Performance with different loss functions. “ ” and “**” denote significance levels of and , respectively, from a two-sided paired t-test when comparing our best model with others. The best results are shown in bold.

Performance with different loss functions. “ ” and “**” denote significance levels of and , respectively, from a two-sided paired t-test when comparing our best model with others. The best results are shown in bold.

<p>Performance with different loss functions. “ ” and “**” denote significance levels of and , respectively, from a two-sided paired t-test when comparing our best model with others. The best results are shown in bold.</p>

Saved in:

Bibliographic Details
Main Author:	Hua Wang (13530) (author)
Other Authors:	Yiming Li (40290) (author), Linwei Qiu (22110240) (author), Jicong Zhang (3700579) (author), Jingfei Hu (8894756) (author)
Published:	2025
Subjects:	Developmental Biology Science Policy Space Science Biological Sciences not elsewhere classified Mathematical Sciences not elsewhere classified Chemical Sciences not elsewhere classified Information Systems not elsewhere classified typical public dataset soft aggregation operation lower computational resources embed features extracted diversified receptive field challenging task due 86 %, 91 81 %, 92 25 %, 92 local feature maps different tissue structures collect global cues free attention mechanism free attention block art segmentation performance free attention range cues local structure different angles rotation consistency poor contrast novel transformer jaccard index embryo images dice coefficient catches non blastocyst components blast transformer based architecture ambiguous boundaries 45 %.
Tags:	Add Tag No Tags, Be the first to tag this record!

Cannot write session to /tmp/vufind_sessions/sess_86lrgm2o3qck5o79i0b71ln4fb