Object Detectors Emerge in Deep Scene CNNs
read the original abstract
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.
This paper has not been read by Pith yet.
Forward citations
Cited by 6 Pith papers
-
Toy Models of Superposition
Toy models demonstrate that polysemanticity arises when neural networks store more sparse features than neurons via superposition, producing a phase transition tied to polytope geometry and increased adversarial vulne...
-
Explainable Part-Based Vehicle Classifier with Spatial Awareness
A part-based vehicle classifier using spatial probability maps for parts and softmax regression achieves accuracy comparable to end-to-end CNNs with greater robustness and explainability.
-
Naturalistic Computational Cognitive Science: Towards generalizable models and theories that capture the full range of natural behavior
Advocates integrating naturalistic paradigms and AI progress into cognitive science to develop generalizable models of natural behavior while retaining experimental control and theoretical insight.
-
Convolutional neural network based decoders for surface codes
Convolutional neural network decoders achieve good performance on surface code error correction and adapt across noise models, with explainable AI used to inspect their decisions.
-
Predicting Visual Memory Schemas with Variational Autoencoders
Variational autoencoders generate higher-resolution dual-channel visual memory schema maps that separately predict true and false memorability, extending prior CNN approaches.
-
Naturalistic Computational Cognitive Science: Towards generalizable models and theories that capture the full range of natural behavior
Position paper advocating integration of naturalistic paradigms and AI models to create generalizable theories of natural human behavior and cognition.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.