paper-with-me

Papers Spatial Token Mixer

“Spatial Token Mixer” 태그가 달린 논문 4편 · 필터 해제

UniNeXt: Exploring A Unified Architecture for Vision Recognition

2023-04-26 · Fangjian Lin, Jianlong Yuan, Sitong Wu, Fan Wang 외

Vision Transformers have shown great potential in computer vision tasks. Most recent works have focused on elaborating the spatial token mixer for performance gains. However, we observe that a well-designed general archi…

Spatial Token Mixer

CARD: Semantic Segmentation with Efficient Class-Aware Regularized Decoder

2023-01-11 · Ye Huang, Di Kang, Liang Chen, Wenjing Jia 외

Semantic segmentation has recently achieved notable advances by exploiting "class-level" contextual information during learning. However, these approaches simply concatenate class-level information to pixel features to b…

DecoderRepresentation LearningSemantic SegmentationSpatial Token Mixer

Demystify Transformers & Convolutions in Modern Image Deep Networks

2022-11-10 · Xiaowei Hu, Min Shi, Weiyun Wang, Sitong Wu 외

Vision transformers have gained popularity recently, leading to the development of new vision backbones with improved features and consistent performance gains. However, these advancements are not solely attributable to …

Adversarial RobustnessImage Deep NetworksSpatial Token Mixer

WaveMix: A Resource-efficient Neural Network for Image Analysis

2022-05-28 · Pranav Jeevan, Kavitha Viswanathan, Anandu A S, Amit Sethi

We propose a novel neural architecture for computer vision -- WaveMix -- that is resource-efficient and yet generalizable and scalable. While using fewer trainable parameters, GPU RAM, and computations, WaveMix networks …

Efficient Neural NetworkGPUImage ClassificationScene Classification+2
1–4 / 4