# Search for Concepts: Discovering Visual Concepts Using Direct Optimization

arXiv: https://arxiv.org/abs/2210.14808 · HTML: https://mlsanity.com/paper/2210.14808/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 34 of its 50 references that are in the map.
- First posted on arXiv 25 Oct 2022.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)

## Builds on (most cited first, 30 of 34)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs](https://mlsanity.com/paper/1606.00915/) (2016)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations](https://mlsanity.com/paper/1602.07332/) (2016)
- [Pyramid Scene Parsing Network](https://mlsanity.com/paper/1612.01105/) (2016)
- [Implicit Neural Representations with Periodic Activation Functions](https://mlsanity.com/paper/2006.09661/) (2020)
- [Rich feature hierarchies for accurate object detection and semantic segmentation](https://mlsanity.com/paper/1311.2524/) (2013)
- [CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning](https://mlsanity.com/paper/1612.06890/) (2016)
- [Object-Centric Learning with Slot Attention](https://mlsanity.com/paper/2006.15055/) (2020)
- [GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fields](https://mlsanity.com/paper/2011.12100/) (2020)
- [Dynamic Routing Between Capsules](https://mlsanity.com/paper/1710.09829/) (2017)
- [MONet: Unsupervised Scene Decomposition and Representation](https://mlsanity.com/paper/1901.11390/) (2019)
- [Multi-Object Representation Learning with Iterative Variational Inference](https://mlsanity.com/paper/1903.00450/) (2019)
- [Visual Relationship Detection with Language Priors](https://mlsanity.com/paper/1608.00187/) (2016)
- [On the Binding Problem in Artificial Neural Networks](https://mlsanity.com/paper/2012.05208/) (2020)
- [GENESIS: Generative Scene Inference and Sampling with Object-Centric Latent Representations](https://mlsanity.com/paper/1907.13052/) (2019)
- [Recurrent Independent Mechanisms](https://mlsanity.com/paper/1909.10893/) (2019)
- [BlockGAN: Learning 3D Object-aware Scene Representations from Unlabelled Images](https://mlsanity.com/paper/2002.08988/) (2020)
- [Neural Expectation Maximization](https://mlsanity.com/paper/1708.03498/) (2017)
- [GENESIS-V2: Inferring Unordered Object Representations without Iterative Refinement](https://mlsanity.com/paper/2104.09958/) (2021)
- [Decomposing 3D Scenes into Objects via Unsupervised Volume Segmentation](https://mlsanity.com/paper/2104.01148/) (2021)
- [Stacked Capsule Autoencoders](https://mlsanity.com/paper/1906.06818/) (2019)
- [Deep Set Prediction Networks](https://mlsanity.com/paper/1906.06565/) (2019)
- [Unsupervised Layered Image Decomposition into Object Prototypes](https://mlsanity.com/paper/2104.14575/) (2021)
- [SegNet: A Deep Convolutional Encoder-Decoder Architecture for Robust Semantic Pixel-Wise Labelling](https://mlsanity.com/paper/1505.07293/) (2015)
- [MarioNette: Self-Supervised Sprite Learning](https://mlsanity.com/paper/2104.14553/) (2021)

## Built on by (most cited first, 2 of 2)

- [AudioSlots: A slot-centric generative model for audio separation](https://mlsanity.com/paper/2305.05591/) (2023)
- [The Learnable Typewriter: A Generative Approach to Text Analysis](https://mlsanity.com/paper/2302.01660/) (2023)

## Abstract (arXiv)

Finding an unsupervised decomposition of an image into individual objects is a key step to leverage compositionality and to perform symbolic reasoning. Traditionally, this problem is solved using amortized inference, which does not generalize beyond the scope of the training data, may sometimes miss correct decompositions, and requires large amounts of training data. We propose finding a decomposition using direct, unamortized optimization, via a combination of a gradient-based optimization for differentiable object properties and global search for non-differentiable properties. We show that using direct optimization is more generalizable, misses fewer correct decompositions, and typically requires less data than methods based on amortized inference. This highlights a weakness of the current prevalent practice of using amortized inference that can potentially be improved by integrating more direct optimization elements.