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-10.3
Paper Title STATISTICAL DISTANCE METRIC LEARNING FOR IMAGE SET RETRIEVAL
Authors Ting-Yao Hu, Alexander G Hauptmann, Carnegie Mellon University, United States
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: [IVARS] Image & Video Analysis, Synthesis, and Retrieval
IEEE Xplore Open Preview  Click here to view in IEEE Xplore
Abstract Measuring similarity between two image sets is instrumental in many computer vision tasks. In most of the recent works, it is done by aggregating embedding features of an image as a fixed size vector, and calculating a metric in vector space (i.e. Euclidean distance). The embedding feature function can be learned by deep metric learning(DML) technique. However, methods relying on feature aggregation fail to capture the diversity and uncertainty within image sets. In this paper, we obviate the need of feature aggregation and propose a novel Statistical Distance Metric Learning(SDML) framework, which represents each image set as a probability distribution in embedding feature space, and compares two image sets by statistical distance between their distributions. Among all types of statistical distance, we choose Jeffrey's divergence, which can be obtained from two embedding feature sets by kNN based density estimator. We also design a statistical centroid loss to enhance the discriminative power of training process. SDML preserves the diversity within an image set, and the relation between two sets. We evaluate our proposed approach on gait recognition and multi-shot person re-id. The results show that SDML outperforms conventional DML, and also receives competitive/superior performance comparing to the previous state-of-the-arts.