FSCE: Few-Shot Object Detection via Contrastive Proposal Encoding

Sun, Bo; Li, Banghuai; Cai, Shengcai; Yuan, Ye; Zhang, Chi

doi:10.1109/cvpr46437.2021.00727

Cited by 327 publications

(280 citation statements)

References 26 publications

Supporting

Mentioning

279

Contrasting

Order By: Relevance

“…The second category of classification-based methods is contrastive learning. Bo Sun et al [70] propose a few-shot object detection method via contrastive proposal encoding (FSCE). FSCE first proposes a stronger baseline than TFA which adapts better to novel data.…”

Section: Transfer-learning Methodsmentioning

confidence: 99%

A Survey of Deep Learning for Low-Shot Object Detection

Huang¹,

Zhang²,

Xue³

et al. 2021

Preprint

View full text Add to dashboard Cite

Object detection is a fundamental task in computer vision and image processing. Current deep learning based object detectors have been highly successful with abundant labeled data. But in real life, it is not guaranteed that each object category has enough labeled samples for training. These large object detectors are easy to overfit when the training data is limited. Therefore, it is necessary to introduce few-shot learning and zeroshot learning into object detection, which can be named low-shot object detection together. Low-Shot Object Detection (LSOD) aims to detect objects from a few or even zero labeled data, which can be categorized into few-shot object detection (FSOD) and zero-shot object detection (ZSD), respectively. This paper conducts a comprehensive survey for deep learning based FSOD and ZSD. First, this survey classifies methods for FSOD and ZSD into different categories and discusses the pros and cons of them. Second, this survey reviews dataset settings and evaluation metrics for FSOD and ZSD, then analyzes the performance of different methods on these benchmarks. Finally, this survey discusses future challenges and promising directions for FSOD and ZSD.

show abstract

Section: Transfer-learning Methodsmentioning

confidence: 99%

A Survey of Deep Learning for Low-Shot Object Detection

Huang¹,

Zhang²,

Xue³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Another line of work focuses on improving the proposal generation process, by introducing attention mechanisms and generating class-aware features for classifiers [7,17,24,35,44,48]. Some work modifies the proposal ranking process and ranks proposals based on similarity with query images [7,17].…”

Section: Related Workmentioning

confidence: 99%

“…An RPN ensemble method is proposed to avoid missing highly informative proposal boxes [48]. Contrastive-aware object proposal encodings are further learned to reduce the possibility of misclassifying novel class objects to confusable classes [35]. Additional information has also been shown helpful, such as semantic relations [50] and multi-scale representations [43].…”

Section: Related Workmentioning

confidence: 99%

Hallucination Improves Few-Shot Object Detection

Zhang¹,

Wang²

2021

Preprint

View full text Add to dashboard Cite

Learning to detect novel objects from few annotated examples is of great practical importance. A particularly challenging yet common regime occurs when there are extremely limited examples (less than three). One critical factor in improving few-shot detection is to address the lack of variation in training data. We propose to build a better model of variation for novel classes by transferring the shared within-class variation from base classes. To this end, we introduce a hallucinator network that learns to generate additional, useful training examples in the region of interest (RoI) feature space, and incorporate it into a modern object detection model. Our approach yields significant performance improvements on two state-of-the-art few-shot detectors with different proposal generation procedures. In particular, we achieve new state of the art in the extremelyfew-shot regime on the challenging COCO benchmark.

show abstract

“…Contrastive learning relies on both positive and negative examples of a class during training. This type of learning has shown to be a successful auxiliary task independently for the few-shot paradigm [3,6,16,17,19,21,25,29,34,47] and for segmentation tasks [14,40]. Inspired by prior work, we offer the first examination of using contrastive learning for few-shot semantic segmentation with a fine-tuning approach.…”

Section: Related Workmentioning

confidence: 99%

Generalized Few-Shot Semantic Segmentation: All You Need is Fine-Tuning

Myers-Dean¹,

Zhao²,

Price³

et al. 2021

Preprint

View full text Add to dashboard Cite

Generalized few-shot semantic segmentation was introduced to move beyond only evaluating few-shot segmentation models on novel classes to include testing their ability to remember base classes. While all approaches currently are based on meta-learning, they perform poorly and saturate in learning after observing only a few shots. We propose the first fine-tuning solution, and demonstrate that it addresses the saturation problem while achieving stateof-art results on two datasets, PASCAL-5 i and COCO-20 i . We also show it outperforms existing methods whether finetuning multiple final layers or only the final layer. Finally, we present a triplet loss regularization that shows how to redistribute the balance of performance between novel and base categories so that there is a smaller gap between them.

show abstract

FSCE: Few-Shot Object Detection via Contrastive Proposal Encoding

Cited by 327 publications

References 26 publications

A Survey of Deep Learning for Low-Shot Object Detection

A Survey of Deep Learning for Low-Shot Object Detection

Hallucination Improves Few-Shot Object Detection

Generalized Few-Shot Semantic Segmentation: All You Need is Fine-Tuning

Contact Info

Product

Resources

About