Reddy, P; Guerrero, P; Mitra, NJ; (2022) Search for Concepts: Discovering Visual Concepts Using Direct Optimization. In: Proceedings of the 33rd British Machine Vision Conference 2022. British Machine Vision Association (BMVA): London, UK.

Preview

PDF 0810.pdf - Published Version Download (5MB) | Preview

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.

Download activity - last month

Export as XMLCSVJSON

Download activity - last 12 months

Export as JSONCSVXML

Downloads by country - last 12 months

Export as XMLJSONCSV

Archive Staff Only

View Item