paper-with-me

홈 › Papers

Self-Reorganizing and Rejuvenating CNNs for Increasing Model Capacity Utilization

2021-02-13 · Wissam J. Baddar, Seungju Han, Seonmin Rhee, Jae-Joon Han

In this paper, we propose self-reorganizing and rejuvenating convolutional neural networks; a biologically inspired method for improving the computational resource utilization of neural networks. The proposed method utilizes the channel activations of a convolution layer in order to reorganize that layers parameters. The reorganized parameters are clustered to avoid parameter redundancies. As such, redundant neurons with similar activations are merged leaving room for the remaining parameters to rejuvenate. The rejuvenated parameters learn different features to supplement those learned by the reorganized surviving parameters. As a result, the network capacity utilization increases improving the baseline network performance without any changes to the network structure. The proposed method can be applied to various network architectures during the training stage, or applied to a pre-trained model improving its performance. Experimental results showed that the proposed method is model-agnostic and can be applied to any backbone architecture increasing its performance due to the elevated utilization of the network capacity.

📄 PDF Abstract BibTeX arXiv:2102.06870

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Similar Papers 제목 키워드 기반

Reconstructing Spiking Neural Networks Using a Single Neuron with Autapses

2026-03-25 · Wuque Cai, Hongze Sun, Quan Tang, Shifeng Mao 외 arxiv

Spiking neural networks (SNNs) are promising for neuromorphic computing, but high-performing models still rely on dense multilayer architectures with substantial communication and state-storage costs. Inspired by autapse…

BERT-JEPA: Reorganizing CLS Embeddings for Language-Invariant Semantics

2026-01-01 · Taj Gillin, Adam Lalani, Kenneth Zhang, Marcel Mateos Salles arxiv

Joint Embedding Predictive Architectures (JEPA) are a novel self supervised training technique that have shown recent promise across domains. We introduce BERT-JEPA (BEPA), a training paradigm that adds a JEPA training o…

Group Equivariant Convolutional Networks

2016-02-24 · Taco S. Cohen, Max Welling

We introduce Group equivariant Convolutional Neural Networks (G-CNNs), a natural generalization of convolutional neural networks that reduces sample complexity by exploiting symmetries. G-CNNs use G-convolutions, a new t…

Breast Tumour ClassificationColorectal Gland Segmentation:Multi-tissue Nucleus SegmentationRotated MNIST

PB-LLM: Partially Binarized Large Language Models

2023-09-29 · Yuzhang Shang, Zhihang Yuan, Qiang Wu, Zhen Dong

This paper explores network binarization, a radical form of quantization, compressing model weights to a single bit, specifically for Large Language Models (LLMs) compression. Due to previous binarization methods collaps…

BinarizationQuantization

Improving Convolutional Networks With Self-Calibrated Convolutions

2020-06-01 · CVPR 2020 6 · Jiang-Jiang Liu, Qibin Hou, Ming-Ming Cheng, Changhu Wang 외

Recent advances on CNNs are mostly devoted to designing more complex architectures to enhance their representation learning capacity. In this paper, we consider how to improve the basic convolutional feature transformati…

Instance SegmentationKeypoint Detectionobject-detectionObject Detection+2