Papers › PatchNet -- Short-range Template Matching for Efficient Video Processing

PatchNet -- Short-range Template Matching for Efficient Video Processing

10 Mar 2021arXiv:2103.07371archive 2025-07-28

Huizi Mao, Sibo Zhu, Song Han, William J. Dally

Object recognition is a fundamental problem in many video processing tasks, accurately locating seen objects at low computation cost paves the way for on-device video recognition. We propose PatchNet, an efficient convolutional neural network to match objects in adjacent video frames. It learns the patchwise correlation features instead of pixel features. PatchNet is very compact, running at just 58MFLOPs, 5× simpler than MobileNetV2. We demonstrate its application on two tasks, video object detection and visual object tracking. On ImageNet VID, PatchNet reduces the flops of R-FCN ResNet-101 by 5x and EfficientDet-D0 by 3.4x with less than 1% mAP loss. On OTB2015, PatchNet reduces SiamFC and SiamRPN by 2.5x with no accuracy loss. Experiments on Jetson Nano further demonstrate 2.8x to 4.3x speed-ups associated with flops reduction. Code is open sourced at https://github.com/RalphMao/PatchNet.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

RalphMao/PatchNet officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

ObjectObject DetectionObject RecognitionObject TrackingTemplate MatchingVideo Object DetectionVideo RecognitionVisual Object Trackingobject-detection

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

1x1 ConvolutionAverage PoolingBatch NormalizationConvolutionDepthwise ConvolutionDepthwise Separable ConvolutionInverted Residual BlockPointwise ConvolutionPosition-Sensitive RoI PoolingR-FCN

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections