TinySet-9M dataset and DEAL point-prompted framework deliver 31.4% relative AP75 gain over supervised baselines for small object detection with one click at inference and generalization to unseen categories.
Isnet: Shape matters for infrared small target detection
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
dataset 1
citation-polarity summary
fields
cs.CV 3years
2026 3verdicts
UNVERDICTED 3roles
dataset 1polarities
background 1representative citing papers
Na-IRSTD improves infrared small target detection by fusing native-resolution features with a selective token reduction strategy, reaching state-of-the-art results on four public benchmarks.
FeedbackSTS-Det improves moving infrared small target detection accuracy and reduces false alarms via a closed-loop spatio-temporal semantic feedback strategy and an embedded sparse semantic module that captures long-range dependencies with low overhead.
citing papers explorer
-
Generalized Small Object Detection:A Point-Prompted Paradigm and Benchmark
TinySet-9M dataset and DEAL point-prompted framework deliver 31.4% relative AP75 gain over supervised baselines for small object detection with one click at inference and generalization to unseen categories.
-
Na-IRSTD: Enhancing Infrared Small Target Detection via Native-Resolution Feature Selection and Fusion
Na-IRSTD improves infrared small target detection by fusing native-resolution features with a selective token reduction strategy, reaching state-of-the-art results on four public benchmarks.
-
FeedbackSTS-Det: Sparse Frames-Based Spatio-Temporal Semantic Feedback Network for Moving Infrared Small Target Detection
FeedbackSTS-Det improves moving infrared small target detection accuracy and reduces false alarms via a closed-loop spatio-temporal semantic feedback strategy and an embedded sparse semantic module that captures long-range dependencies with low overhead.