Outfit Completion via Conditional Set Transformation
This work addresses the problem of generating compatible clothing outfits for users in fashion recommendation systems, representing an incremental advancement in set-based retrieval methods.
The paper tackles the outfit completion problem by formulating it as a set retrieval task and proposes a conditional set transformation framework with deep neural networks and compatibility-based regularization, achieving improved accuracy, condition satisfaction, and compatibility compared to existing methods.
In this paper, we formulate the outfit completion problem as a set retrieval task and propose a novel framework for solving this problem. The proposal includes a conditional set transformation architecture with deep neural networks and a compatibility-based regularization method. The proposed method utilizes a map with permutation-invariant for the input set and permutation-equivariant for the condition set. This allows retrieving a set that is compatible with the input set while reflecting the properties of the condition set. In addition, since this structure outputs the element of the output set in a single inference, it can achieve a scalable inference speed with respect to the cardinality of the output set. Experimental results on real data reveal that the proposed method outperforms existing approaches in terms of accuracy of the outfit completion task, condition satisfaction, and compatibility of completion results.