Some Improvements on Deep Convolutional Neural Network Based Image Classification

Abstract

We investigate multiple techniques to improve upon the current state of the art deep convolutional neural network based image classification pipeline. The techiques include adding more image transformations to training data, adding more transformations to generate additional predictions at test time and using complementary models applied to higher resolution images. This paper summarizes our entry in the Imagenet Large Scale Visual Recognition Challenge 2013. Our system achieved a top 5 classification error rate of 13.55% using no external data which is over a 20% relative improvement on the previous year's winner.

References in corpus (1)

• Improving neural networks by preventing co-adaptation of feature detectors

Cited by in corpus (44)

• A Simple Framework for Contrastive Learning of Visual Representations
• Deep learning with convolutional neural networks for EEG decoding and visualization
• Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
• AutoAugment: Learning Augmentation Policies from Data
• Deep Image: Scaling up Image Recognition
• Systematic evaluation of CNN advances on the ImageNet
• Self-training with Noisy Student improves ImageNet classification
• A Joint Convolutional Neural Networks and Context Transfer for Street Scenes Labeling
• Hydra: an Ensemble of Convolutional Neural Networks for Geospatial Land Classification
• Pix2seq: A Language Modeling Framework for Object Detection
• Comprehensive Attention Self-Distillation for Weakly-Supervised Object Detection
• Self-Supervised Learning with Data Augmentations Provably Isolates Content from Style
• A Survey of Deep Learning for Scientific Discovery
• Deep Recurrent Convolutional Networks for Video-based Person Re-identification: An End-to-End Approach
• Segmentation of histological images and fibrosis identification with a convolutional neural network
• Deep Learning Convolutional Networks for Multiphoton Microscopy Vasculature Segmentation
• LQ-Nets: Learned Quantization for Highly Accurate and Compact Deep Neural Networks
• LFFD: A Light and Fast Face Detector for Edge Devices
• FaceBoxes: A CPU Real-time Face Detector with High Accuracy
• More is Less: A More Complicated Network with Less Inference Complexity
• Deep Layer Aggregation
• Real-world plant species identification based on deep convolutional neural networks and visual attention
• Flip-Rotate-Pooling Convolution and Split Dropout on Convolution Neural Networks for Image Classification
• SFace: An Efficient Network for Face Detection in Large Scale Variations
• Understanding and Improving Robustness of Vision Transformers through Patch-based Negative Augmentation
• EnsembleNet: End-to-End Optimization of Multi-headed Models
• A Deep Generative Deconvolutional Image Model
• Hard-Attention for Scalable Image Classification
• Residual Squeeze VGG16
• EfficientSeg: An Efficient Semantic Segmentation Network
• Surface Damage Detection Scheme using Convolutional Neural Network and Artificial Neural Network
• Learning Strict Identity Mappings in Deep Residual Networks
• Dynamic Scale Inference by Entropy Minimization
• DelugeNets: Deep Networks with Efficient and Flexible Cross-layer Information Inflows
• Analysis of Dimensional Influence of Convolutional Neural Networks for Histopathological Cancer Classification
• Winter Road Surface Condition Recognition Using A Pretrained Deep Convolutional Network
• Adaptive Test-Time Augmentation for Low-Power CPU
• Fusion of an Ensemble of Augmented Image Detectors for Robust Object Detection
• AFFACT - Alignment-Free Facial Attribute Classification Technique
• Assessing The Importance Of Colours For CNNs In Object Recognition
• Fine-grained Optimization of Deep Neural Networks
• A Hierarchical Matcher using Local Classifier Chains
• Multitask training with unlabeled data for end-to-end sign language fingerspelling recognition
• Safe Augmentation: Learning Task-Specific Transformations from Data