Pith. sign in

REVIEW 7 cited by

FasterViT: Fast Vision Transformers with Hierarchical Attention

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 2306.06189 v2 pith:5HJQJBTS submitted 2023-06-09 cs.CV cs.AIcs.LG

Ali Hatamizadeh , Greg Heinrich , Hongxu Yin , Andrew Tao , Jose M. Alvarez , Jan Kautz , Pavlo Molchanov This is my paper · ORCID
classification cs.CVcs.AIcs.LG
keywords fastervitglobalattentionhighcostsefficientfasthierarchical
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

We design a new family of hybrid CNN-ViT neural networks, named FasterViT, with a focus on high image throughput for computer vision (CV) applications. FasterViT combines the benefits of fast local representation learning in CNNs and global modeling properties in ViT. Our newly introduced Hierarchical Attention (HAT) approach decomposes global self-attention with quadratic complexity into a multi-level attention with reduced computational costs. We benefit from efficient window-based self-attention. Each window has access to dedicated carrier tokens that participate in local and global representation learning. At a high level, global self-attentions enable the efficient cross-window communication at lower costs. FasterViT achieves a SOTA Pareto-front in terms of accuracy and image throughput. We have extensively validated its effectiveness on various CV tasks including classification, object detection and segmentation. We also show that HAT can be used as a plug-and-play module for existing networks and enhance them. We further demonstrate significantly faster and more accurate performance than competitive counterparts for images with high resolution. Code is available at https://github.com/NVlabs/FasterViT.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 7 Pith papers

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

  1. Chimera: A Block-Based Neural Architecture Search Framework for Event-Based Object Detection

    cs.CV 2024-12 conditional novelty 6.0 of 10

    Chimera uses zero-shot NAS proxies and a diversity index to search heterogeneous recurrent backbones for event cameras, reaching PEDRo mAP 64.2 with 4.9M parameters.

  2. MTVNet: Mapping using Transformers for Volumes -- Network for Super-Resolution with Long-Range Interactions

    cs.CV 2024-12 conditional novelty 6.0 of 10

    MTVNet is a multi-scale transformer for volumetric super-resolution that uses carrier tokens to carry information across large 3D regions, setting new benchmarks on high-resolution bone CT data.

  3. HSMLA: Hierarchical Softmax Multi-scale Linear Attention for Efficient Vision Transformers

    cs.CV 2026-08 conditional novelty 5.0 of 10

    HSMLA pairs ReLU linear attention with block-level sparse softmax correction to make vision transformers faster on dense prediction without losing local detail.

  4. From Camera-Based Sensing to Reasoning: A Comprehensive Review Toward Proactive Vulnerable Road User Safety

    cs.CV 2025-09 accept novelty 5.0 of 10

    A survey organizing recent camera-based AI methods for vulnerable road user safety into four interlocking visual tasks and four open deployment challenges.

  5. Lightweight Backbone Networks Only Require Adaptive Lightweight Self-Attention Mechanisms

    cs.CV 2025-08 conditional novelty 5.0 of 10

    LOLViT, a GhostNet-based lightweight backbone using adaptive window attention, reports CNN-like CPU speed with MobileViT-level accuracy.

  6. iFormer: Integrating ConvNet and Transformer for Mobile Application

    cs.CV 2025-01 conditional novelty 5.0 of 10

    iFormer combines a mobile-tuned ConvNeXt backbone with single-head modulation attention, reaching 80.4% ImageNet top-1 accuracy at 1.10 ms iPhone 13 latency.

  7. The Linear Attention Resurrection in Vision Transformer

    cs.CV 2025-01 conditional novelty 4.0 of 10

    L2ViT alternates ReLU-based linear attention with a depthwise-convolution local concentration module and window attention, reaching 84.4% ImageNet-1K top-1 accuracy at linear-complexity attention.

Pith tools