MINI: Mining Implicit Novel Instances for Few-Shot Object Detection

by   Yuhang Cao, et al.

Learning from a few training samples is a desirable ability of an object detector, inspiring the explorations of Few-Shot Object Detection (FSOD). Most existing approaches employ a pretrain-transfer paradigm. The model is first pre-trained on base classes with abundant data and then transferred to novel classes with a few annotated samples. Despite the substantial progress, the FSOD performance is still far behind satisfactory. During pre-training, due to the co-occurrence between base and novel classes, the model is learned to treat the co-occurred novel classes as backgrounds. During transferring, given scarce samples of novel classes, the model suffers from learning discriminative features to distinguish novel instances from backgrounds and base classes. To overcome the obstacles, we propose a novel framework, Mining Implicit Novel Instances (MINI), to mine the implicit novel instances as auxiliary training samples, which widely exist in abundant base data but are not annotated. MINI comprises an offline mining mechanism and an online mining mechanism. The offline mining mechanism leverages a self-supervised discriminative model to collaboratively mine implicit novel instances with a trained FSOD network. Taking the mined novel instances as auxiliary training samples, the online mining mechanism takes a teacher-student framework to simultaneously update the FSOD network and the mined implicit novel instances on the fly. Extensive experiments on PASCAL VOC and MS-COCO datasets show MINI achieves new state-of-the-art performance on any shot and split. The significant performance improvements demonstrate the superiority of our method.


page 2

page 16


ECEA: Extensible Co-Existing Attention for Few-Shot Object Detection

Few-shot object detection (FSOD) identifies objects from extremely few a...

Few-shot Forgery Detection via Guided Adversarial Interpolation

Realistic visual media synthesis is becoming a critical societal issue w...

Few-Shot Object Detection via Association and DIscrimination

Object detection has achieved substantial progress in the last decade. H...

Incremental Few-Shot Object Detection

Most existing object detection methods rely on the availability of abund...

Adaptive Base-class Suppression and Prior Guidance Network for One-Shot Object Detection

One-shot object detection (OSOD) aims to detect all object instances tow...

NIFF: Alleviating Forgetting in Generalized Few-Shot Object Detection via Neural Instance Feature Forging

Privacy and memory are two recurring themes in a broad conversation abou...

Low-shot Object Detection via Classification Refinement

This work aims to address the problem of low-shot object detection, wher...

Please sign up or login with your details

Forgot password? Click here to reset