已入深夜,您辛苦了!由于当前在线用户较少,发布求助请尽量完整地填写文献信息,科研通机器人24小时在线,伴您度过漫漫科研夜!祝你早点完成任务,早点休息,好梦!

Simple Image-Level Classification Improves Open-Vocabulary Object Detection

作者
Ruohuan Fang,Guansong Pang,Xiao Ping Bai
出处
期刊:Proceedings of the ... AAAI Conference on Artificial Intelligence [Association for the Advancement of Artificial Intelligence]
卷期号:38 (2): 1716-1725 被引量:27
标识
DOI:10.1609/aaai.v38i2.27939
摘要

Open-Vocabulary Object Detection (OVOD) aims to detect novel objects beyond a given set of base categories on which the detection model is trained. Recent OVOD methods focus on adapting the image-level pre-trained vision-language models (VLMs), such as CLIP, to a region-level object detection task via, eg., region-level knowledge distillation, regional prompt learning, or region-text pre-training, to expand the detection vocabulary. These methods have demonstrated remarkable performance in recognizing regional visual concepts, but they are weak in exploiting the VLMs' powerful global scene understanding ability learned from the billion-scale image-level text descriptions. This limits their capability in detecting hard objects of small, blurred, or occluded appearance from novel/base categories, whose detection heavily relies on contextual information. To address this, we propose a novel approach, namely Simple Image-level Classification for Context-Aware Detection Scoring (SIC-CADS), to leverage the superior global knowledge yielded from CLIP for complementing the current OVOD models from a global perspective. The core of SIC-CADS is a multi-modal multi-label recognition (MLR) module that learns the object co-occurrence-based contextual information from CLIP to recognize all possible object categories in the scene. These image-level MLR scores can then be utilized to refine the instance-level detection scores of the current OVOD models in detecting those hard objects. This is verified by extensive empirical results on two popular benchmarks, OV-LVIS and OV-COCO, which show that SIC-CADS achieves significant and consistent improvement when combined with different types of OVOD models. Further, SIC-CADS also improves the cross-dataset generalization ability on Objects365 and OpenImages. Code is available at https://github.com/mala-lab/SIC-CADS.

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
飘落的樱花完成签到,获得积分10
1秒前
edisonzz发布了新的文献求助10
2秒前
2秒前
2秒前
chen发布了新的文献求助10
3秒前
小丹小丹完成签到 ,获得积分10
3秒前
anian完成签到,获得积分10
4秒前
情怀的应助被科研通管家采纳,获得10
5秒前
思源的应助被科研通管家采纳,获得10
5秒前
DW的应助被科研通管家采纳,获得10
5秒前
perway完成签到,获得积分10
5秒前
Owen的应助被科研通管家采纳,获得30
5秒前
DW的应助被科研通管家采纳,获得10
5秒前
充电宝的应助被科研通管家采纳,获得10
5秒前
5秒前
斯文败类的应助被科研通管家采纳,获得10
5秒前
6秒前
6秒前
Akim的应助被科研通管家采纳,获得30
6秒前
斯文败类的应助被科研通管家采纳,获得10
6秒前
FashionBoy的应助被科研通管家采纳,获得10
6秒前
狂野采波发布了新的文献求助10
6秒前
王思聪完成签到 ,获得积分10
7秒前
Lucas的应助被ezekiet采纳,获得10
7秒前
丘比特的应助被xy采纳,获得10
7秒前
Jasper的应助被Zhixia采纳,获得10
7秒前
wwwww发布了新的文献求助10
8秒前
FoxLY完成签到,获得积分10
8秒前
灵巧的寄容完成签到,获得积分10
8秒前
9秒前
科研通AI2S的应助被Crane采纳,获得10
9秒前
Yaang发布了新的文献求助100
9秒前
Csy发布了新的文献求助20
10秒前
10秒前
畅快的绮完成签到,获得积分10
10秒前
qzq完成签到,获得积分20
12秒前
12秒前
高兴香彤发布了新的文献求助10
13秒前
大个的应助被cxy2采纳,获得10
13秒前
13秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
Grapes 1000
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
John McDowells Bildungstheorie 800
八旗制度の研究 600
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8179104
求助须知:如何正确求助?哪些是违规求助? 9569680
关于积分的说明 21806134
捐赠科研通 7774263
什么是DOI,文献DOI怎么找? 3433003
关于科研通互助平台的介绍 2556897
邀请新用户注册赠送积分活动 2478643