ImageNet Large Scale Visual Recognition Challenge

The ImageNet Large Scale Visual Recognition Challenge is a benchmark in object category classification and detection on hundreds of object categories and millions of images. The challenge has been run annually from 2010 to present, attracting participation from more than fifty institutions. This paper describes the creation of this benchmark dataset and the advances in object recognition that have been possible as a result. We discuss the challenges of collecting large-scale ground truth annotation, highlight key breakthroughs in categorical object recognition, provide a detailed analysis of the current state of the field of large-scale image classification and object detection, and compare the state-of-the-art computer vision accuracy with human accuracy. We conclude with lessons learned in the 5 years of the challenge, and propose future directions and improvements.

• Publication year

  2014

• Venue

  International Journal of Computer Vision

• Publication date

  2014-09-01

• Fields of study

  Computer Science

• Identifiers
  DOI 10.1007/s11263-015-0816-yarXiv 1409.0575
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Return of the devil

  2016cited by this paper
• CloudCV: Large-Scale Distributed Computer Vision as a Cloud Service

  2015cited by this paper
• Contextualizing Object Detection and Classification

  2015cited by this paper
• Learning Deep Features for Scene Recognition using Places Database

  2014cited by this paper
• Caffe: Convolutional Architecture for Fast Feature Embedding

  2014cited by this paper
• Going deeper with convolutions

  2014cited by this paper
• Deep Epitomic Convolutional Neural Networks

  2014cited by this paper
• Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition

  2014cited by this paper
• Very Deep Convolutional Networks for Large-Scale Image Recognition

  2014cited by this paper
• Microsoft COCO: Common Objects in Context

  2014cited by this paper
• The Pascal Visual Object Classes Challenge: A Retrospective

  2014cited by this paper
• Minerva: A Scalable and Highly Efficient Training Platform for Deep Learning

  2014influential reference
• Fisher and VLAD with FLAIR

  2014influential reference
• DeepID-Net: multi-stage and deformable deep convolutional neural networks for object detection

  2014cited by this paper
• Scalable multi-label annotation

  2014cited by this paper
• Hard negative classes for multiple object detection

  2014cited by this paper
• Return of the Devil in the Details: Delving Deep into Convolutional Nets

  2014cited by this paper
• DenseNet: Implementing Efficient ConvNet Descriptor Pyramids

  2014cited by this paper
• Modeling Image Patches with a Generic Dictionary of Mini-epitomes

  2014cited by this paper
• Multiscale Combinatorial Grouping

  2014cited by this paper
• Efficient Estimation of Word Representations in Vector Space

  2013cited by this paper
• Detecting Avocados to Zucchinis: What Have We Done, and Where Are We Going?

  2013cited by this paper
• DeViSE: A Deep Visual-Semantic Embedding Model

  2013cited by this paper
• Some Improvements on Deep Convolutional Neural Network Based Image Classification

  2013influential reference
• Sparse arrays of signatures for online character recognition

  2013cited by this paper
• Deep Fisher Networks for Large-Scale Image Classification

  2013influential reference
• From Large Scale Image Categorization to Entry-Level Categories

  2013cited by this paper
• Fast, Accurate Detection of 100,000 Object Classes on a Single Machine

  2013cited by this paper
• Deep Learning using Support Vector Machines

  2013cited by this paper
• Regularization of Neural Networks using DropConnect

  2013cited by this paper
• Visualizing and Understanding Convolutional Networks

  2013influential reference
• OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks

  2013influential reference
• Prime Object Proposals with Randomized Prim's Algorithm

  2013cited by this paper
• DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition

  2013cited by this paper
• Regionlets for Generic Object Detection

  2013influential reference
• Vision meets robotics: The KITTI dataset

  2013cited by this paper
• OpenSurfaces

  2013cited by this paper
• Joint Deep Learning for Pedestrian Detection

  2013cited by this paper
• Network In Network

  2013influential reference
• Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation

