Search for Concepts: Learning Visual Concepts Using Direct Optimization
Pradyumna Reddy (University College London),* Paul Guerrero (Adobe), Niloy Mitra (University College London)
The 33rd British Machine Vision Conference
Abstract
Finding an unsupervised decomposition of an image into individual objects is a key step to leverage compositionality and to perform symbolic reasoning. Traditionally, the 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, un-amortized optimization, using 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.Video
Citation
@inproceedings{Reddy_2022_BMVC,
author = {Pradyumna Reddy and Paul Guerrero and Niloy Mitra},
title = {Search for Concepts: Learning Visual Concepts Using Direct Optimization},
booktitle = {33rd British Machine Vision Conference 2022, {BMVC} 2022, London, UK, November 21-24, 2022},
publisher = {{BMVA} Press},
year = {2022},
url = {https://bmvc2022.mpi-inf.mpg.de/0810.pdf}
}
Copyright © 2022
The British Machine Vision Conference is organised by