Component-based Attention for Large-scale Trademark Retrieval
This addresses trademark infringement detection for legal and business applications, representing a domain-specific improvement.
The paper tackles the problem of inadequate ranking accuracy in large-scale trademark retrieval systems by incorporating hard and soft attention mechanisms to focus on critical figurative elements while reducing attention to distracting elements like text and background, achieving state-of-the-art results on a challenging dataset.
The demand for large-scale trademark retrieval (TR) systems has significantly increased to combat the rise in international trademark infringement. Unfortunately, the ranking accuracy of current approaches using either hand-crafted or pre-trained deep convolution neural network (DCNN) features is inadequate for large-scale deployments. We show in this paper that the ranking accuracy of TR systems can be significantly improved by incorporating hard and soft attention mechanisms, which direct attention to critical information such as figurative elements and reduce attention given to distracting and uninformative elements such as text and background. Our proposed approach achieves state-of-the-art results on a challenging large-scale trademark dataset.