UniSpector organizes visual prompt space with spatial-spectral and contrastive encoders to support open-set defect localization, beating baselines by at least 19.7% AP50b and 15.8% AP50m on the new Inspect Anything benchmark.
Frustratingly simple few-shot object detection
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
fields
cs.CV 6years
2026 6roles
background 2polarities
background 2representative citing papers
TSMa and SHARe lift COCO few-shot object detection by +10.1 nAP over prior prototype methods by enlarging class margins and refining boxes hierarchically.
CCDM, a composition-stratified feature distance, is claimed to rank synthetic object-detection training sets in near-perfect agreement with downstream mAP, but the body only tests five VisDrone candidates.
GiPL uses iterative pseudo-label self-training on support sets plus generative augmentation from VLMs to improve CD-FSOD performance on RUOD, CARPK, and CarDD under 1/5/10-shot regimes.
Adds refinement loss and auxiliary RPN branch to rebalance novel-class proposals, yielding 1-6% gains on few-shot detection benchmarks.
The NTIRE 2026 CD-FSOD Challenge report details innovative methods and performance results from 19 teams on cross-domain few-shot object detection in open- and closed-source tracks.
citing papers explorer
-
UniSpector: Towards Universal Open-set Defect Recognition via Spectral-Contrastive Visual Prompting
UniSpector organizes visual prompt space with spatial-spectral and contrastive encoders to support open-set defect localization, beating baselines by at least 19.7% AP50b and 15.8% AP50m on the new Inspect Anything benchmark.
-
Rethinking Prototype-based Similarity Learning for Few-Shot Object Detection
TSMa and SHARe lift COCO few-shot object detection by +10.1 nAP over prior prototype methods by enlarging class margins and refining boxes hierarchically.
-
Training-Free Metrics for Synthetic Object Detection Data: A Proxy for Detector Performance
CCDM, a composition-stratified feature distance, is claimed to rank synthetic object-detection training sets in near-perfect agreement with downstream mAP, but the body only tests five VisDrone candidates.
-
GiPL: Generative augmented iterative Pseudo-Labeling for Cross-Domain Few-Shot Object Detection
GiPL uses iterative pseudo-label self-training on support sets plus generative augmentation from VLMs to improve CD-FSOD performance on RUOD, CARPK, and CarDD under 1/5/10-shot regimes.
-
Proposal Refinement for Few-Shot Object Detection
Adds refinement loss and auxiliary RPN branch to rebalance novel-class proposals, yielding 1-6% gains on few-shot detection benchmarks.
-
The Second Challenge on Cross-Domain Few-Shot Object Detection at NTIRE 2026: Methods and Results
The NTIRE 2026 CD-FSOD Challenge report details innovative methods and performance results from 19 teams on cross-domain few-shot object detection in open- and closed-source tracks.