MViTv2: Improved Multiscale Vision Transformers for Classification and Detection
Yanghao Li, Chao-Yuan Wu, Haoqi Fan, Karttikeya Mangalam, Bo Xiong, Jitendra Malik, Christoph Feichtenhofer
Paper appears method- or tooling-adjacent to AI workflows with partial ecosystem coverage.
In this paper, we study Multiscale Vision Transformers (MViTv2) as a unified architecture for image and video classification, as well as object detection. We present an improved version of MViT that incorporates decomposed relative positional embeddings and residual pooling connections. We instantiate this architecture in five sizes and evaluate it for ImageNet classification, COCO detection and Kinetics video recogn ...
ition where it outperforms prior work. We further compare MViTv2s' pooling attention to window attention mechanisms where it outperforms the latter in accuracy/compute. Without bells-and-whistles, MViTv2 has state-of-the-art performance in 3 domains: 88.8% accuracy on ImageNet classification, 58.7 AP <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">box</sup> on COCO object detection as well as 86.1% on Kinetics-400 video classification. Code and models are available at https://github.com/facebookresearch/mvit.
Results & Benchmarks
Some benchmark signal exists in the extracted evidence, but it is not structured strongly enough yet for a confident benchmark decision.
In this paper, we study Multiscale Vision Transformers (MViTv2) as a unified architecture for image and video classification, as well as object detection.
Implementation Evidence Summary
cmhungsteve/Awesome-Transformer-Attention is the closest maintained adjacent implementation (Matches contextual method/domain keyword: transformer). It is not paper-verified; validate algorithm and evaluation setup against the paper before trusting reported metrics. Community adoption signal: 5045 GitHub stars.
Reproduction Risks
- Adjacent implementations are not paper-verified
- Recommended repository is adjacent and not paper-verified.
Hardware Notes
Expect multi-day setup/compute for meaningful reproduction based on current guidance.
Evidence disclosure
Evidence graph: 3 refs, 3 links.
Utility signals: depth 100/100, grounding 85/100, status high.
Implementation Status
There is no verified maintained implementation yet. Use this baseline plan to decide whether to prototype now or defer.
- No maintained paper-verified implementation was found; start with the closest related repositories below.
- Compare repo methods against the paper equations/algorithm before trusting metrics.
- Create a minimal baseline implementation from the paper and use adjacent repos as references.
Reproduction readiness
Hardware requirements
- Expect multi-day setup/compute for meaningful reproduction based on current guidance.
No verified implementation available
- · No maintained repository has been identified for this paper. Check adjacent implementations or HF artifacts below.
Framework baselines
- Hugging Face Transformers training guide
Modern transformer training baseline.
- PyTorch nn.Transformer docs
Reference transformer building block implementation.
- TorchVision object detection finetuning tutorial
Baseline setup for object detection workflows.
Closest related implementations
These are not paper-verified. Use them as reference points when no direct implementation is available.
- cmhungsteve/Awesome-Transformer-AttentionAdjacentConfidence: MediumStars: 5,045
Matches contextual method/domain keyword: transformer
- dk-liang/Awesome-Visual-TransformerAdjacentConfidence: MediumStars: 3,587
Matches contextual method/domain keyword: transformer
- lxtGH/Awesome-Segmentation-With-TransformerAdjacentConfidence: MediumStars: 761
Matches contextual method/domain keyword: transformer
Hugging Face artifacts
No trustworthy direct or curated related Hugging Face artifacts were found yet.
Continue with targeted Hugging Face searches derived from the paper title and method context:
Models
Tip: start with models, then check datasets/spaces if you need evaluation data or demos.
Direct artifact matches are currently sparse. Use targeted Hugging Face searches to quickly locate candidate models, datasets, and demos.
Research context
719
Citations
117
References
Tasks
Pooling, Computer science, Object detection, Contextual image classification, Pattern recognition (psychology), Residual, Feature extraction
Methods
Transformer
Domains
Artificial intelligence, Machine learning, Computer vision, Computer Vision and Pattern Recognition
Evaluation & Human Feedback Data
Open this paper in HFEPX to review benchmark signals, evaluation modes, and human-feedback protocol context.
Open in HFEPXExplore Similar Papers
Jump to Paper2Code search queries derived from this paper's research context.
Related papers
-
Search on Paper2Code
A Fully Trainable Network with RNN-based Pooling (2017) Semantic similarity
-
Search on Paper2Code
A fully trainable network with RNN-based pooling (2019) Semantic similarity
-
Search on Paper2Code
Pooling in high-throughput drug screening. (2009) Semantic similarity
-
Search on Paper2Code
Alpha-Pooling for Convolutional Neural Networks. (2018) Semantic similarity
-
Search on Paper2Code
A improved pooling method for convolutional neural networks (2024) Semantic similarity
-
Search on Paper2Code
Why and when should you pool? Analyzing Pooling in Recurrent Architectures (2020) Semantic similarity
Need human evaluators for your AI research? Scale annotation with expert AI Trainers.