Pith. sign in

REVIEW 3 cited by

MViTv2: Improved Multiscale Vision Transformers for Classification and Detection

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2112.01526 v2 pith:AH445RDS submitted 2021-12-02 cs.CV

Yanghao Li , Chao-Yuan Wu , Haoqi Fan , Karttikeya Mangalam , Bo Xiong , Jitendra Malik , Christoph Feichtenhofer This is my paper · ORCID
classification cs.CV
keywords classificationdetectionmvitv2videoaccuracyarchitectureattentioncoco
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

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 recognition 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 boxAP 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.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Rethinking Depth Pruning for Vision Transformers: A Heterogeneity-Aware Perspective

    cs.CV 2026-07 conditional novelty 6.0 of 10

    Heterogeneity-aware depth pruning of attention and activation layers, guided by a polynomial model-accuracy predictor, delivers up to 1.58× speedup on DeiT-B and 5.19× when combined with width pruning.

  2. STROKEVISION-BENCH: A Multimodal Video And 2D Pose Benchmark For Tracking Stroke Recovery

    eess.IV 2025-09 conditional novelty 6.0 of 10

    A new 1,000-video benchmark of stroke patients performing box-and-block sub-actions, with raw frames and 2D skeletons, establishes baseline action classification accuracy for seven models.

  3. Equipment-centric workpiece localization in near real-time using deep learning-based vision and event-driven finite state machines

    cs.LG 2026-08 conditional novelty 5.0 of 10

    An equipment-centric vision system tracks cranes with fixed cameras and finite state machines, inferring hot-forging workpiece locations with 317.8 mm mean error and 100% event detection within a 33-second tolerance.

Pith tools