Segment object by encode differences and drop duplicates with Semantic Sorting and Contrastive Flow
Segment object by encode differences and drop duplicates with Semantic Sorting and Contrastive Flow
Beyond mAP: Re-evaluating and Improving Performance in Instance Segmentation with Semantic Sorting and Contrastive Flow
arXiv paper abstract https://arxiv.org/abs/2207.01614v1
arXiv PDF paper https://arxiv.org/pdf/2207.01614v1.pdf
Top-down instance segmentation methods improve mAP by hedging bets on low-confidence predictions to match a ground truth.
Moreover, the query-key paradigm of top-down methods leads to the instance merging problem.
An excessive number of duplicate predictions leads to the (over)counting error, and the independence of category and localization branches leads to the naming error.
... propose two graph-based metrics that quantifies the amount of hedging both inter-and intra-class.
... propose a) ... encode contextual differences between instances ... and b) ... suppress duplicates and incorrectly categorized prediction.
... method encodes contextual information better than baselines ... reduces merging and hedging errors compared to state-of-the-art instance segmentation methods.
Please like and share this post if you enjoyed it using the buttons at the bottom!
Stay up to date. Subscribe to my posts https://morrislee1234.wixsite.com/website/contact
Web site with my other posts by category https://morrislee1234.wixsite.com/website
תגובות