Any-Shot Object Detection
- URL: http://arxiv.org/abs/2003.07003v1
- Date: Mon, 16 Mar 2020 03:43:15 GMT
- Title: Any-Shot Object Detection
- Authors: Shafin Rahman and Salman Khan and Nick Barnes and Fahad Shahbaz Khan
- Abstract summary: '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.
- Score: 81.88153407655334
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Previous work on novel object detection considers zero or few-shot settings
where none or few examples of each category are available for training. In real
world scenarios, it is less practical to expect that 'all' the novel classes
are either unseen or {have} few-examples. Here, we propose a more realistic
setting termed 'Any-shot detection', where totally unseen and few-shot
categories can simultaneously co-occur during inference. Any-shot detection
offers unique challenges compared to conventional novel object detection such
as, a high imbalance between unseen, few-shot and seen object classes,
susceptibility to forget base-training while learning novel classes and
distinguishing novel classes from the background. To address these challenges,
we propose a unified any-shot detection model, that can concurrently learn to
detect both zero-shot and few-shot object classes. Our core idea is to use
class semantics as prototypes for object detection, a formulation that
naturally minimizes knowledge forgetting and mitigates the class-imbalance in
the label space. Besides, we propose a rebalanced loss function that emphasizes
difficult few-shot cases but avoids overfitting on the novel classes to allow
detection of totally unseen classes. Without bells and whistles, our framework
can also be used solely for Zero-shot detection and Few-shot detection tasks.
We report extensive experiments on Pascal VOC and MS-COCO datasets where our
approach is shown to provide significant improvements.
Related papers
- 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) - Bridging Non Co-occurrence with Unlabeled In-the-wild Data for
Incremental Object Detection [56.22467011292147]
Several incremental learning methods are proposed to mitigate catastrophic forgetting for object detection.
Despite the effectiveness, these methods require co-occurrence of the unlabeled base classes in the training data of the novel classes.
We propose the use of unlabeled in-the-wild data to bridge the non-occurrence caused by the missing base classes during the training of additional novel classes.
arXiv Detail & Related papers (2021-10-28T10:57:25Z) - 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 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) - Incrementally Zero-Shot Detection by an Extreme Value Analyzer [0.0]
This paper introduces a novel strategy for both zero-shot learning and class-incremental learning in real-world object detection.
We propose a novel extreme value analyzer to detect objects from old seen, new seen, and unseen classes, simultaneously.
Experiments demonstrate the efficacy of our model in detecting objects from both the seen and unseen classes, outperforming the alternative models on Pascal VOC and MSCOCO datasets.
arXiv Detail & Related papers (2021-03-23T15:06:30Z) - Restoring Negative Information in Few-Shot Object Detection [27.876368807936732]
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.
arXiv Detail & Related papers (2020-10-22T13:39:48Z) - 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) - Incremental Few-Shot Object Detection [96.02543873402813]
OpeN-ended Centre nEt is a detector for incrementally learning to detect class objects with few examples.
ONCE fully respects the incremental learning paradigm, with novel class registration requiring only a single forward pass of few-shot training samples.
arXiv Detail & Related papers (2020-03-10T12:56:59Z)
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.