paper-with-me

홈 › Papers

Grid Partitioned Attention: Efficient TransformerApproximation with Inductive Bias for High Resolution Detail Generation

2021-07-08 · Nikolay Jetchev, Gökhan Yildirim, Christian Bracher, Roland Vollgraf

Attention is a general reasoning mechanism than can flexibly deal with image information, but its memory requirements had made it so far impractical for high resolution image generation. We present Grid Partitioned Attention (GPA), a new approximate attention algorithm that leverages a sparse inductive bias for higher computational and memory efficiency in image domains: queries attend only to few keys, spatially close queries attend to close keys due to correlations. Our paper introduces the new attention layer, analyzes its complexity and how the trade-off between memory usage and model power can be tuned by the hyper-parameters.We will show how such attention enables novel deep learning architectures with copying modules that are especially useful for conditional image generation tasks like pose morphing. Our contributions are (i) algorithm and code1of the novel GPA layer, (ii) a novel deep attention-copying architecture, and (iii) new state-of-the art experimental results in human pose morphing generation benchmarks.

📄 PDF Abstract BibTeX arXiv:2107.03742

Code (1)

zalandoresearch/gpa 공식 구현 pytorch

Tasks

Conditional Image GenerationDeep AttentionImage GenerationInductive Bias

Similar Papers 제목 키워드 기반

Grid-Preserving Knowledge Distillation: Transferring Convolutional Inductive Bias to Vision Transformers under Data Scarcity

2026-08-11 · Junyong Choi, Cheolhyeon Park, Jaehoon Cho arxiv

Vision Transformers demonstrate remarkable global modeling capacity but often underperform in data-scarce regimes. Distilling convolutional inductive biases from a CNN teacher provides an effective remedy while leaving t…

Knowledge DistillationGeneral Knowledge

Grid-to-Graph: Flexible Spatial Relational Inductive Biases for Reinforcement Learning

2021-02-08 · Zhengyao Jiang, Pasquale Minervini, Minqi Jiang, Tim Rocktaschel

Although reinforcement learning has been successfully applied in many domains in recent years, we still lack agents that can systematically generalize. While relational inductive biases that fit a task can improve genera…

reinforcement-learningReinforcement Learning (RL)

VisCo Grids: Surface Reconstruction with Viscosity and Coarea Grids

2023-03-25 · Albert Pumarola, Artsiom Sanakoyeu, Lior Yariv, Ali Thabet 외

Surface reconstruction has been seeing a lot of progress lately by utilizing Implicit Neural Representations (INRs). Despite their success, INRs often introduce hard to control inductive bias (i.e., the solution surface …

Inductive BiasSurface Reconstruction

Physics-Informed Inductive Biases for Voltage Prediction in Distribution Grids

2025-09-29 · Ehimare Okoyomon, Arbel Yaniv, Christoph Goebel arxiv

Voltage prediction in distribution grids is a critical yet difficult task for maintaining power system stability. Machine learning approaches, particularly Graph Neural Networks (GNNs), offer significant speedups but suf…

I-BERT: Inductive Generalization of Transformer to Arbitrary Context Lengths

2020-06-18 · Hyoungwook Nam, Seung Byum Seo, Vikram Sharma Mailthody, Noor Michael 외

Self-attention has emerged as a vital component of state-of-the-art sequence-to-sequence models for natural language processing in recent years, brought to the forefront by pre-trained bi-directional Transformer models. …

Language ModelingLanguage ModellingMasked Language Modeling