# Object Detectors Emerge in Deep Scene CNNs

arXiv: https://arxiv.org/abs/1412.6856 · HTML: https://mlsanity.com/paper/1412.6856/

## Key facts

- Cited by 179 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Dec 2014.

## Built on by (most cited first, 30 of 179)

- [Masked Feature Prediction for Self-Supervised Visual Pre-Training](https://mlsanity.com/paper/2112.09133/) (2021)
- [Interpretable Machine Learning: Fundamental Principles and 10 Grand Challenges](https://mlsanity.com/paper/2103.11251/) (2021)
- [Localizing Objects with Self-Supervised Transformers and no Labels](https://mlsanity.com/paper/2109.14279/) (2021)
- [Anabranch Network for Camouflaged Object Segmentation](https://mlsanity.com/paper/2105.09451/) (2021)
- [CLIP-Dissect: Automatic Description of Neuron Representations in Deep Vision Networks](https://mlsanity.com/paper/2204.10965/) (2022)
- [From Attribution Maps to Human-Understandable Explanations through Concept Relevance Propagation](https://mlsanity.com/paper/2206.03208/) (2022)
- [Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural Networks](https://mlsanity.com/paper/2207.13243/) (2022)
- [Concept-based Explainable Artificial Intelligence: A Survey](https://mlsanity.com/paper/2312.12936/) (2023)
- [An Interpretability Illusion for BERT](https://mlsanity.com/paper/2104.07143/) (2021)
- [Wider and Deeper LLM Networks are Fairer LLM Evaluators](https://mlsanity.com/paper/2308.01862/) (2023)
- [Sparse Mixture-of-Experts are Domain Generalizable Learners](https://mlsanity.com/paper/2206.04046/) (2022)
- [A Primer on the Inner Workings of Transformer-based Language Models](https://mlsanity.com/paper/2405.00208/) (2024)
- [Explainability of deep vision-based autonomous driving systems: Review and challenges](https://mlsanity.com/paper/2101.05307/) (2021)
- [Finding Skill Neurons in Pre-trained Transformer-based Language Models](https://mlsanity.com/paper/2211.07349/) (2022)
- [On the Symmetries of Deep Learning Models and their Internal Representations](https://mlsanity.com/paper/2205.14258/) (2022)
- [Semantics for Robotic Mapping, Perception and Interaction: A Survey](https://mlsanity.com/paper/2101.00443/) (2021)
- [Beyond Trivial Counterfactual Explanations with Diverse Valuable Explanations](https://mlsanity.com/paper/2103.10226/) (2021)
- [Learning Bottleneck Concepts in Image Classification](https://mlsanity.com/paper/2304.10131/) (2023)
- [Modeling Image Composition for Complex Scene Generation](https://mlsanity.com/paper/2206.00923/) (2022)
- [Context-Aware Layout to Image Generation with Enhanced Object Appearance](https://mlsanity.com/paper/2103.11897/) (2021)
- [STEEX: Steering Counterfactual Explanations with Semantics](https://mlsanity.com/paper/2111.09094/) (2021)
- [Defining and Quantifying the Emergence of Sparse Concepts in DNNs](https://mlsanity.com/paper/2111.06206/) (2021)
- [EigenGAN: Layer-Wise Eigen-Learning for GANs](https://mlsanity.com/paper/2104.12476/) (2021)
- [Explaining Deepfake Detection by Analysing Image Matching](https://mlsanity.com/paper/2207.09679/) (2022)
- [LINe: Out-of-Distribution Detection by Leveraging Important Neurons](https://mlsanity.com/paper/2303.13995/) (2023)
- [Gradient based Feature Attribution in Explainable AI: A Technical Review](https://mlsanity.com/paper/2403.10415/) (2024)
- [Interpreting Neural Networks through the Polytope Lens](https://mlsanity.com/paper/2211.12312/) (2022)
- [A Preliminary Study of the Intrinsic Relationship between Complexity and Alignment](https://mlsanity.com/paper/2308.05696/) (2023)
- [Neural Response Interpretation through the Lens of Critical Pathways](https://mlsanity.com/paper/2103.16886/) (2021)
- [FIND: A Function Description Benchmark for Evaluating Interpretability Methods](https://mlsanity.com/paper/2309.03886/) (2023)

## 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.