paper-with-me

Papers

SAG-ViT: A Scale-Aware, High-Fidelity Patching Approach with Graph Attention for Vision Transformers

2024-11-14 · Shravan Venkatraman, Jaskaran Singh Walia, Joe Dhanith P R

Vision Transformers (ViTs) have redefined image classification by leveraging self-attention to capture complex patterns and long-range dependencies between image patches. However, a key challenge for ViTs is efficiently incorporating multi-scale feature representations, which is inherent in convolutional neural networks (CNNs) through their hierarchical structure. Graph transformers have made strides in addressing this by leveraging graph-based modeling, but they often lose or insufficiently represent spatial hierarchies, especially since redundant or less relevant areas dilute the image's contextual representation. To bridge this gap, we propose SAG-ViT, a Scale-Aware Graph Attention ViT that integrates multi-scale feature capabilities of CNNs, representational power of ViTs, graph-attended patching to enable richer contextual representation. Using EfficientNetV2 as a backbone, the model extracts multi-scale feature maps, dividing them into patches to preserve richer semantic information compared to directly patching the input images. The patches are structured into a graph using spatial and feature similarities, where a Graph Attention Network (GAT) refines the node embeddings. This refined graph representation is then processed by a Transformer encoder, capturing long-range dependencies and complex interactions. We evaluate SAG-ViT on benchmark datasets across various domains, validating its effectiveness in advancing image classification tasks. Our code and weights are available at https://github.com/shravan-18/SAG-ViT.

📄 PDF Abstract BibTeX arXiv:2411.09420

Code (1)

shravan-18/SAG-ViT 공식 구현 pytorch

Tasks

Graph Attentionimage-classificationImage Classification

Methods 이 논문이 사용한 방법론

Attention 설명 없음
EfficientNetV2 EfficientNetV2 is a type convolutional neural network that has faster training speed and better parameter efficiency than [previous…
Patching Activation patching studies the model's computation by altering its latent representations, the token embeddings in transformer-based language models, during the inference process
Sigmoid Activation 설명 없음
Depthwise Convolution Depthwise Convolution is a type of convolution where we apply a single convolutional filter for each input channel. In the regular 2D…
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…
(FiLe@Against@Claim)How do I file a claim against Expedia? How do I file a claim against Expedia? How Do I File a Claim Against Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Fast Help &…
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…

Similar Papers 제목 키워드 기반

TimeSqueeze: Dynamic Patching for Efficient Time Series Forecasting

2026-03-11 · Sravan Kumar Ankireddy, Nikita Seleznev, Nam H. Nguyen, Yulun Wu 외 arxiv

Transformer-based time series foundation models face a fundamental trade-off in choice of tokenization: point-wise embeddings preserve temporal fidelity but scale poorly with sequence length, whereas fixed-length patchin…

Time Series Forecasting

Context-aware taxi dispatching at city-scale using deep reinforcement learning

2021-05-26 · IEEE Transactions on Intelligent Transportation Systems 2021 5 · Zhidan Liu, Jiangzhou Li, and Kaishun Wu, Member 외

Abstract— Proactive taxi dispatching is of great importance to balance taxi demand-supply gaps among different locations in a city. Recent advances primarily rely on deep reinforcement learning (DRL) to directly learn…

Action GenerationDeep Reinforcement Learningreinforcement-learningReinforcement Learning (RL)

Efficient Large-Scale Traffic Forecasting with Transformers: A Spatial Data Management Perspective

2024-12-13 · Yuchen Fang, Yuxuan Liang, Bo Hui, Zezhi Shao 외

Road traffic forecasting is crucial in real-world intelligent transportation scenarios like traffic dispatching and path planning in city management and personal traveling. Spatio-temporal graph neural networks (STGNNs) …

ManagementTraffic Prediction

A General “Power-of-d” Dispatching Framework for Heterogeneous Systems

2021-10-20 · Anonymous

Intelligent dispatching is crucial to obtaining low response times in large-scale systems. One common scalable dispatching paradigm is the “power-of-d,” in which the dispatcher queries d servers at…

SEMIR: Topology-Preserving Graph Minors for Thin-Structure Segmentation

2026-06-22 · Luke James Miller, Yugyung Lee arxiv

Thin-structure segmentation--power lines, cracks, lane markings at 1-3 pixel width--requires preserving connectivity that standard representations preclude: patching severs continuous structures and conventional superpix…