Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles
Explore this paper's citation graph
Summary
A novel unsupervised learning approach to build features suitable for object detection and classification and to facilitate the transfer of features to other tasks, the context-free network (CFN), a siamese-ennead convolutional neural network is introduced.
- Type
- preprint
- Published
- 2016-03-30
- Cited by
- 3,292
- References
- 43
- Access
- Open access
- OpenAlex
- https://openalex.org/W2949497014
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:187547
Keywords
Jigsaw, Computer science, Artificial intelligence, Convolutional neural network, Transfer of learning
References
- Unsupervised Learning of Visual Representations Using Videos
- Unsupervised Visual Representation Learning by Context Prediction
- Learning to See by Moving
- Information processing in dynamical systems: foundations of harmony theory
- Understanding Neural Networks Through Deep Visualization
- Fully convolutional networks for semantic segmentation
- Understanding deep image representations by inverting them
- A fully automated greedy square jigsaw puzzle solver
- Apictorial Jigsaw Puzzles: The Computer Solution of a Problem in Pattern Recognition
- A jigsaw-puzzle imagery task for assessing active visuospatial processes in old and young people
- Auto-association by multilayer perceptrons and singular value decomposition
- The Pascal Visual Object Classes Challenge: A Retrospective
- Nonlinear dimensionality reduction by locally linear embedding.
- Laplacian Eigenmaps for Dimensionality Reduction and Data Representation
- Autoencoders, Minimum Description Length and Helmholtz Free Energy
- Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
- Sparse coding with an overcomplete basis set: a strategy employed by V1?
- ImageNet: A large-scale hierarchical image database
- Building high-level features using large scale unsupervised learning
- Object class recognition by unsupervised scale-invariant learning
Cited by
- Interpreting Deep Visual Representations via Network Dissection
- Deep Successor Reinforcement Learning
- What makes ImageNet good for transfer learning?
- Unsupervised Learning of Discriminative Attributes and Visual Representations
- Exploiting Spatio-Temporal Structure with Recurrent Winner-Take-All Networks
- Semi-Supervised Learning with Context-Conditional Generative Adversarial Networks
- Quad-Networks: Unsupervised Learning to Rank for Interest Point Detection
- Sentence Ordering and Coherence Modeling using Recurrent Neural Networks
- Split-Brain Autoencoders: Unsupervised Learning by Cross-Channel Prediction
- Unsupervised learning of image motion by recomposing sequences
- Learning Features by Watching Objects Move
- An Adversarial Regularisation for Semi-Supervised Training of Structured Output Neural Networks
- Supervision Beyond Manual Annotations for Learning Visual Representations
- PixelNet: Representation of the pixels, by the pixels, and for the pixels
- Colorization as a Proxy Task for Visual Understanding
- Toward an Integration of Deep Learning and Neuroscience
- DeepPermNet: Visual Permutation Learning
- Weakly-Supervised Spatial Context Networks
- Network Dissection: Quantifying Interpretability of Deep Visual Representations
- Unsupervised Learning of Object Landmarks by Factorized Spatial Embeddings
Related papers
- Learning Image Representations by Completing Damaged Jigsaw Puzzles
- Self-supervised Learning with Fully Convolutional Networks
- Self-supervised multi-task learning for semantic segmentation of urban scenes
- Transfer Learning Method for Very Deep CNN for Text Classification and Methods for its Evaluation
- OBoW: Online Bag-of-Visual-Words Generation for Self-Supervised Learning
- Representation learning for natural language
- Online Bag-of-Visual-Words Generation for Unsupervised Representation Learning
- Learning Robust Visual-Semantic Embeddings