Semantic Relation Reasoning for Shot-Stable Few-Shot Object Detection

Zhu, Chenchen; Chen, Fangyi; Ahmed, Uzair; Shen, Zhiqiang; Savvides, Marios

doi:10.1109/cvpr46437.2021.00867

Cited by 116 publications

(55 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It measures the similarity between different region proposals and adds a contrastive loss function to maximize the agreement between region proposals from the same category and promote the distinctiveness of region proposals from The third category of classification-based methods is semantic-based methods. SRR-FSD [100] is a FSOD method based on semantic relation reasoning to improve the classification performance of the model. This method first constructs a semantic space and projects the visual features into this semantic space.…”

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

“…Few-shot object detection needs to not only recognize novel objects using a few train-ing examples, but also localize objects in the image. Existing works can be mainly grouped into the following two categories according to the model architecture: (1) Single-branch based methods [36,45,47,51,52]. These methods attempt to learn object detection using the long-tailed training data from both data-abundant base classes and data-scarce novel classes.…”

Section: Related Workmentioning

confidence: 99%

“…Current methods for this task mainly follow a twostage learning paradigm [45] to transfer the knowledge learned from the data-abundant base classes to assist in object detection for few-shot novel classes. The detailed model architectures vary in different works, which can be roughly divided into two categories, single-branch based methods [36,45,47,51,52] and two-branch based methods [8,12,13,20,23,49]. (1) Single-branch based methods employ a typical object detection model, e.g., Faster R-CNN [33], and build a multi-class classifier for detection.…”

Section: Introductionmentioning

confidence: 99%

Few-Shot Object Detection with Fully Cross-Transformer

Han¹,

Ma²,

Huang³

et al. 2022

Preprint

View full text Add to dashboard Cite

Few-shot object detection (FSOD), with the aim to detect novel objects using very few training examples, has recently attracted great research interest in the community. Metriclearning based methods have been demonstrated to be effective for this task using a two-branch based siamese network, and calculate the similarity between image regions and fewshot examples for detection. However, in previous works, the interaction between the two branches is only restricted in the detection head, while leaving the remaining hundreds of layers for separate feature extraction. Inspired by the recent work on vision transformers and vision-language transformers, we propose a novel Fully Cross-Transformer based model (FCT) for FSOD by incorporating cross-transformer into both the feature backbone and detection head. The asymmetric-batched cross-attention is proposed to aggregate the key information from the two branches with different batch sizes. Our model can improve the few-shot similarity learning between the two branches by introducing the multilevel interactions. Comprehensive experiments on both PAS-CAL VOC and MSCOCO FSOD benchmarks demonstrate the effectiveness of our model.

show abstract

“…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]. Orthogonal to existing work, we address few-shot detection by hallucinating additional data and enriching sample variation.…”

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

Semantic Relation Reasoning for Shot-Stable Few-Shot Object Detection

Cited by 116 publications

References 27 publications

A Survey of Deep Learning for Low-Shot Object Detection

A Survey of Deep Learning for Low-Shot Object Detection

Few-Shot Object Detection with Fully Cross-Transformer

Hallucination Improves Few-Shot Object Detection

Contact Info

Product

Resources

About