Multi-Scale Positive Sample Refinement for Few-Shot Object Detection

By Jiaxi Wu, Songtao Liu, Di Huang, Yunhong Wang. European Conference on Computer Vision, 2020

363 citations recorded by the source corpus.

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. Unlike previous attempts that exploit few-shot classification techniques to facilitate FSOD, this work highlights the necessity of handling the problem of scale variations, which is challenging due to the unique sample distribution. To this end, we propose a Multi-scale Positive Sample Refinement (MPSR) approach to enrich object scales in FSOD. It generates multi-scale positive samples as object pyramids and refines the prediction at various scales. We demonstrate its advantage by integrating it as an auxiliary branch to the popular architecture of Faster R-CNN with FPN, delivering a strong FSOD solution. Several experiments are conducted on PASCAL VOC and MS COCO, and the proposed approach achieves state of the art results and significantly outperforms other counterparts, which shows its effectiveness. Code is available at this https URL.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/ba4078b5956f6521f4b9589a62303e4e4c021c54

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

OTA: Optimal Transport Assignment for Object Detection (2021, methodology): “IoU based label assignment is proved effective and soon been adopted by many Faster R-CNN’s variants like [2, 12, 20, 42, 26, 49, 37], as well as many one-stage detectors like [31, 32, 25, 27, 23, 21].”
FSCE: Few-Shot Object Detection via Contrastive Proposal Encoding (2021, methodology): “MPSR [17] improves upon TFA by alleviating the scale bias inherent to few-shot dataset, but their positive reﬁnement branch demands manual selection, which is somewhat less neat.”
LARGE: Latent-Based Regression through GAN Semantics (2021, methodology): “In the context of visual media, such methods have been widely studied for classification [55, 59, 64], object detection [13, 67] and segmentation [12, 42].”
Boosting Long-tailed Object Detection via Step-wise Learning on Smooth-tail Data (2023, background): “Approaches of few-shot object detection can be categorized into meta-learning based [34, 11, 36, 38] and fine-tuning based methods [33, 35, 27].”
3rd Continual Learning Workshop Challenge on Egocentric Category and Instance Level Object Understanding (2022, background): “Research does not only cover the advancement of performance under classic learning paradigms (supervised, offline training) [20, 21, 22, 23, 24, 25, 26, 27], but also encompasses areas such as weakly-supervised learning [28, 29, 30, 31], few-shot learning [32, 33, 34, 35, 36, 37, 38], and semi-super”
A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunities (2022, neutral): “7AP ✓ MPSR[251] ECCV’20 ResNet-101 Embedding ✓ ✓ ✓ ✓ 9.”
DeFRCN: Decoupled Faster R-CNN for Few-Shot Object Detection (2021, methodology): “All detection results for comparison refer from [19, 48, 53].”