EIC-LIE uses an event-illumination collaborative module and illumination-aware event filter plus a new real-world dataset to improve low-light image enhancement over prior methods.
Rethinking semantic segmen- tation from a sequence-to-sequence perspective with trans- formers
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
fields
cs.CV 4years
2026 4representative citing papers
A YOLO26 model trained on four leaf segmentation datasets reaches 83.9% mean mAP50-95 on their test sets but only 40.2% on a new 23-species benchmark, revealing substantial cross-domain generalization gaps.
PEPR reframes learning with privileged event data as predicting latent event features from RGB to improve domain generalization in object detection and segmentation without direct cross-modal alignment.
DGM-Net reaches 82.3% mIoU on Cityscapes and 45.24% on ADE20K using directional geometric guidance inside a linear-complexity Mamba backbone, without heavy pretraining or large models.
citing papers explorer
-
Event-Illumination Collaborative Low-light Image Enhancement with a High-resolution Real-world Dataset
EIC-LIE uses an event-illumination collaborative module and illumination-aware event filter plus a new real-world dataset to improve low-light image enhancement over prior methods.
-
ReLeaf: Benchmarking Leaf Segmentation across Domains and Species
A YOLO26 model trained on four leaf segmentation datasets reaches 83.9% mean mAP50-95 on their test sets but only 40.2% on a new 23-species benchmark, revealing substantial cross-domain generalization gaps.
-
PEPR: Privileged Event-based Predictive Regularization for Domain Generalization
PEPR reframes learning with privileged event data as predicting latent event features from RGB to improve domain generalization in object detection and segmentation without direct cross-modal alignment.
-
Breaking the Resource Wall: Geometry-Guided Sequence Modeling for Efficient Semantic Segmentation
DGM-Net reaches 82.3% mIoU on Cityscapes and 45.24% on ADE20K using directional geometric guidance inside a linear-complexity Mamba backbone, without heavy pretraining or large models.