  2013influential reference
• Selective Search for Object Recognition

  2013cited by this paper
• Graphical Gaussian Vector for Image Categorization

  2012influential reference
• ImageNet classification with deep convolutional neural networks

  2012influential reference
• Efficiently Scaling up Crowdsourced Video Annotation

  2012cited by this paper
• Multi-column deep neural networks for image classification

  2012cited by this paper
• Diagnosing Error in Object Detectors

  2012cited by this paper
• Novel Dataset for Fine-Grained Image Categorization : Stanford Dogs

  2012cited by this paper
• Towards good practice in large-scale learning for image classification

  2012influential reference
• Crowdsourcing Annotations for Visual Object Detection

  2012influential reference
• Metric Learning for Large Scale Image Classification: Generalizing to New Classes at Near-Zero Cost

  2012influential reference
• Segmentation Propagation in ImageNet

  2012cited by this paper
• Improving neural networks by preventing co-adaptation of feature detectors

  2012cited by this paper
• Modeling the spatial layout of images beyond spatial pyramids

  2012influential reference
• Multi-attribute spaces: Calibration for attribute fusion and similarity search

  2012cited by this paper
• Three things everyone should know to improve object retrieval

  2012influential reference
• Exact Acceleration of Linear Object Detectors

  2012cited by this paper
• Adaptive deconvolutional networks for mid and high level feature learning

  2011cited by this paper
• Measuring the Objectness of Image Windows

  2011cited by this paper
• Segmentation as selective search for object recognition

  2011cited by this paper
• Large-scale image classification: Fast feature extraction and SVM training

  2011influential reference
• High-dimensional signature compression for large-scale image classification

  2011influential reference
• Quality Assessment for Crowdsourced Object Annotations

  2011cited by this paper
• Unbiased look at dataset bias

  2011influential reference
• Nonparametric Scene Parsing via Label Transfer

  2011cited by this paper
• Empowering Visual Categorization With the GPU

  2011influential reference
• Combining randomization and discrimination for fine-grained image categorization

  2011cited by this paper
• Contour Detection and Hierarchical Image Segmentation

  2011cited by this paper
• Object Detection with Discriminatively Trained Part Based Models

  2010influential reference
• The Pascal Visual Object Classes (VOC) Challenge

  2010cited by this paper
• Locality-constrained Linear Coding for image classification

  2010cited by this paper
• Image Classification Using Super-Vector Coding of Local Image Descriptors

  2010cited by this paper
• SUN database: Large-scale scene recognition from abbey to zoo

  2010cited by this paper
• Improving the Fisher Kernel for Large-Scale Image Classification

  2010influential reference
• Evaluating Color Descriptors for Object and Scene Recognition

  2010cited by this paper
• The Multidimensional Wisdom of Crowds

  2010cited by this paper
• ImageNet: A large-scale hierarchical image database

  2009cited by this paper
• Decomposing a scene into geometric and semantically consistent regions

  2009influential reference
• Object detection using a max-margin Hough transform

  2009influential reference
• Linear spatial pyramid matching using sparse coding for image classification

  2009cited by this paper
• Utility data annotation with Amazon Mechanical Turk

  2008cited by this paper
• LabelMe: A Database and Web-Based Tool for Image Annotation

  2008cited by this paper
• Labeled Faces in the Wild: A Database forStudying Face Recognition in Unconstrained Environments

  2008influential reference
• Get another label? improving data quality and data mining using multiple, noisy labelers

  2008cited by this paper
• Caltech-256 Object Category Dataset

  2007cited by this paper
• Fisher Kernels on Visual Vocabularies for Image Categorization

  2007cited by this paper
• Introduction to a Large-Scale General Purpose Ground Truth Database: Methodology, Annotation Tool and Benchmarks

  2007cited by this paper
• The PASCAL Visual Object Classes Challenge

  2006cited by this paper
• Graph-Based Visual Saliency

  2006cited by this paper
• Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories

  2006cited by this paper
• Face Description with Local Binary Patterns: Application to Face Recognition

  2006cited by this paper
• A Bayesian hierarchical model for learning natural scene categories

