Exploring Effective Knowledge Transfer for Few-shot Object Detection
- URL: http://arxiv.org/abs/2210.02021v1
- Date: Wed, 5 Oct 2022 04:53:58 GMT
- Title: Exploring Effective Knowledge Transfer for Few-shot Object Detection
- Authors: Zhiyuan Zhao, Qingjie Liu, Yunhong Wang
- Abstract summary: Methods that excel in low-shot regimes are likely to struggle in high-shot regimes, and vice versa.
In the low-shot regime, the primary challenge is the lack of inner-class variation.
In the high-shot regime, as the variance approaches the real one, the main hindrance to the performance comes from misalignment between learned and true distributions.
- Score: 54.45009859654753
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Recently, few-shot object detection~(FSOD) has received much attention from
the community, and many methods are proposed to address this problem from a
knowledge transfer perspective. Though promising results have been achieved,
these methods fail to achieve shot-stable:~methods that excel in low-shot
regimes are likely to struggle in high-shot regimes, and vice versa. We believe
this is because the primary challenge of FSOD changes when the number of shots
varies. In the low-shot regime, the primary challenge is the lack of
inner-class variation. In the high-shot regime, as the variance approaches the
real one, the main hindrance to the performance comes from misalignment between
learned and true distributions. However, these two distinct issues remain
unsolved in most existing FSOD methods. In this paper, we propose to overcome
these challenges by exploiting rich knowledge the model has learned and
effectively transferring them to the novel classes. For the low-shot regime, we
propose a distribution calibration method to deal with the lack of inner-class
variation problem. Meanwhile, a shift compensation method is proposed to
compensate for possible distribution shift during fine-tuning. For the
high-shot regime, we propose to use the knowledge learned from ImageNet as
guidance for the feature learning in the fine-tuning stage, which will
implicitly align the distributions of the novel classes. Although targeted
toward different regimes, these two strategies can work together to further
improve the FSOD performance. Experiments on both the VOC and COCO benchmarks
show that our proposed method can significantly outperform the baseline method
and produce competitive results in both low-shot settings (shot<5) and
high-shot settings (shot>=5). Code is available at
https://github.com/JulioZhao97/EffTrans_Fsdet.git.
Related papers
- Enhancing Training Data Attribution for Large Language Models with Fitting Error Consideration [74.09687562334682]
We introduce a novel training data attribution method called Debias and Denoise Attribution (DDA)
Our method significantly outperforms existing approaches, achieving an averaged AUC of 91.64%.
DDA exhibits strong generality and scalability across various sources and different-scale models like LLaMA2, QWEN2, and Mistral.
arXiv Detail & Related papers (2024-10-02T07:14:26Z) - Phasic Content Fusing Diffusion Model with Directional Distribution
Consistency for Few-Shot Model Adaption [73.98706049140098]
We propose a novel phasic content fusing few-shot diffusion model with directional distribution consistency loss.
Specifically, we design a phasic training strategy with phasic content fusion to help our model learn content and style information when t is large.
Finally, we propose a cross-domain structure guidance strategy that enhances structure consistency during domain adaptation.
arXiv Detail & Related papers (2023-09-07T14:14:11Z) - Causal Interventions-based Few-Shot Named Entity Recognition [5.961427870758681]
Few-shot named entity recognition (NER) systems aims at recognizing new classes of entities based on a few labeled samples.
The heavy overfitting in few-shot learning is mainly led by spurious correlation caused by the few samples selection bias.
We propose a causal intervention-based few-shot NER method to alleviate the problem of the spurious correlation.
arXiv Detail & Related papers (2023-05-03T06:11:39Z) - Stable Target Field for Reduced Variance Score Estimation in Diffusion
Models [5.9115407007859755]
Diffusion models generate samples by reversing a fixed forward diffusion process.
We argue that the source of such variance lies in the handling of intermediate noise-variance scales.
We propose to remedy the problem by incorporating a reference batch which we use to calculate weighted conditional scores as more stable training targets.
arXiv Detail & Related papers (2023-02-01T18:57:01Z) - MEAL: Stable and Active Learning for Few-Shot Prompting [26.60924937965494]
Few-shot classification has high variance both across different sets of few shots and across different finetuning runs.
We propose novel ensembling methods and show that they substantially reduce run variability.
Second, we introduce a new active learning (AL) criterion for data selection and present the first AL-based approach specifically tailored towards prompt-based learning.
arXiv Detail & Related papers (2022-11-15T18:06:53Z) - A New Knowledge Distillation Network for Incremental Few-Shot Surface
Defect Detection [20.712532953953808]
This paper proposes a new knowledge distillation network, called Dual Knowledge Align Network (DKAN)
The proposed DKAN method follows a pretraining-finetuning transfer learning paradigm and a knowledge distillation framework is designed for fine-tuning.
Experiments have been conducted on the incremental Few-shot NEU-DET dataset and results show that DKAN outperforms other methods on various few-shot scenes.
arXiv Detail & Related papers (2022-09-01T15:08:44Z) - Scale-Equivalent Distillation for Semi-Supervised Object Detection [57.59525453301374]
Recent Semi-Supervised Object Detection (SS-OD) methods are mainly based on self-training, generating hard pseudo-labels by a teacher model on unlabeled data as supervisory signals.
We analyze the challenges these methods meet with the empirical experiment results.
We introduce a novel approach, Scale-Equivalent Distillation (SED), which is a simple yet effective end-to-end knowledge distillation framework robust to large object size variance and class imbalance.
arXiv Detail & Related papers (2022-03-23T07:33:37Z) - Revisiting Consistency Regularization for Semi-Supervised Learning [80.28461584135967]
We propose an improved consistency regularization framework by a simple yet effective technique, FeatDistLoss.
Experimental results show that our model defines a new state of the art for various datasets and settings.
arXiv Detail & Related papers (2021-12-10T20:46:13Z) - Few-shot Action Recognition with Prototype-centered Attentive Learning [88.10852114988829]
Prototype-centered Attentive Learning (PAL) model composed of two novel components.
First, a prototype-centered contrastive learning loss is introduced to complement the conventional query-centered learning objective.
Second, PAL integrates a attentive hybrid learning mechanism that can minimize the negative impacts of outliers.
arXiv Detail & Related papers (2021-01-20T11:48:12Z) - Leveraging the Feature Distribution in Transfer-based Few-Shot Learning [2.922007656878633]
Few-shot classification is a challenging problem due to the uncertainty caused by using few labelled samples.
We propose a novel transfer-based method that builds on two successive steps: 1) preprocessing the feature vectors so that they become closer to Gaussian-like distributions, and 2) leveraging this preprocessing using an optimal-transport inspired algorithm.
We prove the ability of the proposed methodology to achieve state-of-the-art accuracy with various datasets, backbone architectures and few-shot settings.
arXiv Detail & Related papers (2020-06-06T07:32:08Z)
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.