Summary of Stitchfusion: Weaving Any Visual Modalities to Enhance Multimodal Semantic Segmentation, by Bingyu Li et al.
StitchFusion: Weaving Any Visual Modalities to Enhance Multimodal Semantic Segmentationby Bingyu Li, Da Zhang, Zhiyuan…
StitchFusion: Weaving Any Visual Modalities to Enhance Multimodal Semantic Segmentationby Bingyu Li, Da Zhang, Zhiyuan…
Synthetic dual image generation for reduction of labeling efforts in semantic segmentation of micrographs with…
Learning Ordinality in Semantic Segmentationby Ricardo P. M. Cruz, Rafael Cristino, Jaime S. CardosoFirst submitted…
Diffusion for Out-of-Distribution Detection on Road Scenes and Beyondby Silvio Galesso, Philipp Schröppel, Hssan Driss,…
Downstream-Pretext Domain Knowledge Traceback for Active Learningby Beichen Zhang, Liang Li, Zheng-Jun Zha, Jiebo Luo,…
Early Preparation Pays Off: New Classifier Pre-tuning for Class Incremental Semantic Segmentationby Zhengyuan Xie, Haiquan…
Many Perception Tasks are Highly Redundant Functions of their Input Databy Rahul Ramesh, Anthony Bisulco,…
XEdgeAI: A Human-centered Industrial Inspection Framework with Data-centric Explainable Edge AI Approachby Truong Thanh Hung…
OAM-TCD: A globally diverse dataset of high-resolution tree cover mapsby Josh Veitch-Michaelis, Andrew Cottam, Daniella…
Evaluating the Adversarial Robustness of Semantic Segmentation: Trying Harder Pays Offby Levente Halmosi, Bálint Mohos,…