Published on Tue Mar 30 2021

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

Hanzhe Hu, Shuai Bai, Aoxue Li, Jinshi Cui, Liwei Wang
0
0
0
Abstract

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.

Tue Aug 06 2019
Computer Vision
Few-Shot Object Detection with Attention-RPN and Multi-Relation Detector
Few-shot object detection aims at detecting objects of unseen categories with only a few annotated examples. Central to our method are our Attention-RPN, Multi-Relation Detector and Contrastive Training strategy. To train our network, we contribute a new dataset that contains 1000 categories of
0
0
0
Wed Aug 04 2021
Computer Vision
Dynamic Relevance Learning for Few-Shot Object Detection
The detector must recognize objects of novel classes with only a few training samples. Expensive bounding-box annotations have limited the development of object-detection task. The proposed model achieves the best overall performance, which shows its effectiveness of learning more generalized features.
1
0
1
Wed Feb 24 2021
Computer Vision
Dual-Awareness Attention for Few-Shot Object Detection
Few-shot object detection (FSOD) remains challenging for modern learning systems. Existing FSOD systems follow FSC approaches, ignoring the issues of spatial misalignment and vagueness in class representations. We propose a novel Dual-Awareness Attention (DAnA) mechanism
2
0
0
Mon Nov 30 2020
Computer Vision
AFD-Net: Adaptive Fully-Dual Network for Few-Shot Object Detection
Few-shot object detection (FSOD) aims at learning a detector that can fast adapt to previously unseen objects with scarce annotated examples. Existing methods solve this problem by performing a shared component (e.g.,RoI head) in the detector, yet few of them take the distinct
0
0
0
Tue Sep 10 2019
Computer Vision
PARN: Position-Aware Relation Networks for Few-Shot Learning
Few-shot learning presents a challenge that a classifier must quickly adapt to new classes that do not appear in the training set. This paper proposes a position-aware relation network (PARN) to learn a more flexible metric ability.
0
0
0
Thu Apr 15 2021
Computer Vision
Meta Faster R-CNN: Towards Accurate Few-Shot Object Detection with Attentive Feature Alignment
Few-shot object detection (FSOD) aims to detect objects using only few examples. We propose a meta-learning based few- shot object detection method. Our method incorporates a coarse-to-fine approach into the proposal based object detection framework.
4
0
1