  2005cited by this paper
• Learning Generative Visual Models from Few Training Examples: An Incremental Bayesian Approach Tested on 101 Object Categories

  2004cited by this paper
• Distinctive Image Features from Scale-Invariant Keypoints

  2004influential reference
• Labeling images with a computer game

  2004cited by this paper
• Epitomic analysis of appearance and shape

  2003cited by this paper
• Online Passive-Aggressive Algorithms

  2003cited by this paper
• Modeling the Shape of the Scene: A Holistic Representation of the Spatial Envelope

  2001cited by this paper
• Speed of processing in the human visual system

  1996cited by this paper
• WordNet: A Lexical Database for English

  1995cited by this paper
• [Clothing].

  1974cited by this paper

• Combating Noisy Labels through Fostering Self- and Neighbor-Consistency

  2026influential citation
• An interpretable Transformer–LSTM denoising autoencoder for semi-supervised fault diagnosis in chemical processes

  2026cites this paper
• CNeXt-DANet: ConvNeXt with dual attention for violence detection in surveillance videos

  2026cites this paper
• Automatic Tag Generation (ATG) Using Machine Learning Tech-niques for Women Violence Detection

  2026cites this paper
• Few-shot learning perfected: The efficacy and simplicity of Mate-baseline++

  2026cites this paper
• Robust Cell-Level Classification for Liquid-Based Cervical Cytology Using Deep Transfer Learning: A Multi-Source Study Addressing Scanner-Induced Domain Shifts

  2026cites this paper
• Efficient UAV High-Resolution Image Stitching via Dense Deep Kernelized Feature

  2026cites this paper
• CLIP-Driven Lifelong Multi-view Clustering

  2026cites this paper
• Locality-Attending Vision Transformer

  2026cites this paper
• A Simple Baseline for Unifying Understanding, Generation, and Editing via Vanilla Next-token Prediction

  2026cites this paper
• Fusion-CAM: Integrating Gradient and Region-Based Class Activation Maps for Robust Visual Explanations

  2026cites this paper
• Selective Sensing of Hydrogen and Ammonia Using a Single CMOS-Compatible Sensor and Transfer Learning Methods.

  2026cites this paper
• Improvement of the method of the multiclass Pap smear image segmentation based on cross-domain transfer learning with limited data

  2026cites this paper
• Real-Time Histopathological Cancer Diagnosis Using ResNet50: Transfer Learning for Automated Tumor Detection and Classification

  2026cites this paper
• SSR: A Generic Framework for Text-Aided Map Compression for Localization

  2026cites this paper
• Underrepresented in Foundation Model Pretraining Data? A One-Shot Probe

  2026cites this paper
• Solving adversarial examples requires solving exponential misalignment

  2026influential citation
• Why Do Unlearnable Examples Work: A Novel Perspective of Mutual Information

  2026cites this paper
• When Visual Evidence is Ambiguous: Pareidolia as a Diagnostic Probe for Vision Models

  2026cites this paper
• Structure-Aware Distributed Backdoor Attacks in Federated Learning

  2026cites this paper
• Cognitive Dark Matter: Measuring What AI Misses

  2026cites this paper
• Foreign object detection in power transmission lines using SESYOLO.

  2026cites this paper
• Does data augmentation help or hinder the generalization of deepfake video detection?

  2026cites this paper
• Interpretable hybrid ensemble with attention-based fusion and EAOO-GA optimization for lung cancer detection

  2026cites this paper
• TC-Pad\'e: Trajectory-Consistent Pad\'e Approximation for Diffusion Acceleration

  2026cites this paper
• DSBA: Dynamic Stealthy Backdoor Attack with Collaborative Optimization in Self-Supervised Learning

  2026cites this paper
• Temporal Imbalance of Positive and Negative Supervision in Class-Incremental Learning

  2026cites this paper
• Learning Object-Centric Spatial Reasoning for Sequential Manipulation in Cluttered Environments

  2026cites this paper
• Confounding factors and biases abound when predicting molecular biomarkers from histological images.

