paper-with-me

홈 › Papers

Gradually Updated Neural Networks for Large-Scale Image Recognition

2017-11-25 · ICML 2018 7 · Siyuan Qiao, Zhishuai Zhang, Wei Shen, Bo wang, Alan Yuille

Depth is one of the keys that make neural networks succeed in the task of large-scale image recognition. The state-of-the-art network architectures usually increase the depths by cascading convolutional layers or building blocks. In this paper, we present an alternative method to increase the depth. Our method is by introducing computation orderings to the channels within convolutional layers or blocks, based on which we gradually compute the outputs in a channel-wise manner. The added orderings not only increase the depths and the learning capacities of the networks without any additional computation costs, but also eliminate the overlap singularities so that the networks are able to converge faster and perform better. Experiments show that the networks based on our method achieve the state-of-the-art performances on CIFAR and ImageNet datasets.

📄 PDF Abstract BibTeX arXiv:1711.09280

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Beyond Pattern Recognition: Probing Mental Representations of LMs

2025-02-23 · Moritz Miller, Kumar Shridhar

Language Models (LMs) have demonstrated impressive capabilities in solving complex reasoning tasks, particularly when prompted to generate intermediate explanations. However, it remains an open question whether these int…

Convolutional Neural Networks with Alternately Updated Clique

2018-02-28 · CVPR 2018 6 · Yibo Yang, Zhisheng Zhong, Tiancheng Shen, Zhouchen Lin

Improving information flow in deep networks helps to ease the training difficulties and utilize parameters more efficiently. Here we propose a new convolutional neural network architecture with alternately updated clique…

Improving Word Recognition using Multiple Hypotheses and Deep Embeddings

2020-10-27 · Siddhant Bansal, Praveen Krishnan, C. V. Jawahar

We propose a novel scheme for improving the word recognition accuracy using word image embeddings. We use a trained text recognizer, which can predict multiple text hypothesis for a given word image. Our fusion scheme im…

Triplet

C2F-SemiCD: A Coarse-to-Fine Semi-Supervised Change Detection Method Based on Consistency Regularization in High-Resolution Remote Sensing Images

2024-04-22 · Chengxi Han, Chen Wu, Meiqi Hu, Jiepan Li 외

A high-precision feature extraction model is crucial for change detection (CD). In the past, many deep learning-based supervised CD methods learned to recognize change feature patterns from a large number of labelled bi-…

Change DetectionSemi-supervised Change Detection

Multi-scale Dynamic Graph Convolutional Network for Hyperspectral Image Classification

2019-05-14 · Sheng Wan, Chen Gong, Ping Zhong, Bo Du 외

Convolutional Neural Network (CNN) has demonstrated impressive ability to represent hyperspectral images and to achieve promising results in hyperspectral image classification. However, traditional CNN models can only op…

ClassificationGeneral ClassificationHyperspectral Image Classificationimage-classification+1