OverLoCK: An Overview-first-Look-Closely-next ConvNet with Context-Mixing Dynamic Kernels

计算机科学 混合(物理) 背景(考古学) 物理 量子力学 古生物学 生物
作者
Meng Lou,Yizhou Yu
出处
期刊: 卷期号:: 128-138 被引量:15
标识
DOI:10.1109/cvpr52734.2025.00021
摘要

Top-down attention plays a crucial role in the human vision system, wherein the brain initially obtains a rough overview of a scene to discover salient cues (i.e., overview first), followed by a more careful finer-grained examination (i.e., look closely next). However, modern ConvNets remain confined to a pyramid structure that successively downsamples the feature map for receptive field expansion, neglecting this crucial biomimetic principle. We present OverLoCK, the first pure ConvNet backbone architecture that explicitly incorporates a top-down attention mechanism. Unlike pyramid backbone networks, our design features a branched architecture with three synergistic sub-networks: 1) a Base-Net that encodes low/mid-level features; 2) a lightweight Overview-Net that generates dynamic top-down attention through coarse global context modeling (i.e., overview first); and 3) a robust Focus-Net that performs finer-grained perception guided by top-down attention (i.e., look closely next). To fully unleash the power of top-down attention, we further propose a novel context-mixing dynamic convolution (ContMix) that effectively models long-range dependencies while preserving inherent local inductive biases even when the input resolution increases, addressing critical limitations in existing convolutions. Our OverLoCK exhibits a notable performance improvement over existing methods. For instance, OverLoCK-T achieves a Top-1 accuracy of 84.2%, significantly surpassing ConvNeXt-B while using only around one-third of the FLOPs/parameters. On object detection, our OverLoCK-S clearly surpasses MogaNet-B by 1% in AP^b. On semantic segmentation, our OverLoCK-T remarkably improves UniRepLKNet-T by 1.7% in mIoU. Code is publicly available at https://github.com/LMMMEng/OverLoCK.
最长约 10秒,即可获得该文献文件

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
刚刚
1秒前
1秒前
秋风的应助被醉熏的寄松采纳,获得10
3秒前
秋风的应助被醉熏的寄松采纳,获得10
3秒前
Maestro_S的应助被醉熏的寄松采纳,获得10
3秒前
4秒前
临床躺学发布了新的文献求助10
4秒前
可乐乐发布了新的文献求助10
4秒前
多情的仰发布了新的文献求助10
4秒前
快乐的紫寒完成签到,获得积分10
5秒前
xiao完成签到,获得积分10
5秒前
5秒前
6秒前
隐形曼青的应助被简单晓博采纳,获得10
6秒前
7秒前
泥头车发布了新的文献求助10
8秒前
8秒前
wz完成签到 ,获得积分10
8秒前
LGJ完成签到,获得积分10
8秒前
8秒前
9秒前
9秒前
乐乐的应助被Gloria2023采纳,获得20
9秒前
xixi发布了新的文献求助20
9秒前
9秒前
9秒前
嘎嘎嘎发布了新的文献求助10
9秒前
10秒前
sleblueep完成签到,获得积分10
10秒前
10秒前
10秒前
11秒前
11秒前
12秒前
远了个方发布了新的文献求助10
12秒前
12秒前
13秒前
13秒前
麦粑块发布了新的文献求助10
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
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
八旗制度の研究 600
Improving the wear resistance of vehicle gear oil by oil soluble LaF3 nanoparticles and typical additives of gear oil 500
Boundaries and Bodhisattvas 500
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 8183263
求助须知:如何正确求助?哪些是违规求助? 9572532
关于积分的说明 21826339
捐赠科研通 7780187
什么是DOI,文献DOI怎么找? 3433993
关于科研通互助平台的介绍 2558131
邀请新用户注册赠送积分活动 2480239