19 papers with code • 4 benchmarks • 3 datasets
Target: To detect objects of novel categories with just a few training samples.
Such a simple approach outperforms the meta-learning methods by roughly 2~20 points on current benchmarks and sometimes even doubles the accuracy of the prior methods.
Ranked #7 on Few-Shot Object Detection on MS-COCO (30-shot)
The feature learner extracts meta features that are generalizable to detect novel object classes, using training data from base classes with sufficient samples.
Ranked #11 on Few-Shot Object Detection on MS-COCO (30-shot)
To train our network, we contribute a new dataset that contains 1000 categories of various objects with high-quality annotations.
Ranked #5 on Few-Shot Object Detection on MS-COCO (10-shot) (using extra training data)
We demonstrate empirical results on MS Coco highlighting challenges of the one-shot setting: while transferring knowledge about instance segmentation to novel object categories works very well, targeting the detection network towards the reference category appears to be more difficult.
Ranked #1 on One-Shot Instance Segmentation on COCO
Resembling the rapid learning capability of human, low-shot learning empowers vision systems to understand new concepts by training with few samples.
Ranked #10 on Few-Shot Object Detection on MS-COCO (10-shot)
Distance metric learning (DML) has been successfully applied to object classification, both in the standard regime of rich training data and in the few-shot scenario, where each category is represented by only a few examples.
Few-shot object detection (FSOD) helps detectors adapt to unseen classes with few training instances, and is useful when manual annotation is time-consuming or data acquisition is limited.
Ranked #6 on Few-Shot Object Detection on MS-COCO (30-shot)
We present Few-Shot object detection via Contrastive proposals Encoding (FSCE), a simple yet effective approach to learning contrastive-aware object proposal encodings that facilitate the classification of detected objects.
Ranked #3 on Few-Shot Object Detection on MS-COCO (30-shot)
Second, we introduce a novel regularized transfer learning framework for low-shot detection, where the transfer knowledge (TK) and background depression (BD) regularizations are proposed to leverage object knowledge respectively from source and target domains, in order to further enhance fine-tuning with a few target images.
Ranked #12 on Few-Shot Object Detection on MS-COCO (30-shot)