每年專案
摘要
This paper develops a deep learning model for the beauty product image retrieval problem. The proposed model has two main components-an encoder and a memory. The encoder extracts and aggregates features from a deep convolutional neural network at multiple scales to get feature embeddings. With the use of an attention mechanism and a data augmentation method, it learns to focus on foreground objects and neglect background on images, so can it extract more relevant features. The memory consists of representative states of all database images as its stacks, and it can be updated during training process. Based on the memory, we introduce a distance loss to regularize embedding vectors from the encoder to be more discriminative. Our model is fully end-to-end, requires no manual feature aggregation and post-processing. Experimental results on the Perfect-500K dataset demonstrate the effectiveness of the proposed model with a significant retrieval accuracy.
原文 | ???core.languages.en_GB??? |
---|---|
主出版物標題 | MM 2020 - Proceedings of the 28th ACM International Conference on Multimedia |
發行者 | Association for Computing Machinery, Inc |
頁面 | 4728-4732 |
頁數 | 5 |
ISBN(電子) | 9781450379885 |
DOIs | |
出版狀態 | 已出版 - 12 10月 2020 |
事件 | 28th ACM International Conference on Multimedia, MM 2020 - Virtual, Online, United States 持續時間: 12 10月 2020 → 16 10月 2020 |
出版系列
名字 | MM 2020 - Proceedings of the 28th ACM International Conference on Multimedia |
---|
???event.eventtypes.event.conference???
???event.eventtypes.event.conference??? | 28th ACM International Conference on Multimedia, MM 2020 |
---|---|
國家/地區 | United States |
城市 | Virtual, Online |
期間 | 12/10/20 → 16/10/20 |
指紋
深入研究「Learning to Remember Beauty Products」主題。共同形成了獨特的指紋。專案
- 1 已完成