paper-with-me

Papers

A Sensorimotor Vision Transformer

2025-04-03 · Konrad Gadzicki, Kerstin Schill, Christoph Zetzsche

This paper presents the Sensorimotor Transformer (SMT), a vision model inspired by human saccadic eye movements that prioritize high-saliency regions in visual input to enhance computational efficiency and reduce memory consumption. Unlike traditional models that process all image patches uniformly, SMT identifies and selects the most salient patches based on intrinsic two-dimensional (i2D) features, such as corners and occlusions, which are known to convey high-information content and align with human fixation patterns. The SMT architecture uses this biological principle to leverage vision transformers to process only the most informative patches, allowing for a substantial reduction in memory usage that scales with the sequence length of selected patches. This approach aligns with visual neuroscience findings, suggesting that the human visual system optimizes information gathering through selective, spatially dynamic focus. Experimental evaluations on Imagenet-1k demonstrate that SMT achieves competitive top-1 accuracy while significantly reducing memory consumption and computational complexity, particularly when a limited number of patches is used. This work introduces a saccade-like selection mechanism into transformer-based vision models, offering an efficient alternative for image analysis and providing new insights into biologically motivated architectures for resource-constrained applications.

📄 PDF Abstract BibTeX arXiv:2504.02536

Code (0)

등록된 구현이 없습니다.

Tasks

Computational Efficiency

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Multi-Head Attention 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
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…
Residual Connection 설명 없음
Adam 설명 없음
ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…

Similar Papers 제목 키워드 기반

Active Vision Reinforcement Learning under Limited Visual Observability

2023-06-01 · NeurIPS 2023 11 · Jinghuan Shang, Michael S. Ryoo

In this work, we investigate Active Vision Reinforcement Learning (ActiveVision-RL), where an embodied agent simultaneously learns action policy for the task while also controlling its visual observations in partially ob…

reinforcement-learningReinforcement Learning

Coaching a Teachable Student

2023-06-16 · CVPR 2023 1 · Jimuyang Zhang, Zanming Huang, Eshed Ohn-Bar

We propose a novel knowledge distillation framework for effectively teaching a sensorimotor student agent to drive from the supervision of a privileged teacher agent. Current distillation for sensorimotor agents methods …

CARLA longest6Knowledge DistillationRepresentation Learning

Robot Learning with Sensorimotor Pre-training

2023-06-16 · Ilija Radosavovic, Baifeng Shi, Letian Fu, Ken Goldberg 외

We present a self-supervised sensorimotor pre-training approach for robotics. Our model, called RPT, is a Transformer that operates on sequences of sensorimotor tokens. Given a sequence of camera images, proprioceptive r…

Motion Planning

Unsupervised Emergence of Spatial Structure from Sensorimotor Prediction

2018-10-02 · Alban Laflaquière, Michael Garcia Ortiz

Despite its omnipresence in robotics application, the nature of spatial knowledge and the mechanisms that underlie its emergence in autonomous agents are still poorly understood. Recent theoretical work suggests that the…

Prediction

Unsupervised Emergence of Egocentric Spatial Structure from Sensorimotor Prediction

2019-06-04 · NeurIPS 2019 12 · Alban Laflaquière, Michael Garcia Ortiz

Despite its omnipresence in robotics application, the nature of spatial knowledge and the mechanisms that underlie its emergence in autonomous agents are still poorly understood. Recent theoretical works suggest that the…

PositionPrediction