Restoring Negative Information in Few-Shot Object Detection
- URL: http://arxiv.org/abs/2010.11714v2
- Date: Mon, 26 Oct 2020 03:33:08 GMT
- Title: Restoring Negative Information in Few-Shot Object Detection
- Authors: Yukuan Yang, Fangyun Wei, Miaojing Shi, Guoqi Li
- Abstract summary: Few-shot learning has recently emerged as a new challenge in the deep learning field.
We introduce a new negative- and positive-representative based metric learning framework and a new inference scheme with negative and positive representatives.
Our method substantially improves the state-of-the-art few-shot object detection solutions.
- Score: 27.876368807936732
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Few-shot learning has recently emerged as a new challenge in the deep
learning field: unlike conventional methods that train the deep neural networks
(DNNs) with a large number of labeled data, it asks for the generalization of
DNNs on new classes with few annotated samples. Recent advances in few-shot
learning mainly focus on image classification while in this paper we focus on
object detection. The initial explorations in few-shot object detection tend to
simulate a classification scenario by using the positive proposals in images
with respect to certain object class while discarding the negative proposals of
that class. Negatives, especially hard negatives, however, are essential to the
embedding space learning in few-shot object detection. In this paper, we
restore the negative information in few-shot object detection by introducing a
new negative- and positive-representative based metric learning framework and a
new inference scheme with negative and positive representatives. We build our
work on a recent few-shot pipeline RepMet with several new modules to encode
negative information for both training and testing. Extensive experiments on
ImageNet-LOC and PASCAL VOC show our method substantially improves the
state-of-the-art few-shot object detection solutions. Our code is available at
https://github.com/yang-yk/NP-RepMet.
Related papers
- Proposal-Contrastive Pretraining for Object Detection from Fewer Data [11.416621957617334]
We present Proposal Selection Contrast (ProSeCo), a novel unsupervised overall pretraining approach.
ProSeCo uses the large number of object proposals generated by the detector for contrastive learning.
We show that our method outperforms state of the art in unsupervised pretraining for object detection on standard and novel benchmarks.
arXiv Detail & Related papers (2023-10-25T17:59:26Z) - Incremental-DETR: Incremental Few-Shot Object Detection via
Self-Supervised Learning [60.64535309016623]
We propose the Incremental-DETR that does incremental few-shot object detection via fine-tuning and self-supervised learning on the DETR object detector.
To alleviate severe over-fitting with few novel class data, we first fine-tune the class-specific components of DETR with self-supervision.
We further introduce a incremental few-shot fine-tuning strategy with knowledge distillation on the class-specific components of DETR to encourage the network in detecting novel classes without catastrophic forgetting.
arXiv Detail & Related papers (2022-05-09T05:08:08Z) - Experience feedback using Representation Learning for Few-Shot Object
Detection on Aerial Images [2.8560476609689185]
The performance of our method is assessed on DOTA, a large-scale remote sensing images dataset.
It highlights in particular some intrinsic weaknesses for the few-shot object detection task.
arXiv Detail & Related papers (2021-09-27T13:04:53Z) - Generalized Few-Shot Object Detection without Forgetting [17.719042946397487]
We propose a simple yet effective few-shot detector, Retentive R-CNN.
It consists of Bias-Balanced RPN to debias the pretrained RPN and Re-detector to find few-shot class objects without forgetting previous knowledge.
Our approach has demonstrated that the long desired never-forgetting learner is available in object detection.
arXiv Detail & Related papers (2021-05-20T03:25:29Z) - Few-Shot Learning for Video Object Detection in a Transfer-Learning
Scheme [70.45901040613015]
We study the new problem of few-shot learning for video object detection.
We employ a transfer-learning framework to effectively train the video object detector on a large number of base-class objects and a few video clips of novel-class objects.
arXiv Detail & Related papers (2021-03-26T20:37:55Z) - Few-shot Weakly-Supervised Object Detection via Directional Statistics [55.97230224399744]
We propose a probabilistic multiple instance learning approach for few-shot Common Object Localization (COL) and few-shot Weakly Supervised Object Detection (WSOD)
Our model simultaneously learns the distribution of the novel objects and localizes them via expectation-maximization steps.
Our experiments show that the proposed method, despite being simple, outperforms strong baselines in few-shot COL and WSOD, as well as large-scale WSOD tasks.
arXiv Detail & Related papers (2021-03-25T22:34:16Z) - Any-Shot Object Detection [81.88153407655334]
'Any-shot detection' is where totally unseen and few-shot categories can simultaneously co-occur during inference.
We propose a unified any-shot detection model, that can concurrently learn to detect both zero-shot and few-shot object classes.
Our framework can also be used solely for Zero-shot detection and Few-shot detection tasks.
arXiv Detail & Related papers (2020-03-16T03:43:15Z) - Frustratingly Simple Few-Shot Object Detection [98.42824677627581]
We find that fine-tuning only the last layer of existing detectors on rare classes is crucial to the few-shot object detection task.
Such a simple approach outperforms the meta-learning methods by roughly 220 points on current benchmarks.
arXiv Detail & Related papers (2020-03-16T00:29:14Z) - StarNet: towards Weakly Supervised Few-Shot Object Detection [87.80771067891418]
We introduce StarNet - a few-shot model featuring an end-to-end differentiable non-parametric star-model detection and classification head.
Through this head, the backbone is meta-trained using only image-level labels to produce good features for jointly localizing and classifying previously unseen categories of few-shot test tasks.
Being a few-shot detector, StarNet does not require any bounding box annotations, neither during pre-training nor for novel classes adaptation.
arXiv Detail & Related papers (2020-03-15T11:35:28Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.