# Some Improvements on Deep Convolutional Neural Network Based Image Classification

arXiv: https://arxiv.org/abs/1312.5402 · HTML: https://mlsanity.com/paper/1312.5402/

## Key facts

- Cited by 34 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Dec 2013.

## Built on by (most cited first, 30 of 34)

- [Pix2seq: A Language Modeling Framework for Object Detection](https://mlsanity.com/paper/2109.10852/) (2021)
- [Self-Supervised Learning with Data Augmentations Provably Isolates Content from Style](https://mlsanity.com/paper/2106.04619/) (2021)
- [Understanding and Improving Robustness of Vision Transformers through Patch-based Negative Augmentation](https://mlsanity.com/paper/2110.07858/) (2021)
- [CoCoSoDa: Effective Contrastive Learning for Code Search](https://mlsanity.com/paper/2204.03293/) (2022)
- [Hard-Attention for Scalable Image Classification](https://mlsanity.com/paper/2102.10212/) (2021)
- [Test-Time Distribution Normalization for Contrastively Learned Vision-language Models](https://mlsanity.com/paper/2302.11084/) (2023)
- [CAM-loss: Towards Learning Spatially Discriminative Feature Representations](https://mlsanity.com/paper/2109.01359/) (2021)
- [Measuring the Ripeness of Fruit with Hyperspectral Imaging and Deep Learning](https://mlsanity.com/paper/2104.09808/) (2021)
- [Identifiable Causal Representation Learning: Unsupervised, Multi-View, and Multi-Environment](https://mlsanity.com/paper/2406.13371/) (2024)
- [On the Origins of the Block Structure Phenomenon in Neural Network Representations](https://mlsanity.com/paper/2202.07184/) (2022)
- [InsCon:Instance Consistency Feature Representation via Self-Supervised Learning](https://mlsanity.com/paper/2203.07688/) (2022)
- [Deep invariant networks with differentiable augmentation layers](https://mlsanity.com/paper/2202.02142/) (2022)
- [Learn From the Past: Experience Ensemble Knowledge Distillation](https://mlsanity.com/paper/2202.12488/) (2022)
- [Low-cost and high-performance data augmentation for deep-learning-based skin lesion classification](https://mlsanity.com/paper/2101.02353/) (2021)
- [Bridging Gap between Image Pixels and Semantics via Supervision: A Survey](https://mlsanity.com/paper/2107.13757/) (2021)
- [Test-Time Augmentation for 3D Point Cloud Classification and Segmentation](https://mlsanity.com/paper/2311.13152/) (2023)
- [MobileDenseNet: A new approach to object detection on mobile devices](https://mlsanity.com/paper/2207.11031/) (2022)
- [Interpolation for Robust Learning: Data Augmentation on Wasserstein Geodesics](https://mlsanity.com/paper/2302.02092/) (2023)
- [Temporal Contrastive Learning for Spiking Neural Networks](https://mlsanity.com/paper/2305.13909/) (2023)
- [VLM-UQBench: A Benchmark for Modality-Specific and Cross-Modality Uncertainties in Vision Language Models](https://mlsanity.com/paper/2602.09214/) (2026)
- [Adaptive Test-Time Augmentation for Low-Power CPU](https://mlsanity.com/paper/2105.06183/) (2021)
- [DU-Net based Unsupervised Contrastive Learning for Cancer Segmentation in Histology Images](https://mlsanity.com/paper/2206.08791/) (2022)
- [Real-Time Cattle Interaction Recognition via Triple-stream Network](https://mlsanity.com/paper/2209.02241/) (2022)
- [Geometric Data Augmentation Based on Feature Map Ensemble](https://mlsanity.com/paper/2107.10524/) (2021)
- [Enhanced Performance of Pre-Trained Networks by Matched Augmentation Distributions](https://mlsanity.com/paper/2201.07894/) (2022)
- [Vision-Based American Sign Language Classification Approach via Deep Learning](https://mlsanity.com/paper/2204.04235/) (2022)
- [Multi-Augmentation for Efficient Visual Representation Learning for Self-supervised Pre-training](https://mlsanity.com/paper/2205.11772/) (2022)
- [Robust and Efficient Imbalanced Positive-Unlabeled Learning with Self-supervision](https://mlsanity.com/paper/2209.02459/) (2022)
- [A Diver Attention Estimation Framework for Effective Underwater Human-Robot Interaction](https://mlsanity.com/paper/2209.14447/) (2022)
- [Semi-Supervised Representative Region Texture Extraction of Faccade](https://mlsanity.com/paper/2212.02220/) (2022)

## Abstract (arXiv)

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.