Deep Feature Factorization For Concept Discovery

@inproceedings{Collins2018DeepFF,
  title={Deep Feature Factorization For Concept Discovery},
  author={Edo Collins and R. Achanta and S. S{\"u}sstrunk},
  booktitle={ECCV},
  year={2018}
}
We propose Deep Feature Factorization (DFF), a method capable of localizing similar semantic concepts within an image or a set of images. We use DFF to gain insight into a deep convolutional neural network's learned features, where we detect hierarchical cluster structures in feature space. This is visualized as heat maps, which highlight semantically matching regions across a set of images, revealing what the network `perceives' as similar. DFF can also be used to perform co-segmentation and… Expand
Deep Feature Factorization for Content-Based Image Retrieval and Localization
Interpretable and Accurate Fine-grained Recognition via Region Grouping
  • Zixuan Huang, Yin Li
  • Computer Science
  • 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2020
Linear Semantics in Generative Adversarial Networks
SCOPS: Self-Supervised Co-Part Segmentation
Self-Supervised Viewpoint Learning From Image Collections
Unsupervised Part Segmentation through Disentangling Appearance and Shape
  • Shilong Liu, Lei Zhang, X. Yang, Hang Su, Jun Zhu
  • Computer Science
  • ArXiv
  • 2021
DeepCO3: Deep Instance Co-Segmentation by Co-Peak Search and Co-Saliency Detection
...
1
2
3
...

References

SHOWING 1-10 OF 40 REFERENCES
Learning Deep Features for Discriminative Localization
Network Dissection: Quantifying Interpretability of Deep Visual Representations
Co-localization with Category-Consistent Features and Geodesic Distance Propagation
Do Semantic Parts Emerge in Convolutional Neural Networks?
Very Deep Convolutional Networks for Large-Scale Image Recognition
Methods for interpreting and understanding deep neural networks
Representation Learning: A Review and New Perspectives
Image Co-localization by Mimicking a Good Detector's Confidence Score Distribution
Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials
...
1
2
3
4
...