Incremental-DETR: Incremental Few-Shot Object Detection via Self-Supervised Learning

  title={Incremental-DETR: Incremental Few-Shot Object Detection via Self-Supervised Learning},
  author={Na Dong and Yongqiang Zhang and Ming Ding and Gim Hee Lee},
Incremental few-shot object detection aims at detecting novel classes without forgetting knowledge of the base classes with only a few labeled training data from the novel classes. Most related prior works are on incremental object detection that rely on the availability of abundant training samples per novel class that substantially limits the scalability to real-world setting where novel data can be scarce. In this paper, we propose the Incremental-DETR that does incremental few-shot object… 

Figures and Tables from this paper


Incremental Few-Shot Object Detection
OpeN-ended Centre nEt (ONCE), a detector designed for incrementally learning to detect novel class objects with few examples, is proposed by an elegant adaptation of the efficient CentreNet detector to the few-shot learning scenario, and meta-learning a class-wise code generator model for registering novel classes.
Few-Shot Object Detection via Feature Reweighting
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.
Incremental Object Detection via Meta-Learning
A meta-learning approach that learns to reshape model gradients, such that information across incremental tasks is optimally shared ensures a seamless information transfer via a meta-learned gradient preconditioning that minimizes forgetting and maximizes knowledge transfer.
Meta-RCNN: Meta Learning for Few-Shot Object Detection
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.
Meta-Learning to Detect Rare Objects
A conceptually simple but powerful meta-learning based framework that simultaneously tackles few- shot classification and few-shot localization in a unified, coherent way and introduces a weight prediction meta-model that enables predicting the parameters of category-specific components from few examples.
Incremental Learning of Object Detectors without Catastrophic Forgetting
This work presents a method to learn object detectors incrementally, when neither the original training data nor annotations for the original classes in the new training set are available, and presents object detection results on the PASCAL VOC 2007 and COCO datasets.
Boosting Few-Shot Visual Learning With Self-Supervision
This work uses self-supervision as an auxiliary task in a few-shot learning pipeline, enabling feature extractors to learn richer and more transferable visual representations while still using few annotated samples.
Meta-DETR: Few-Shot Object Detection via Unified Image-Level Meta-Learning
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.
Frustratingly Simple Few-Shot Object Detection
This work finds that fine-tuning only the last layer of existing detectors on rare classes is crucial to the few-shot object detection task, and establishes a new state of the art on the revised benchmarks.
FSCE: Few-Shot Object Detection via Contrastive Proposal Encoding
This work presents 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.