2021 IEEE International Conference on Acoustics, Speech and Signal Processing

6-11 June 2021 • Toronto, Ontario, Canada

Extracting Knowledge from Information

2021 IEEE International Conference on Acoustics, Speech and Signal Processing

6-11 June 2021 • Toronto, Ontario, Canada

Extracting Knowledge from Information
Login Paper Search My Schedule Paper Index Help

My ICASSP 2021 Schedule

Note: Your custom schedule will not be saved unless you create a new account or login to an existing account.
  1. Create a login based on your email (takes less than one minute)
  2. Perform 'Paper Search'
  3. Select papers that you desire to save in your personalized schedule
  4. Click on 'My Schedule' to see the current list of selected papers
  5. Click on 'Printable Version' to create a separate window suitable for printing (the header and menu will appear, but will not actually print)

Paper Detail

Paper IDIVMSP-10.2
Paper Title A RANKED SIMILARITY LOSS FUNCTION WITH PAIR WEIGHTING FOR DEEP METRIC LEARNING
Authors Jian Wang, Zhichao Zhang, Shanghai Ocean University, China; Dongmei Huang, Shanghai University of Electric Power, China; Wei Song, Shanghai Ocean University, China; Quanmiao Wei, Donghai Bureau of the Ministry of Natural Resources, China; Xinyue Li, Shanghai Ocean University, China
SessionIVMSP-10: Metric Learning and Interpretability
LocationGather.Town
Session Time:Wednesday, 09 June, 13:00 - 13:45
Presentation Time:Wednesday, 09 June, 13:00 - 13:45
Presentation Poster
Topic Image, Video, and Multidimensional Signal Processing: [IVTEC] Image & Video Processing Techniques
IEEE Xplore Open Preview  Click here to view in IEEE Xplore
Abstract Metric learning is a widely-used method for image retrieval. The object of metric learning is to limit the distance between similar samples and increase the distance between samples of different classes through learning. Many studies tend to pay more attention to keep the distance between positive and negative samples, but ignore the distance between different classes of negative samples. In fact, query samples should be separated from negative samples of different classes by different distances. To address these problems, we propose to build a ranked similarity loss function with pair weighting (dubbed RMS loss). The proposed RMS loss can keep a distance between samples of different classes by weighting the negative samples according to the sorting order. Meanwhile, it further widens the distance between positive and negative samples by different processing of similarity of positive pairs and negative pairs. The effectiveness of our method is evaluated by extensive experiments on four public datasets and compared with state-of-the-art methods. The results show the proposed method obtains new performance on four public datasets, e.g., reaching 67.4% on CUB200 at Recall@1.