Repvit: Revisiting mobile cnn from vit perspective
Abstract Recently lightweight Vision Transformers (ViTs) demonstrate superior performance
and lower latency compared with lightweight Convolutional Neural Networks (CNNs) on …
and lower latency compared with lightweight Convolutional Neural Networks (CNNs) on …
MobileNetV4: Universal Models for the Mobile Ecosystem
We present the latest generation of MobileNets: MobileNetV4 (MNv4). They feature
universally-efficient architecture designs for mobile devices. We introduce the Universal …
universally-efficient architecture designs for mobile devices. We introduce the Universal …
UniRepLKNet: A Universal Perception Large-Kernel ConvNet for Audio Video Point Cloud Time-Series and Image Recognition
Large-kernel convolutional neural networks (ConvNets) have recently received extensive
research attention but two unresolved and critical issues demand further investigation. 1) …
research attention but two unresolved and critical issues demand further investigation. 1) …
Mobileclip: Fast image-text models through multi-modal reinforced training
Contrastive pre-training of image-text foundation models such as CLIP demonstrated
excellent zero-shot performance and improved robustness on a wide range of downstream …
excellent zero-shot performance and improved robustness on a wide range of downstream …
Self-supervised masked convolutional transformer block for anomaly detection
Anomaly detection has recently gained increasing attention in the field of computer vision,
likely due to its broad set of applications ranging from product fault detection on industrial …
likely due to its broad set of applications ranging from product fault detection on industrial …
Shvit: Single-head vision transformer with memory efficient macro design
Abstract Recently efficient Vision Transformers have shown great performance with low
latency on resource-constrained devices. Conventionally they use 4x4 patch embeddings …
latency on resource-constrained devices. Conventionally they use 4x4 patch embeddings …
Pruning self-attentions into convolutional layers in single path
Vision Transformers (ViTs) have achieved impressive performance over various computer
vision tasks. However, modeling global correlations with multi-head self-attention (MSA) …
vision tasks. However, modeling global correlations with multi-head self-attention (MSA) …
Model compression in practice: Lessons learned from practitioners creating on-device machine learning experiences
On-device machine learning (ML) promises to improve the privacy, responsiveness, and
proliferation of new, intelligent user experiences by moving ML computation onto everyday …
proliferation of new, intelligent user experiences by moving ML computation onto everyday …
[HTML][HTML] Real-time semantic segmentation for autonomous driving: A review of CNNs, Transformers, and Beyond
Real-time semantic segmentation is a crucial component of autonomous driving systems,
where accurate and efficient scene interpretation is essential to ensure both safety and …
where accurate and efficient scene interpretation is essential to ensure both safety and …
Ditfastattn: Attention compression for diffusion transformer models
Diffusion Transformers (DiT) excel at image and video generation but face computational
challenges due to the quadratic complexity of self-attention operators. We propose …
challenges due to the quadratic complexity of self-attention operators. We propose …