Places: An Image Database for Deep Scene Understanding
Not on the map. Why?
Abstract (arXiv)
The rise of multi-million-item dataset initiatives has enabled data-hungry machine learning algorithms to reach near-human semantic classification at tasks such as object and scene recognition. Here we describe the Places Database, a repository of 10 million scene photographs, labeled with scene semantic categories and attributes, comprising a quasi-exhaustive list of the types of environments encountered in the world. Using state of the art Convolutional Neural Networks, we provide impressive baseline performances at scene classification. With its high-coverage and high-diversity of exemplars, the Places Database offers an ecosystem to guide future progress on currently intractable visual recognition problems.
Key facts. Cited by 76 papers in the map (data through 7 Oct 2026). First posted on arXiv 6 Oct 2016.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 11; 2022: 13; 2023: 14; 2024: 15; 2025: 14; 2026: 9.
76 papers.
Sort:
By area:
- 2022Socratic Models: Composing Zero-Shot Multimodal Reasoning with Languagecited by 513
- 2023Interpreting CLIP's Image Representation via Text-Based Decompositioncited by 189
- 2021Exploring Deep Neural Networks via Layer-Peeled Model: Minority Collapse in Imbalanced Trainingcited by 166
- 2022Offline Visual Representation Learning for Embodied Navigationcited by 74
- 2021Drop the GAN: In Defense of Patches Nearest Neighbors as Single Image Generative Modelscited by 51
- 2021PASS: An ImageNet replacement for self-supervised pretraining without humanscited by 51
- 2024Balancing Act: Distribution-Guided Debiasing in Diffusion Modelscited by 50
- 2021SLIDE: Single Image 3D Photography with Soft Layering and Depth-aware Inpaintingcited by 48
- 2023NECO: NEural Collapse Based Out-of-distribution detectioncited by 41
- 2023Diversified Outlier Exposure for Out-of-Distribution Detection via Informative Extrapolationcited by 38
- 2021INTERN: A New Learning Paradigm Towards General Visioncited by 33
- 2022Self-Supervised Learning via Maximum Entropy Codingcited by 33
38 more
- 2023Beyond Confidence: Reliable Models Should Also Consider Atypicalitycited by 25
- 2022Bamboo: Building Mega-Scale Vision Dataset Continually with Human-Machine Synergycited by 20
- 2025UniVG: A Generalist Diffusion Model for Unified Image Generation and Editingcited by 19
- 2023Unleashing Mask: Explore the Intrinsic Out-of-Distribution Detection Capabilitycited by 16
- 2022Certified Defences Against Adversarial Patch Attacks on Semantic Segmentationcited by 15
- 2024Self-Calibrated Tuning of Vision-Language Models for Out-of-Distribution Detectioncited by 15
- 2023Masked Modeling for Self-supervised Representation Learning on Vision and Beyondcited by 13
- 2021Leveraging Semantic Scene Characteristics and Multi-Stream Convolutional Architectures in a Contextual Approach for Video-Based Visual Emotion Recognition in the Wildcited by 12
- 2023Localized Symbolic Knowledge Distillation for Visual Commonsense Modelscited by 12
- 2024ExtraNeRF: Visibility-Aware View Extrapolation of Neural Radiance Fields with Diffusion Modelscited by 12
- 2025Affective Image Editing: Shaping Emotional Factors via Text Descriptionscited by 11
- 2022Practical Network Acceleration with Tiny Setscited by 9
- 2022Measuring the Interpretability of Unsupervised Representations via Quantized Reverse Probingcited by 8
- 2024ExMap: Leveraging Explainability Heatmaps for Unsupervised Group Robustness to Spurious Correlationscited by 8
- 2024FALIP: Visual Prompt as Foveal Attention Boosts CLIP Zero-Shot Performancecited by 7
- 2024Out-Of-Distribution Detection with Diversification (Provably)cited by 6
