paper-with-me

홈 › Papers

Rethinking the Zigzag Flattening for Image Reading

2022-02-21 · Qingsong Zhao, Yi Wang, Zhipeng Zhou, Duoqian Miao, LiMin Wang, Yu Qiao, Cairong Zhao

Sequence ordering of word vector matters a lot to text reading, which has been proven in natural language processing (NLP). However, the rule of different sequence ordering in computer vision (CV) was not well explored, e.g., why the ``zigzag" flattening (ZF) is commonly utilized as a default option to get the image patches ordering in vision networks. Notably, when decomposing multi-scale images, the ZF could not maintain the invariance of feature point positions. To this end, we investigate the Hilbert fractal flattening (HF) as another method for sequence ordering in CV and contrast it against ZF. The HF has proven to be superior to other curves in maintaining spatial locality, when performing multi-scale transformations of dimensional space. And it can be easily plugged into most deep neural networks (DNNs). Extensive experiments demonstrate that it can yield consistent and significant performance boosts for a variety of architectures. Finally, we hope that our studies spark further research about the flattening strategy of image reading.

📄 PDF Abstract BibTeX arXiv:2202.10240

Code (0)

등록된 구현이 없습니다.

Tasks

Image ClassificationRepresentation LearningSemantic Segmentation

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Adam 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
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 $x$…
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…

Similar Papers 제목 키워드 기반

Rethinking Critic Learning in PPO: Understanding and Mitigating Value Flattening

2026-09-16 · Yizhuo Li, Jianhao Yan, Yun Luo, Zhi Wang 외 hf

In reinforcement learning for large language models, Proximal Policy Optimization (PPO) commonly uses a critic to estimate state values and reduce the variance of policy updates. However, we uncover a systematic failure …

Reinforcement Learning

3D zigzag for multislicing, multiband and video processing

2016-06-16 · Mario Mastriani

We present a 3D zigzag rafter (first in literature) which allows us to obtain the exact sequence of spectral components after application of Discrete Cosine Transform 3D (DCT-2D) over a cube. Such cube represents part of…

Consistent Story Generation with Asymmetry Zigzag Sampling

2025-06-11 · Mingxiao Li, Mang Ning, Marie-Francine Moens

Text-to-image generation models have made significant progress in producing high-quality images from textual descriptions, yet they continue to struggle with maintaining subject consistency across multiple images, a fund…

Image GenerationStory GenerationStory VisualizationText to Image Generation+2

Z-GCNETs: Time Zigzags at Graph Convolutional Networks for Time Series Forecasting

2021-05-10 · Yuzhou Chen, Ignacio Segovia-Dominguez, Yulia R. Gel

There recently has been a surge of interest in developing a new class of deep learning (DL) architectures that integrate an explicit time dimension as a fundamental building block of learning and representation mechanism…

Time SeriesTime Series AnalysisTime Series Forecasting

Complexity of zigzag sampling algorithm for strongly log-concave distributions

2020-12-21 · Jianfeng Lu, Lihan Wang

We study the computational complexity of zigzag sampling algorithm for strongly log-concave distributions. The zigzag process has the advantage of not requiring time discretization for implementation, and that each propo…