crucial to understand whether a pretrained model can be …

In-Context LearningMamba

Liger: Linearizing Large Language Models to Gated Recurrent Structures

2025-03-03 · Disen Lan, Weigao Sun, Jiaxi Hu, Jusen Du 외

Transformers with linear recurrent modeling offer linear-time training and constant-memory inference. Despite their demonstrated efficiency and performance, pretraining such non-standard architectures from scratch remain…

Gated recurrent units and temporal convolutional network for multilabel classification

2021-10-09 · Loris Nanni, Alessandra Lumini, Alessandro Manfe, Riccardo Rampon 외

Multilabel learning tackles the problem of associating a sample with multiple class labels. This work proposes a new ensemble method for managing multilabel classification: the core of the proposed approach combines a se…

Classification