- 2021What Image Features Boost Housing Market Predictions?cited by 5
- 2022Self-Supervised Domain Calibration and Uncertainty Estimation for Place Recognitioncited by 5
- 2023Removing Spurious Concepts from Neural Network Representations via Joint Subspace Estimationcited by 5
- 2025SimLabel: Consistency-Guided OOD Detection with Pretrained Vision-Language Modelscited by 5
- 2021Pose-GNN : Camera Pose Estimation System Using Graph Neural Networkscited by 4
- 2022Content-based Graph Privacy Advisorcited by 4
- 2023Human-interpretable and deep features for image privacy classificationcited by 4
- 2024Your Classifier Can Be Secretly a Likelihood-Based OOD Detectorcited by 4
- 2024Margin-bounded Confidence Scores for Out-of-Distribution Detectioncited by 4
- 2024Out-of-Distribution Detection with Prototypical Outlier Proxycited by 4
- 2025Outlier Synthesis via Hamiltonian Monte Carlo for Out-of-Distribution Detectioncited by 4
- 2025The Impact of Coreset Selection on Spurious Correlations and Group Robustnesscited by 4
- 2024Optimizing importance weighting in the presence of sub-population shiftscited by 3
- 2025Preserving Task-Relevant Information Under Linear Concept Removalcited by 3
- 2026IsoCLIP: Decomposing CLIP Projectors for Efficient Intra-modal Alignmentcited by 3
- 2021Urban land-use analysis using proximate sensing imagery: a surveycited by 2
- 2023Practical Network Acceleration with Tiny Sets: Hypothesis, Theory, and Algorithmcited by 2
- 2023Prompt-Based Exemplar Super-Compression and Regeneration for Class-Incremental Learningcited by 2
- 2024FEVER-OOD: Free Energy Vulnerability Elimination for Robust Out-of-Distribution Detectioncited by 2
- 2025Benchmarking Large and Small MLLMscited by 2
- 2025MedicalNarratives: Connecting Medical Vision and Language with Localized Narrativescited by 2
- 2025Learning Privacy from Visual Entitiescited by 2
50 most cited of 76 All 76 (JSON)
- 2026CHOQOLATE: Organizing Concept Bottleneck Latent Spaces with Choquet Integrals29 Sep 2026
- 2026Mitigating Spurious Correlations with Memorization-Guided Dataset De-Biasing1 Jun 2026
- 2026Multi-modal panoramic 3D outdoor datasets for place categorization14 Apr 2026
- 2026HSFM: Hard-Set-Guided Feature-Space Meta-Learning for Robust Classification under Spurious Correlations31 Mar 2026
- 2026Xuanwu: Evolving General Multimodal Models into an Industrial-Grade Foundation for Content Ecosystems31 Mar 2026
- 2026One View Is Enough: In-the-Wild Monocular Pretraining for Novel View Generation24 Mar 2026
- 2026Improving Image-to-Image Translation via a Rectified Flow Reformulation20 Mar 2026
- 2026IsoCLIP: Decomposing CLIP Projectors for Efficient Intra-modal Alignment20 Mar 2026
- 2026TASTE: Task-Aware Out-of-Distribution Detection via Stein Operators7 Feb 2026
- 2025Pre-training vision models for the classification of alerts from wide-field time-domain surveys12 Dec 2025
- 2025Tackling the Noisy Elephant in the Room: Label Noise-robust Out-of-Distribution Detection via Loss Correction and Low-rank Decomposition8 Sep 2025
- 2025Pseudo-label Induced Subspace Representation Learning for Robust Out-of-Distribution Detection5 Aug 2025
38 more
- 2025Object Recognition Datasets and Challenges: A Review30 Jul 2025
- 2025The Impact of Coreset Selection on Spurious Correlations and Group Robustness15 Jul 2025
- 2025Exploring Diffusion with Test-Time Training on Efficient Image Restoration17 Jun 2025
- 2025Preserving Task-Relevant Information Under Linear Concept Removal12 Jun 2025
- 2025Affective Image Editing: Shaping Emotional Factors via Text Descriptions24 May 2025
- 2025UniVG: A Generalist Diffusion Model for Unified Image Generation and Editing16 Mar 2025
- 2025Learning Privacy from Visual Entities16 Mar 2025
