Dense Relation Distillation with Context-aware Aggregation for Few-Shot Object Detection

03/30/2021
by   Hanzhe Hu, et al.
0

Conventional deep learning based methods for object detection require a large amount of bounding box annotations for training, which is expensive to obtain such high quality annotated data. Few-shot object detection, which learns to adapt to novel classes with only a few annotated examples, is very challenging since the fine-grained feature of novel object can be easily overlooked with only a few data available. In this work, aiming to fully exploit features of annotated novel object and capture fine-grained features of query object, we propose Dense Relation Distillation with Context-aware Aggregation (DCNet) to tackle the few-shot detection problem. Built on the meta-learning based framework, Dense Relation Distillation module targets at fully exploiting support features, where support features and query feature are densely matched, covering all spatial locations in a feed-forward fashion. The abundant usage of the guidance information endows model the capability to handle common challenges such as appearance changes and occlusions. Moreover, to better capture scale-aware features, Context-aware Aggregation module adaptively harnesses features from different scales for a more comprehensive feature representation. Extensive experiments illustrate that our proposed approach achieves state-of-the-art results on PASCAL VOC and MS COCO datasets. Code will be made available at https://github.com/hzhupku/DCNet.

READ FULL TEXT

page 1

page 4

page 7

research
01/31/2023

Few-Shot Object Detection via Variational Feature Aggregation

As few-shot object detectors are often trained with abundant base sample...
research
12/30/2020

MM-FSOD: Meta and metric integrated few-shot object detection

In the object detection task, CNN (Convolutional neural networks) models...
research
08/04/2021

Dynamic Relevance Learning for Few-Shot Object Detection

Expensive bounding-box annotations have limited the development of objec...
research
07/22/2023

Spatial Self-Distillation for Object Detection with Inaccurate Bounding Boxes

Object detection via inaccurate bounding boxes supervision has boosted a...
research
08/15/2022

Hierarchical Attention Network for Few-Shot Object Detection via Meta-Contrastive Learning

Few-shot object detection (FSOD) aims to classify and detect few images ...
research
11/27/2022

Breaking Immutable: Information-Coupled Prototype Elaboration for Few-Shot Object Detection

Few-shot object detection, expecting detectors to detect novel classes w...
research
11/21/2019

Learning Spatial Fusion for Single-Shot Object Detection

Pyramidal feature representation is the common practice to address the c...

Please sign up or login with your details

Forgot password? Click here to reset