2021 IEEE International Conference on Acoustics, Speech and Signal Processing
6-11 June 2021 • Toronto, Ontario, Canada
Extracting Knowledge from Information
IVMSP-10: Metric Learning and Interpretability |
| Session Type: Poster |
| Time: Wednesday, 9 June, 13:00 - 13:45 |
| Location: Gather.Town |
| Virtual Session: View on Virtual Platform |
| Session Chair: Shashikant Patil, SVKMs NMIMS Shirpur |
| IVMSP-10.1: DEEP SEMI-SUPERVISED METRIC LEARNING VIA IDENTIFICATION OF MANIFOLD MEMBERSHIPS |
| Furen Zhuang; University of Illinois at Urbana-Champaign |
| Pierre Moulin; University of Illinois at Urbana-Champaign |
| IVMSP-10.2: A RANKED SIMILARITY LOSS FUNCTION WITH PAIR WEIGHTING FOR DEEP METRIC LEARNING |
| Jian Wang; Shanghai Ocean University |
| Zhichao Zhang; Shanghai Ocean University |
| Dongmei Huang; Shanghai University of Electric Power |
| Wei Song; Shanghai Ocean University |
| Quanmiao Wei; Donghai Bureau of the Ministry of Natural Resources |
| Xinyue Li; Shanghai Ocean University |
| IVMSP-10.3: STATISTICAL DISTANCE METRIC LEARNING FOR IMAGE SET RETRIEVAL |
| Ting-Yao Hu; Carnegie Mellon University |
| Alexander G Hauptmann; Carnegie Mellon University |
| IVMSP-10.4: DISTRIBUTION-AWARE HIERARCHICAL WEIGHTING METHOD FOR DEEP METRIC LEARNING |
| Yinong Zhu; Chongqing University |
| Yong Feng; Chongqing University |
| Mingliang Zhou; University of Macau |
| Baohua Qiang; Guilin University of Electronic Technology |
| Leong Hou U; University of Macau |
| Jiajie Zhu; Chongqing University |
| IVMSP-10.5: INTEGRATED GRAD-CAM: SENSITIVITY-AWARE VISUAL EXPLANATION OF DEEP CONVOLUTIONAL NETWORKS VIA INTEGRATED GRADIENT-BASED SCORING |
| Sam Sattarzadeh; University of Toronto |
| Mahesh Sudhakar; University of Toronto |
| Konstantinos N. Plataniotis; University of Toronto |
| Jongseong Jang; LG AI Research |
| Yeonjeong Jeong; LG AI Research |
| Hyunwoo Kim; LG AI Research |
| IVMSP-10.6: VISUALIZING ASSOCIATION IN EXEMPLAR-BASED CLASSIFICATION |
| Taiga Kashima; University of Tokyo |
| Ryuichiro Hataya; University of Tokyo |
| Hideki Nakayama; University of Tokyo |