- 2025Outlier Synthesis via Hamiltonian Monte Carlo for Out-of-Distribution Detection28 Jan 2025
- 2025SimLabel: Consistency-Guided OOD Detection with Pretrained Vision-Language Models20 Jan 2025
- 2025MedicalNarratives: Connecting Medical Vision and Language with Localized Narratives7 Jan 2025
- 2025Benchmarking Large and Small MLLMs4 Jan 2025
- 2024Out-of-Distribution Detection with Prototypical Outlier Proxy22 Dec 2024
- 2024FEVER-OOD: Free Energy Vulnerability Elimination for Robust Out-of-Distribution Detection2 Dec 2024
- 2024Out-Of-Distribution Detection with Diversification (Provably)21 Nov 2024
- 2024Self-Calibrated Tuning of Vision-Language Models for Out-of-Distribution Detection5 Nov 2024
- 2024Double Descent Meets Out-of-Distribution Detection: Theoretical Insights and Empirical Analysis on the role of model complexity4 Nov 2024
- 2024Optimizing importance weighting in the presence of sub-population shifts18 Oct 2024
- 2024Margin-bounded Confidence Scores for Out-of-Distribution Detection22 Sep 2024
- 2024EDADepth: Enhanced Data Augmentation for Monocular Depth Estimation10 Sep 2024
- 2024Your Classifier Can Be Secretly a Likelihood-Based OOD Detector9 Aug 2024
- 2024Training with Explanations Alone: A New Paradigm to Prevent Shortcut Learning13 Jul 2024
- 2024FALIP: Visual Prompt as Foveal Attention Boosts CLIP Zero-Shot Performance8 Jul 2024
- 2024ExtraNeRF: Visibility-Aware View Extrapolation of Neural Radiance Fields with Diffusion Models10 Jun 2024
- 2024Refining Skewed Perceptions in Vision-Language Contrastive Models through Visual Representations22 May 2024
- 2024ExMap: Leveraging Explainability Heatmaps for Unsupervised Group Robustness to Spurious Correlations20 Mar 2024
- 2024Balancing Act: Distribution-Guided Debiasing in Diffusion Models28 Feb 2024
- 2023Masked Modeling for Self-supervised Representation Learning on Vision and Beyond31 Dec 2023
- 2023Localized Symbolic Knowledge Distillation for Visual Commonsense Models8 Dec 2023
- 2023Prompt-Based Exemplar Super-Compression and Regeneration for Class-Incremental Learning30 Nov 2023
- 2023Human-interpretable and deep features for image privacy classification30 Oct 2023
- 2023Diversified Outlier Exposure for Out-of-Distribution Detection via Informative Extrapolation21 Oct 2023
- 2023Removing Spurious Concepts from Neural Network Representations via Joint Subspace Estimation18 Oct 2023
- 2023Recursive Segmentation Living Image: An eXplainable AI (XAI) Approach for Computing Structural Beauty of Images or the Livingness of Space16 Oct 2023
- 2023NECO: NEural Collapse Based Out-of-distribution detection10 Oct 2023
- 2023Interpreting CLIP's Image Representation via Text-Based Decomposition9 Oct 2023
- 2023Enhancing the Prediction of Emotional Experience in Movies using Deep Neural Networks: The Significance of Audio and Language17 Jun 2023
- 2023Unleashing Mask: Explore the Intrinsic Out-of-Distribution Detection Capability6 Jun 2023
- 2023Beyond Confidence: Reliable Models Should Also Consider Atypicality29 May 2023
50 newest of 76 All 76 (JSON)
- 2024Balancing Act: Distribution-Guided Debiasing in Diffusion Modelscited by 50
- 2025UniVG: A Generalist Diffusion Model for Unified Image Generation and Editingcited by 19
- 2024ExtraNeRF: Visibility-Aware View Extrapolation of Neural Radiance Fields with Diffusion Modelscited by 12
- 2023Prompt-Based Exemplar Super-Compression and Regeneration for Class-Incremental Learningcited by 2
- 2024EDADepth: Enhanced Data Augmentation for Monocular Depth Estimationcited by 0
- 2026Improving Image-to-Image Translation via a Rectified Flow Reformulationcited by 0
- 2026Improving Image-to-Image Translation via a Rectified Flow Reformulation20 Mar 2026
