# Deep Feature Factorization For Concept Discovery

arXiv: https://arxiv.org/abs/1806.10206 · HTML: https://mlsanity.com/paper/1806.10206/

## Key facts

- Cited by 64 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Jun 2018.

## Built on by (most cited first, 30 of 64)

- [GAN Inversion: A Survey](https://mlsanity.com/paper/2101.05278/) (2021)
- [Deep ViT Features as Dense Visual Descriptors](https://mlsanity.com/paper/2112.05814/) (2021)
- [Unsupervised Semantic Segmentation by Distilling Feature Correspondences](https://mlsanity.com/paper/2203.08414/) (2022)
- [Deep Spectral Methods: A Surprisingly Strong Baseline for Unsupervised Semantic Segmentation and Localization](https://mlsanity.com/paper/2205.07839/) (2022)
- [ReCo: Retrieve and Co-segment for Zero-shot Transfer](https://mlsanity.com/paper/2206.07045/) (2022)
- [PartImageNet: A Large, High-Quality Dataset of Parts](https://mlsanity.com/paper/2112.00933/) (2021)
- [LASSIE: Learning Articulated Shapes from Sparse Image Ensemble via 3D Part Discovery](https://mlsanity.com/paper/2207.03434/) (2022)
- [Unsupervised Part Discovery from Contrastive Reconstruction](https://mlsanity.com/paper/2111.06349/) (2021)
- [Self-supervised Multi-view Stereo via Effective Co-Segmentation and Data-Augmentation](https://mlsanity.com/paper/2104.05374/) (2021)
- [Hi-LASSIE: High-Fidelity Articulated Shape and Skeleton Discovery from Sparse Image Ensemble](https://mlsanity.com/paper/2212.11042/) (2022)
- [Unsupervised Part Segmentation through Disentangling Appearance and Shape](https://mlsanity.com/paper/2105.12405/) (2021)
- [Self Correspondence Distillation for End-to-End Weakly-Supervised Semantic Segmentation](https://mlsanity.com/paper/2302.13765/) (2023)
- [Linear Semantics in Generative Adversarial Networks](https://mlsanity.com/paper/2104.00487/) (2021)
- [DeepCut: Unsupervised Segmentation using Graph Neural Networks Clustering](https://mlsanity.com/paper/2212.05853/) (2022)
- [PDiscoNet: Semantically consistent part discovery for fine-grained recognition](https://mlsanity.com/paper/2309.03173/) (2023)
- [PandA: Unsupervised Learning of Parts and Appearances in the Feature Maps of GANs](https://mlsanity.com/paper/2206.00048/) (2022)
- [GANSeg: Learning to Segment by Unsupervised Hierarchical Image Generation](https://mlsanity.com/paper/2112.01036/) (2021)
- [AutoLink: Self-supervised Learning of Human Skeletons and Object Outlines by Linking Keypoints](https://mlsanity.com/paper/2205.10636/) (2022)
- [Neural Networks are Decision Trees](https://mlsanity.com/paper/2210.05189/) (2022)
- [Unsupervised Keypoints from Pretrained Diffusion Models](https://mlsanity.com/paper/2312.00065/) (2023)
- [Unsupervised Co-part Segmentation through Assembly](https://mlsanity.com/paper/2106.05897/) (2021)
- [Interpreting and Analysing CLIP's Zero-Shot Image Classification via Mutual Knowledge](https://mlsanity.com/paper/2410.13016/) (2024)
- [Training and Tuning Generative Neural Radiance Fields for Attribute-Conditional 3D-Aware Face Generation](https://mlsanity.com/paper/2208.12550/) (2022)
- [Benchmarking XAI Explanations with Human-Aligned Evaluations](https://mlsanity.com/paper/2411.02470/) (2024)
- [HP-Capsule: Unsupervised Face Part Discovery by Hierarchical Parsing Capsule Network](https://mlsanity.com/paper/2203.10699/) (2022)
- [Uncovering the Inner Workings of STEGO for Safe Unsupervised Semantic Segmentation](https://mlsanity.com/paper/2304.07314/) (2023)
- [Optical Flow boosts Unsupervised Localization and Segmentation](https://mlsanity.com/paper/2307.13640/) (2023)
- [Post-hoc Part-prototype Networks](https://mlsanity.com/paper/2406.03421/) (2024)
- [Unsupervised Discovery of 3D Hierarchical Structure with Generative Diffusion Features](https://mlsanity.com/paper/2305.00067/) (2023)
- [Unsupervised Object Discovery: A Comprehensive Survey and Unified Taxonomy](https://mlsanity.com/paper/2411.00868/) (2024)

## Abstract (arXiv)

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 co-localization, and we report state-of-the-art results on these tasks.