UHR-DETR delivers 2.8% higher mAP and 10x faster inference than sliding-window baselines for small object detection in UHR remote sensing imagery on a single 24GB GPU.
Imagenet large scale visual recognition challenge,
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.CV 3years
2026 3verdicts
UNVERDICTED 3representative citing papers
RF-Sampling enhances flow matching models by implicitly performing gradient ascent on text-image alignment scores via linear textual combinations and flow inversion.
Natural Selection (NS) dynamically reweights DNN training losses by estimating each sample's competitive status inside groups assembled as composite images.
citing papers explorer
-
UHR-DETR: Efficient End-to-End Small Object Detection for Ultra-High-Resolution Remote Sensing Imagery
UHR-DETR delivers 2.8% higher mAP and 10x faster inference than sliding-window baselines for small object detection in UHR remote sensing imagery on a single 24GB GPU.
-
Reflective Flow Sampling Enhancement
RF-Sampling enhances flow matching models by implicitly performing gradient ascent on text-image alignment scores via linear textual combinations and flow inversion.
-
Evolution-Inspired Sample Competition for Deep Neural Network Optimization
Natural Selection (NS) dynamically reweights DNN training losses by estimating each sample's competitive status inside groups assembled as composite images.