- 2025UniVG: A Generalist Diffusion Model for Unified Image Generation and Editing16 Mar 2025
- 2024EDADepth: Enhanced Data Augmentation for Monocular Depth Estimation10 Sep 2024
- 2024ExtraNeRF: Visibility-Aware View Extrapolation of Neural Radiance Fields with Diffusion Models10 Jun 2024
- 2024Balancing Act: Distribution-Guided Debiasing in Diffusion Models28 Feb 2024
- 2023Prompt-Based Exemplar Super-Compression and Regeneration for Class-Incremental Learning30 Nov 2023
- 2024Self-Calibrated Tuning of Vision-Language Models for Out-of-Distribution Detectioncited by 15
- 2025SimLabel: Consistency-Guided OOD Detection with Pretrained Vision-Language Modelscited by 5
- 2026IsoCLIP: Decomposing CLIP Projectors for Efficient Intra-modal Alignmentcited by 3
- 2025Benchmarking Large and Small MLLMscited by 2
- 2026CHOQOLATE: Organizing Concept Bottleneck Latent Spaces with Choquet Integralscited by 0
- 2026CHOQOLATE: Organizing Concept Bottleneck Latent Spaces with Choquet Integrals29 Sep 2026
- 2026IsoCLIP: Decomposing CLIP Projectors for Efficient Intra-modal Alignment20 Mar 2026
- 2025SimLabel: Consistency-Guided OOD Detection with Pretrained Vision-Language Models20 Jan 2025
- 2025Benchmarking Large and Small MLLMs4 Jan 2025
- 2024Self-Calibrated Tuning of Vision-Language Models for Out-of-Distribution Detection5 Nov 2024
- 2023Interpreting CLIP's Image Representation via Text-Based Decompositioncited by 189
- 2021Exploring Deep Neural Networks via Layer-Peeled Model: Minority Collapse in Imbalanced Trainingcited by 166
- 2022Offline Visual Representation Learning for Embodied Navigationcited by 74
- 2021Drop the GAN: In Defense of Patches Nearest Neighbors as Single Image Generative Modelscited by 51
- 2021PASS: An ImageNet replacement for self-supervised pretraining without humanscited by 51
- 2021SLIDE: Single Image 3D Photography with Soft Layering and Depth-aware Inpaintingcited by 48
- 2023NECO: NEural Collapse Based Out-of-distribution detectioncited by 41
- 2023Diversified Outlier Exposure for Out-of-Distribution Detection via Informative Extrapolationcited by 38
- 2021INTERN: A New Learning Paradigm Towards General Visioncited by 33
- 2022Self-Supervised Learning via Maximum Entropy Codingcited by 33
- 2023Beyond Confidence: Reliable Models Should Also Consider Atypicalitycited by 25
- 2022Bamboo: Building Mega-Scale Vision Dataset Continually with Human-Machine Synergycited by 20
12 most cited of 64 All 64 (JSON)
- 2026Mitigating Spurious Correlations with Memorization-Guided Dataset De-Biasing1 Jun 2026
- 2026Multi-modal panoramic 3D outdoor datasets for place categorization14 Apr 2026
- 2026HSFM: Hard-Set-Guided Feature-Space Meta-Learning for Robust Classification under Spurious Correlations31 Mar 2026
- 2026Xuanwu: Evolving General Multimodal Models into an Industrial-Grade Foundation for Content Ecosystems31 Mar 2026
- 2026One View Is Enough: In-the-Wild Monocular Pretraining for Novel View Generation24 Mar 2026
- 2026TASTE: Task-Aware Out-of-Distribution Detection via Stein Operators7 Feb 2026
- 2025Pre-training vision models for the classification of alerts from wide-field time-domain surveys12 Dec 2025
- 2025Tackling the Noisy Elephant in the Room: Label Noise-robust Out-of-Distribution Detection via Loss Correction and Low-rank Decomposition8 Sep 2025
- 2025Pseudo-label Induced Subspace Representation Learning for Robust Out-of-Distribution Detection5 Aug 2025
- 2025Object Recognition Datasets and Challenges: A Review30 Jul 2025
- 2025The Impact of Coreset Selection on Spurious Correlations and Group Robustness15 Jul 2025
- 2025Exploring Diffusion with Test-Time Training on Efficient Image Restoration17 Jun 2025
12 newest of 64 All 64 (JSON)