Exploring Effective Knowledge Transfer for Few-shot Object Detection

by   Zhiyuan Zhao, et al.

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.


page 2

page 4

page 11


Frustratingly Simple Few-Shot Object Detection

Detecting rare objects from a few examples is an emerging problem. Prior...

Singular Value Fine-tuning: Few-shot Segmentation requires Few-parameters Fine-tuning

Freezing the pre-trained backbone has become a standard paradigm to avoi...

Hallucination Improves Few-Shot Object Detection

Learning to detect novel objects from few annotated examples is of great...

Proposal Distribution Calibration for Few-Shot Object Detection

Adapting object detectors learned with sufficient supervision to novel c...

Multi-Faceted Distillation of Base-Novel Commonality for Few-shot Object Detection

Most of existing methods for few-shot object detection follow the fine-t...

Efficient Few-Shot Object Detection via Knowledge Inheritance

Few-shot object detection (FSOD), which aims at learning a generic detec...

Benchmarking Low-Shot Robustness to Natural Distribution Shifts

Robustness to natural distribution shifts has seen remarkable progress t...

Please sign up or login with your details

Forgot password? Click here to reset