Meta R-CNN: Towards General Solver for Instance-Level Low-Shot Learning

@article{Yan2019MetaRT,
  title={Meta R-CNN: Towards General Solver for Instance-Level Low-Shot Learning},
  author={Xiaopeng Yan and Ziliang Chen and Anni Xu and Xiaoxi Wang and Xiaodan Liang and Liang Lin},
  journal={2019 IEEE/CVF International Conference on Computer Vision (ICCV)},
  year={2019},
  pages={9576-9585}
}
Resembling the rapid learning capability of human, low-shot learning empowers vision systems to understand new concepts by training with few samples. [...] Key Method Specifically, we introduce a Predictor-head Remodeling Network (PRN) that shares its main backbone with Faster /Mask R-CNN. PRN receives images containing low-shot objects with their bounding boxes or masks to infer their class attentive vectors.Expand
Meta-DETR: Few-Shot Object Detection via Unified Image-Level Meta-Learning
TLDR
A novel meta-detector framework, namely Meta-DETR, which eliminates region-wise prediction and instead meta-learns object localization and classification at image level in a unified and complementary manner and design a simple but effective Semantic Alignment Mechanism to facilitate meta-learning with deep networks. Expand
MM-FSOD: Meta and metric integrated few-shot object detection
TLDR
An effective object detection framework (MM-FSOD) that integrates metric learning and meta-learning to tackle the few-shot object detection task and achieves state-of-the-art (SOTA) results is presented. Expand
DeFRCN: Decoupled Faster R-CNN for Few-Shot Object Detection
TLDR
Decoupled Faster R-CNN (DeFRCN) is proposed, which is remarkably superior to other existing approaches and establishes a new state-of-the-art in few-shot literature. Expand
Meta-RetinaNet for Few-shot Object Detection
TLDR
A novel Meta-RetinaNet for FSD is proposed, which avoids a biased meta-learner and improves its generalization ability and achieves the state-of-theart performance on the multiple settings of Pascal VOC and COCO datasets. Expand
One-Shot Object Detection without Fine-Tuning
TLDR
A two-stage model consisting of a first stage Matching-FCOS network and a second stage Structure-Aware Relation Module is introduced, the combination of which integrates metric learning with an anchor-free Faster R-CNN-style detection pipeline, eventually eliminating the need to fine-tune on the support images. Expand
Many-shot from Low-shot: Learning to Annotate using Mixed Supervision for Object Detection
TLDR
This work introduces, for the first time, an online annotation module (OAM) that learns to generate a many-shot set of \emph{reliable} annotations from a larger volume of weakly labelled images, resulting in a fully end-to-end strategy that only requires a low- shot set of fully annotated images. Expand
Meta-RCNN: Meta Learning for Few-Shot Object Detection
TLDR
This paper proposes a new meta-learning framework for object detection named "Meta-RCNN", which learns the ability to perform few-shot detection via meta- learning, and demonstrates the effectiveness of Meta- RCNN in few- shot detection on three datasets with promising results. Expand
Dynamic Relevance Learning for Few-Shot Object Detection
TLDR
A dynamic relevance learning model is proposed, which utilizes the relationship between all support images and Region of Interest on the query images to construct a dynamic graph convolutional network (GCN) and can guide the detector to improve the class representation implicitly. Expand
Few-Shot Object Detection via Knowledge Transfer
TLDR
This paper introduces a few-shot object detection via knowledge transfer, which aims to detect objects from a few training examples with explicit guidance of prior knowledge that represents correlations among categories. Expand
Active Image Sampling on Canonical Views for Novel Object Detection
TLDR
A novel on-line viewpoint exploration (OLIVE) method that defines goodness-of-view by combining informativeness of visual features and consistency of model-based object detection, and systematically explores and selects viewpoints to boost learning efficiency is proposed. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 59 REFERENCES
Mask R-CNN
TLDR
This work presents a conceptually simple, flexible, and general framework for object instance segmentation that outperforms all existing, single-model entries on every task, including the COCO 2016 challenge winners. Expand
Few-Shot Object Detection via Feature Reweighting
TLDR
This work develops a few-shot object detector that can learn to detect novel objects from only a few annotated examples, using a meta feature learner and a reweighting module within a one-stage detection architecture. Expand
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
TLDR
This work introduces a Region Proposal Network (RPN) that shares full-image convolutional features with the detection network, thus enabling nearly cost-free region proposals and further merge RPN and Fast R-CNN into a single network by sharing their convolutionAL features. Expand
Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
TLDR
This paper proposes a simple and scalable detection algorithm that improves mean average precision (mAP) by more than 30% relative to the previous best result on VOC 2012 -- achieving a mAP of 53.3%. Expand
Learning to Compare: Relation Network for Few-Shot Learning
TLDR
A conceptually simple, flexible, and general framework for few-shot learning, where a classifier must learn to recognise new classes given only few examples from each, which is easily extended to zero- shot learning. Expand
RepMet: Representative-Based Metric Learning for Classification and Few-Shot Object Detection
TLDR
This work proposes a new method for DML that simultaneously learns the backbone network parameters, the embedding space, and the multi-modal distribution of each of the training categories in that space, in a single end-to-end training process. Expand
Learning to Refine Object Segments
TLDR
This work proposes to augment feedforward nets for object segmentation with a novel top-down refinement approach that is capable of efficiently generating high-fidelity object masks and is 50 % faster than the original DeepMask network. Expand
R-FCN: Object Detection via Region-based Fully Convolutional Networks
TLDR
This work presents region-based, fully convolutional networks for accurate and efficient object detection, and proposes position-sensitive score maps to address a dilemma between translation-invariance in image classification and translation-variance in object detection. Expand
Learning feed-forward one-shot learners
TLDR
This paper constructs the learner as a second deep network, called a learnet, which predicts the parameters of a pupil network from a single exemplar, and obtains an efficient feed-forward one-shot learner, trained end-to-end by minimizing a one- shot classification objective in a learning to learn formulation. Expand
Matching Networks for One Shot Learning
TLDR
This work employs ideas from metric learning based on deep neural features and from recent advances that augment neural networks with external memories to learn a network that maps a small labelled support set and an unlabelled example to its label, obviating the need for fine-tuning to adapt to new class types. Expand
...
1
2
3
4
5
...