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

arXiv: https://arxiv.org/abs/2502.20087 · HTML: https://mlsanity.com/paper/2502.20087/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- Builds on 68 of its 90 references that are in the map.
- First posted on arXiv 27 Feb 2025.

## Builds on (most cited first, 30 of 68)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [Pyramid Scene Parsing Network](https://mlsanity.com/paper/1612.01105/) (2016)
- [Xception: Deep Learning with Depthwise Separable Convolutions](https://mlsanity.com/paper/1610.02357/) (2016)
- [Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions](https://mlsanity.com/paper/2102.12122/) (2021)
- [The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization](https://mlsanity.com/paper/2006.16241/) (2020)
- [Do ImageNet Classifiers Generalize to ImageNet?](https://mlsanity.com/paper/1902.10811/) (2019)
- [Deformable Convolutional Networks](https://mlsanity.com/paper/1703.06211/) (2017)
- [Natural Adversarial Examples](https://mlsanity.com/paper/1907.07174/) (2019)
- [Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering](https://mlsanity.com/paper/1707.07998/) (2017)
- [Unified Perceptual Parsing for Scene Understanding](https://mlsanity.com/paper/1807.10221/) (2018)
- [Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model](https://mlsanity.com/paper/2401.09417/) (2024)
- [Learning Robust Global Representations by Penalizing Local Predictive Power](https://mlsanity.com/paper/1905.13549/) (2019)
- [Deep Networks with Stochastic Depth](https://mlsanity.com/paper/1603.09382/) (2016)
- [VMamba: Visual State Space Model](https://mlsanity.com/paper/2401.10166/) (2024)
- [Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learning](https://mlsanity.com/paper/1702.03118/) (2017)
- [PVT v2: Improved Baselines with Pyramid Vision Transformer](https://mlsanity.com/paper/2106.13797/) (2021)
- [Understanding the Effective Receptive Field in Deep Convolutional Neural Networks](https://mlsanity.com/paper/1701.04128/) (2017)
- [Stand-Alone Self-Attention in Vision Models](https://mlsanity.com/paper/1906.05909/) (2019)

## Built on by (most cited first, 25 of 25)

- [Vision Transformers Need More Than Registers](https://mlsanity.com/paper/2602.22394/) (2026)
- [Frequency-Dynamic Attention Modulation for Dense Prediction](https://mlsanity.com/paper/2507.12006/) (2025)
- [Advancing Image Super-resolution Techniques in Remote Sensing: A Comprehensive Survey](https://mlsanity.com/paper/2505.23248/) (2025)
- [Vision Transformers are Circulant Attention Learners](https://mlsanity.com/paper/2512.21542/) (2025)
- [Spatial Frequency Modulation for Semantic Segmentation](https://mlsanity.com/paper/2507.11893/) (2025)
- [ARTA: Adaptive Mixed-Resolution Token Allocation for Efficient Dense Feature Extraction](https://mlsanity.com/paper/2603.26258/) (2026)
- [A2Mamba: Attention-augmented State Space Models for Visual Recognition](https://mlsanity.com/paper/2507.16624/) (2025)
- [SRMambaV2: Biomimetic Attention for Sparse Point Cloud Upsampling in Autonomous Driving](https://mlsanity.com/paper/2507.17479/) (2025)
- [Parameters as Experts: Adapting Vision Models with Dynamic Parameter Routing](https://mlsanity.com/paper/2602.06862/) (2026)
- [Progressive Multimodal Interaction Network for Reliable Quantification of Fish Feeding Intensity in Aquaculture](https://mlsanity.com/paper/2506.14170/) (2025)
- [DPTrack:Directional Kernel-Guided Prompt Learning for Robust Nighttime Aerial Tracking](https://mlsanity.com/paper/2510.15449/) (2025)
- [WaveSeg: Enhancing Segmentation Precision via High-Frequency Prior and Mamba-Driven Spectrum Decomposition](https://mlsanity.com/paper/2510.21079/) (2025)
- [D2-VPR: A Parameter-efficient Visual-foundation-model-based Visual Place Recognition Method via Knowledge Distillation and Deformable Aggregation](https://mlsanity.com/paper/2511.12528/) (2025)
- [Generalized Geometry Encoding Volume for Real-time Stereo Matching](https://mlsanity.com/paper/2512.06793/) (2025)
- [SGDC: Structurally-Guided Dynamic Convolution for Medical Image Segmentation](https://mlsanity.com/paper/2602.23496/) (2026)
- [PaveBench: A Versatile Benchmark for Pavement Distress Perception and Interactive Vision-Language Analysis](https://mlsanity.com/paper/2604.02804/) (2026)
- [Advancing Vision Transformer with Enhanced Spatial Priors](https://mlsanity.com/paper/2604.18549/) (2026)
- [EAPFusion: Intrinsic Evolving Auxiliary Prior Guidance for Infrared and Visible Image Fusion](https://mlsanity.com/paper/2605.01916/) (2026)
- [Denoising-Enhanced Coarse-to-Fine Infrared Small Target Detection with Attention Prior-Guided Knowledge Distillation](https://mlsanity.com/paper/2606.21956/) (2026)
- [CPR: Chained Perceptual Refinement for Coarse-to-Fine Medical Image Classification](https://mlsanity.com/paper/2607.02591/) (2026)
- [Automatic Echocardiography Segmentation via Transition Probability Correlation for Stable Semantic Extraction](https://mlsanity.com/paper/2607.07580/) (2026)
- [Visible-Light Imaging Diagnosis of Neutral Particle Emission Tomography in the Tokamak Divertor: An Efficient Transformer-based Surrogate Model](https://mlsanity.com/paper/2607.22704/) (2026)
- [Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI](https://mlsanity.com/paper/2608.05258/) (2026)
- [CLARE: Scalable Class-Incremental Continual Learning via a Sparsity-Based Framework](https://mlsanity.com/paper/2609.17026/) (2026)
- [AD-SRF: Attack-Defense Semantic Reinforcement for Multi-Modal Image Fusion](https://mlsanity.com/paper/2610.12897/) (2026)

## Abstract (arXiv)

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.