Two-Stream Multi-Task Network for Fashion Recognition
This addresses the challenge of predicting multiple attributes in fashion clothing for real-time industrial systems, representing an incremental improvement over existing methods.
The paper tackles fashion recognition by formulating it as a multi-task learning problem involving landmark detection, category, and attribute classifications, and proposes a two-stream network with knowledge sharing strategies that achieves state-of-the-art results on a large-scale dataset.
In this paper, we present a two-stream multi-task network for fashion recognition. This task is challenging as fashion clothing always contain multiple attributes, which need to be predicted simultaneously for real-time industrial systems. To handle these challenges, we formulate fashion recognition into a multi-task learning problem, including landmark detection, category and attribute classifications, and solve it with the proposed deep convolutional neural network. We design two knowledge sharing strategies which enable information transfer between tasks and improve the overall performance. The proposed model achieves state-of-the-art results on large-scale fashion dataset comparing to the existing methods, which demonstrates its great effectiveness and superiority for fashion recognition.