mlsanityData to 7 Oct 2026

Object Detectors Emerge in Deep Scene CNNs

arXiv 1412.6856 ↗First posted 22 Dec 2014cs.CV cs.NEcited by 178

Not on the map. Why?

Abstract (arXiv)

With the success of new computational architectures for visual processing, such as convolutional neural networks (CNN) and access to image databases with millions of labeled examples (e.g., ImageNet, Places), the state of the art in computer vision is advancing rapidly. One important factor for continued progress is to understand the representations that are learned by the inner layers of these deep architectures. Here we show that object detectors emerge from training CNNs to perform scene classification. As scenes are composed of objects, the CNN for scene classification automatically discovers meaningful objects detectors, representative of the learned scene categories. With object detectors emerging as a result of learning to recognize scenes, our work demonstrates that the same network can perform both scene recognition and object localization in a single forward-pass, without ever having been explicitly taught the notion of objects.

Key facts. Cited by 178 papers in the map (data through 7 Oct 2026). First posted on arXiv 22 Dec 2014.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 56; 2022: 39; 2023: 33; 2024: 27; 2025: 17; 2026: 6.

178 papers.

Sort:

By area:

  1. 2021Masked Feature Prediction for Self-Supervised Visual Pre-Trainingcited by 573
  2. 2021Interpretable Machine Learning: Fundamental Principles and 10 Grand Challengescited by 364
  3. 2021Anabranch Network for Camouflaged Object Segmentationcited by 227
  4. 2021Localizing Objects with Self-Supervised Transformers and no Labelscited by 227
  5. 2022CLIP-Dissect: Automatic Description of Neuron Representations in Deep Vision Networkscited by 144
  6. 2022From Attribution Maps to Human-Understandable Explanations through Concept Relevance Propagationcited by 141
  7. 2022Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural Networkscited by 126
  8. 2023Concept-based Explainable Artificial Intelligence: A Surveycited by 97
  9. 2021An Interpretability Illusion for BERTcited by 94
  10. 2023Wider and Deeper LLM Networks are Fairer LLM Evaluatorscited by 91
  11. 2022Sparse Mixture-of-Experts are Domain Generalizable Learnerscited by 85
  12. 2024A Primer on the Inner Workings of Transformer-based Language Modelscited by 83
38 more
  1. 2021Explainability of deep vision-based autonomous driving systems: Review and challengescited by 80
  2. 2022Finding Skill Neurons in Pre-trained Transformer-based Language Modelscited by 65
  3. 2022On the Symmetries of Deep Learning Models and their Internal Representationscited by 63
  4. 2021Semantics for Robotic Mapping, Perception and Interaction: A Surveycited by 56
  5. 2021Beyond Trivial Counterfactual Explanations with Diverse Valuable Explanationscited by 56
  6. 2023Learning Bottleneck Concepts in Image Classificationcited by 49
  7. 2022Modeling Image Composition for Complex Scene Generationcited by 43
  8. 2021Context-Aware Layout to Image Generation with Enhanced Object Appearancecited by 41
  9. 2021STEEX: Steering Counterfactual Explanations with Semanticscited by 40
  10. 2021Defining and Quantifying the Emergence of Sparse Concepts in DNNscited by 36
  11. 2021EigenGAN: Layer-Wise Eigen-Learning for GANscited by 34
  12. 2022Explaining Deepfake Detection by Analysing Image Matchingcited by 34
  13. 2023LINe: Out-of-Distribution Detection by Leveraging Important Neuronscited by 34
  14. 2024Gradient based Feature Attribution in Explainable AI: A Technical Reviewcited by 34
  15. 2022Interpreting Neural Networks through the Polytope Lenscited by 33
  16. 2023A Preliminary Study of the Intrinsic Relationship between Complexity and Alignmentcited by 33
  17. 2021Neural Response Interpretation through the Lens of Critical Pathwayscited by 32
  18. 2023FIND: A Function Description Benchmark for Evaluating Interpretability Methodscited by 32
  19. 2021Space-Time Crop & Attend: Improving Cross-modal Video Representation Learningcited by 31
  20. 2022OCTET: Object-aware Counterfactual Explanationscited by 28
  21. 2021Looking Outside the Window: Wide-Context Transformer for the Semantic Segmentation of High-Resolution Remote Sensing Imagescited by 27
  22. 2023Does a Neural Network Really Encode Symbolic Concepts?cited by 27
  23. 2023Circuit Breaking: Removing Model Behaviors with Targeted Ablationcited by 27
  24. 2021Finding Discriminative Filters for Specific Degradations in Blind Super-Resolutioncited by 26
  25. 2024Large Multi-modal Models Can Interpret Features in Large Multi-modal Modelscited by 23
  26. 2021Carrying out CNN Channel Pruning in a White Boxcited by 22
  27. 2024Optimal ablation for interpretabilitycited by 21
  28. 2022Channel Importance Matters in Few-Shot Image Classificationcited by 20
  29. 2022Contrastive Deep Supervisioncited by 20
  30. 2024Linear Explanations for Individual Neuronscited by 19
  31. 2022HINT: Hierarchical Neuron Concept Explainercited by 17
  32. 2022Revealing Hidden Context Bias in Segmentation and Object Detection through Concept-specific Explanationscited by 17
  33. 2024CausalFormer: An Interpretable Transformer for Temporal Causal Discoverycited by 17
  34. 2021Integrated Grad-CAM: Sensitivity-Aware Visual Explanation of Deep Convolutional Networks via Integrated Gradient-Based Scoringcited by 16
  35. 2023Soft Matching Distance: A metric on neural representations that captures single-neuron tuningcited by 16
  36. 2021Detection and Localization of Facial Expression Manipulationscited by 15
  37. 2021Neural View Synthesis and Matching for Semi-Supervised Few-Shot Learning of 3D Posecited by 15
  38. 2023Towards a fuller understanding of neurons with Clustered Compositional Explanationscited by 15

50 most cited of 178 All 178 (JSON)