paper-with-me

Papers

Deep Networks with Internal Selective Attention through Feedback Connections

2014-07-11 · NeurIPS 2014 12 · Marijn Stollenga, Jonathan Masci, Faustino Gomez, Juergen Schmidhuber

Traditional convolutional neural networks (CNN) are stationary and feedforward. They neither change their parameters during evaluation nor use feedback from higher to lower layers. Real brains, however, do. So does our Deep Attention Selective Network (dasNet) architecture. DasNets feedback structure can dynamically alter its convolutional filter sensitivities during classification. It harnesses the power of sequential processing to improve classification performance, by allowing the network to iteratively focus its internal attention on some of its convolutional filters. Feedback is trained through direct policy search in a huge million-dimensional parameter space, through scalable natural evolution strategies (SNES). On the CIFAR-10 and CIFAR-100 datasets, dasNet outperforms the previous state-of-the-art model.

📄 PDF Abstract BibTeX arXiv:1407.3068

Code (0)

등록된 구현이 없습니다.

Tasks

Deep AttentionGeneral Classification

Similar Papers 제목 키워드 기반

A Siamese Long Short-Term Memory Architecture for Human Re-Identification

2016-07-28 · European Conference on Computer Vision 2016 10 · Rahul Rama Varior, Bing Shuai, Jiwen Lu, Dong Xu 외

Matching pedestrians across multiple camera views known as human re-identification (re-identification) is a challenging problem in visual surveillance. In the existing works concentrating on feature extraction, represent…

Person Re-Identification

Connections between reinforcement learning with feedback,test-time scaling, and diffusion guidance: An anthology

2025-09-04 · Yuchen Jiao, Yuxin Chen, Gen Li arxiv

In this note, we reflect on several fundamental connections among widely used post-training techniques. We clarify some intimate connections and equivalences between reinforcement learning with human feedback, reinforcem…

Reinforcement Learning

Source-Free Bistable Fluidic Gripper for Size-Selective and Stiffness-Adaptive Grasping

2025-11-05 · Zhihang Qin, Yueheng Zhang, Wan Su, Linxin Hou 외 arxiv

Conventional fluid-driven soft grippers typically depend on external sources, which limit portability and long-term autonomy. This work introduces a self-contained soft gripper with fixed size that operates solely throug…

XAttnRes: Cross-Stage Attention Residuals for Medical Image Segmentation

2026-03-28 · Xinyu Liu, Qing Xu, Zhen Chen arxiv

In the field of Large Language Models (LLMs), Attention Residuals have recently demonstrated that learned, selective aggregation over all preceding layer outputs can outperform fixed residual connections. We propose Cros…

Medical Image Segmentation

Recurrent Vision Transformer for Solving Visual Reasoning Problems

2021-11-29 · Nicola Messina, Giuseppe Amato, Fabio Carrara, Claudio Gennaro 외

Although convolutional neural networks (CNNs) showed remarkable results in many vision tasks, they are still strained by simple yet challenging visual reasoning problems. Inspired by the recent success of the Transformer…

Object DetectionVisual Reasoning