Instance Retrieval at Fine-grained Level Using Multi-Attribute Recognition
This work addresses fine-grained retrieval for applications like fashion and bird species identification, but it is incremental as it builds on existing multi-attribute and bilinear CNN methods.
The paper tackles fine-grained instance retrieval by using a multi-attribute recognition model with global features, eliminating the need for landmarks or part annotations, and adapts it for mobile devices via bilinear CNN to reduce parameters. Results on DeepFashion and CUB200 datasets show promising performance, particularly in texture and color.
In this paper, we present a method for instance ranking and retrieval at fine-grained level based on the global features extracted from a multi-attribute recognition model which is not dependent on landmarks information or part-based annotations. Further, we make this architecture suitable for mobile-device application by adopting the bilinear CNN to make the multi-attribute recognition model smaller (in terms of the number of parameters). The experiments run on the Dress category of DeepFashion In-Shop Clothes Retrieval and CUB200 datasets show that the results of instance retrieval at fine-grained level are promising for these datasets, specially in terms of texture and color.