Efficient Image Gallery Representations at Scale Through Multi-Task Learning
This work addresses the need for scalable and generalizable image representations in recommendation systems, though it appears incremental as it builds on existing MTL approaches.
The paper tackled the problem of building a universal image gallery encoder using multi-task learning to achieve generalizability for recommendation and retrieval applications, finding that MTL can address sparsity in low-resource binary tasks.
Image galleries provide a rich source of diverse information about a product which can be leveraged across many recommendation and retrieval applications. We study the problem of building a universal image gallery encoder through multi-task learning (MTL) approach and demonstrate that it is indeed a practical way to achieve generalizability of learned representations to new downstream tasks. Additionally, we analyze the relative predictive performance of MTL-trained solutions against optimal and substantially more expensive solutions, and find signals that MTL can be a useful mechanism to address sparsity in low-resource binary tasks.