Papers › MPViT: Multi-Path Vision Transformer for Dense Prediction

MPViT: Multi-Path Vision Transformer for Dense Prediction

21 Dec 2021CVPR 2022 1arXiv:2112.11010archive 2025-07-28

Youngwan Lee, Jonghee Kim, Jeff Willette, Sung Ju Hwang

Dense computer vision tasks such as object detection and segmentation require effective multi-scale feature representation for detecting or classifying objects or regions with varying sizes. While Convolutional Neural Networks (CNNs) have been the dominant architectures for such tasks, recently introduced Vision Transformers (ViTs) aim to replace them as a backbone. Similar to CNNs, ViTs build a simple multi-stage structure (i.e., fine-to-coarse) for multi-scale representation with single-scale patches. In this work, with a different perspective from existing Transformers, we explore multi-scale patch embedding and multi-path structure, constructing the Multi-Path Vision Transformer (MPViT). MPViT embeds features of the same size (i.e., sequence length) with patches of different scales simultaneously by using overlapping convolutional patch embedding. Tokens of different scales are then independently fed into the Transformer encoders via multiple paths and the resulting features are aggregated, enabling both fine and coarse feature representations at the same feature level. Thanks to the diverse, multi-scale feature representations, our MPViTs scaling from tiny (5M) to base (73M) consistently achieve superior performance over state-of-the-art Vision Transformers on ImageNet classification, object detection, instance segmentation, and semantic segmentation. These extensive results demonstrate that MPViT can serve as a versatile backbone network for various vision tasks. Code will be made publicly available at https://git.io/MPViT.

PaperPDFConference PDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

youngwanLEE/MPViT officialmentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
DarshanDeshpande/jax-models mentioned on GitHubjaxSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Deep Networks with Stochastic Depth (arXiv:1603.09382; that paper's own run record: 8 ran (of which 5 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified), Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions (arXiv:2102.12122; that paper's own run record: 22 ran (of which 16 constructed an object rather than computing a result; 18 with no instrument failure: 2 honoured, 0 violated, 16 with no contract checked; 4 where Syntology's instrument failed) · 8 unverified), Swin Transformer: Hierarchical Vision Transformer using Shifted Windows (arXiv:2103.14030; that paper's own run record: 123 ran (of which 45 constructed an object rather than computing a result; 79 with no instrument failure: 6 honoured, 3 violated, 70 with no contract checked; 44 where Syntology's instrument failed) · 84 unverified) and 5 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
towhee-io/towhee pytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Deep Residual Learning for Image Recognition (arXiv:1512.03385; that paper's own run record: 254 ran (of which 108 constructed an object rather than computing a result; 163 with no instrument failure: 3 honoured, 1 violated, 159 with no contract checked; 91 where Syntology's instrument failed) · 123 unverified), Perceiver: General Perception with Iterative Attention (arXiv:2103.03206; that paper's own run record: 41 ran (of which 20 constructed an object rather than computing a result; 30 with no instrument failure: 0 honoured, 2 violated, 28 with no contract checked; 11 where Syntology's instrument failed) · 14 unverified), LightningDOT: Pre-training Visual-Semantic Embeddings for Real-Time Image-Text Retrieval (arXiv:2103.08784; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified) and 9 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

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

Tasks

Instance SegmentationObject DetectionPredictionSegmentationSemantic Segmentationobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Instance Segmentation COCO minival MPViT-B (Cascade Mask R-CNN, multi-scale, IN1k pre-train) mask AP 47.0 #40 of 93 Archive leaderboard report
Instance Segmentation COCO minival MPViT-B (Cascade R-CNN, sinlge-scale, IN-1K pre-train) mask AP 45.8 #46 of 93 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformerVision Transformer

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