  2026cites this paper
• CSWin-MDKDNet: cross-shaped window network with multi-dimensional fusion and knowledge distillation for medical image segmentation.

  2026cites this paper
• Task-Driven Subspace Decomposition for Knowledge Sharing and Isolation in LoRA-based Continual Learning

  2026cites this paper
• Boosting Entropy with Bell Box Quantization

  2026cites this paper
• What Helps---and What Hurts: Bidirectional Explanations for Vision Transformers

  2026cites this paper
• Scaling Quantum Machine Learning without Tricks: High-Resolution and Diverse Image Generation

  2026cites this paper
• Search Multilayer Perceptron-Based Fusion for Efficient and Accurate Siamese Tracking

  2026cites this paper
• Dream2Learn: Structured Generative Dreaming for Continual Learning

  2026cites this paper
• Semantic See-through Goggles: Wearing Linguistic Virtual Reality in (Artificial) Intelligence

  2026cites this paper
• A novel stochastic conjugate gradient algorithm based on a stochastic differential equation perspective

  2026cites this paper
• DM-SR: Diffusion-based Multimodal Semantic Restoration within Semantic Communication Systems

  2026cites this paper
• Automated Identification of Stylolites in Geological Whole-Core Images using Hybrid Deep Learning Networks

  2026cites this paper
• HCDCMQ: Hessian-Aware Channel Determinism-Decomposition with Counterfactual Multi-Agent Optimization for Channel-Wise Mixed-Precision Post-Training Quantization

  2026cites this paper
• Hierarchical Concept-based Interpretable Models

  2026cites this paper
• Incremental dimension reduction for efficient and accurate visual anomaly detection

  2026cites this paper
• A survey of recent advances in adversarial attack and defense on vision-language models.

  2026cites this paper
• TINCLIP: Improving compositional reasoning of CLIP via textual inversion with no

  2026cites this paper
• A Computational Community Blind Challenge on Pan-Coronavirus Drug Discovery Data.

  2026cites this paper
• Functional bipartite invariance in mouse primary visual cortex receptive fields.

  2026cites this paper
• Review of Hybrid and Data-Efficient Methods in Medical Image Segmentation

  2026cites this paper
• PRNet: prototype reorganization few-shot semantic segmentation network

  2026cites this paper
• LH-MemUDA: low-high resolution memory black-box unsupervised domain adaptation

  2026cites this paper
• TriLite: Efficient Weakly Supervised Object Localization with Universal Visual Features and Tri-Region Disentanglement

  2026cites this paper
• Certified Circuits: Stability Guarantees for Mechanistic Circuits

  2026cites this paper
• Denoising as Path Planning: Training-Free Acceleration of Diffusion Models with DPCache

  2026cites this paper
• Evaluation of the Impact of Image Mutations on the Origin Classification of Digital Images

  2026cites this paper
• Data-centric single teacher guided knowledge distillation for alleviating sub-optimal supervision in image classification

  2026cites this paper
• A survey on design choices for self-supervised learning in computer vision

  2026cites this paper
• ADCT: Improving Robustness and Calibration of Pattern Recognition Models Against Visual Illusions

  2026cites this paper
• Semantic segmentation performance of aerial image segmentation using weighted ensemble trained networks CNNs

  2026cites this paper
• Analyzing Heart Tones to Diagnose Pulmonary Hypertension

  2026cites this paper
• Detection of Cataract Using Deep Learning Models

  2026cites this paper
• Edge-Optimized Voice Control with 0.26 M Parameters: Distilling 86M Adaptive Window Audio Transformer for Real-World Variable-Length Inputs

  2025cites this paper
• Leveraging Brain Inspired Principles for Data Efficient Multimodal Learning

  2025cites this paper
• HNNet: Histogrammic Neural Network for Rapidly Detecting Diabetic Retinopathy with Retinal Fundus Images

  2025cites this paper
• CLFE-GAN: A Generation Framework for Contactless Fingerprint Enhancement

  2025cites this paper
• VISOR: An AI-Powered Guiding Shield for Vision

  2025cites this paper
• Comparative Analysis of Deep Learning Models to Identify Skin Cancer

  2025cites this paper
• Reconstruct and De-identify (RaD): A Joint Task Framework for Face Reconstruction and De-identification Leveraging the 3D Morphable Model Explainability

  2025cites this paper
• Face Detection and Identification Using Convolutional Neural Network and MobileNetV3 Model

  2025cites this paper
• Smart Home Automation System: Secure Face Recognition and Gesture-Based Control

  2025cites this paper
• A Comprehensive Survey of Modern Image Classification Architectures: Comparative Analysis of CNN, Transformer, and Hybrid Approaches on ImageNet

  2025cites this paper
• Adaptive Prefiltering for High-Dimensional Similarity Search: A Frequency-Aware Approach

  2025cites this paper
• Weakly Supervised MaxN Estimation in Baited Remote Underwater Videos

  2025cites this paper
• Accuracy Improvement of Prompt-Based Continual Learning with Past Information

  2025cites this paper
• B-Cos Networks as an Architectural Inductive Bias for Mitigating Catastrophic Forgetting

  2025cites this paper
• Push Quantization-Aware Training Toward Full Precision Performances via Consistency Regularization

  2024cites this paper
• A Unified Generalization Analysis of Re-Weighting and Logit-Adjustment for Imbalanced Learning

  2023cites this paper
• The Certification Paradox: Certifications Admit Better Attacks

  2023cites this paper
• From promise to practice: towards the realisation of AI-informed mental health care.

  2022cites this paper
• An Automated and Robust Image Watermarking Scheme Based on Deep Neural Networks

  2020cites this paper
• The Power of Sparsity in Convolutional Neural Networks

  2017cites this paper
• Joint Optimization of Camera Model and Deep Neural Network for Image Recognition

  year unknowninfluential citation
• HEART-PFL: Stable Personalized Federated Learning under Heterogeneity with Hierarchical Directional Alignment and Adversarial Knowledge Transfer

  year unknowncites this paper
• SeaClips: A Video Dataset for Maritime Object Detection.

  year unknowncites this paper
• BAFLE-DCT: Bypassing Adversarial Filters via Frequency-Selective Embedding in the DCT Domain

  year unknowncites this paper
• Knowledge-Based Systems

  year unknowncites this paper
• UvA-DARE (Digital Academic Repository) {MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning

  year unknowncites this paper
• algorithm for land segmentation and building recognition to protect the Egyptian cultıvated land based on u-NET and CNN

  year unknowncites this paper
• Appendix for Enhancing Transferability of Targeted Adversarial Examples via Inverse Target Gradient Competition and Spatial Distance Stretching

  year unknowncites this paper
• KOEnsAttack: Towards Efficient Data-Free Black-Box Adversarial Attacks via Knowledge-Orthogonalized Substitute Ensembles

  year unknowncites this paper
• Bringing RNNs Back to Efficient Open-Ended Video Understanding Supplementary Material

  year unknowncites this paper
• MIT Open Access

  year unknowncites this paper
• Supplementary Material for JointDiT: Enhancing RGB-Depth Joint Modeling with Diffusion Transformers

  year unknowncites this paper
• An Efficient Subset Selection Strategy Using Text-Guided Data Attribution to Mitigate Simplicity Bias

  year unknowninfluential citation
• World Journal of Radiology

  year unknowncites this paper
• S TRUCTURING H IDDEN F EATURES VIA C LUSTERING OF U NIT -L EVEL A CTIVATION P ATTERNS

  year unknowncites this paper
• Multiscale Attention-Based Prototypical Network For Few-Shot Semantic Segmentation

  year unknowncites this paper
• Medical Image Analysis

  year unknowncites this paper
• Scalable Automated Video Labeling for Early Wildfire Smoke Detection with Fast-Then-Precise Two-Stage Inference

  year unknowncites this paper