REVIEW 6 cited by
RepViT: Revisiting Mobile CNN From ViT Perspective
Not yet reviewed by Pith; the record is open.
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
Signed reviews
abstract
Recently, lightweight Vision Transformers (ViTs) demonstrate superior performance and lower latency, compared with lightweight Convolutional Neural Networks (CNNs), on resource-constrained mobile devices. Researchers have discovered many structural connections between lightweight ViTs and lightweight CNNs. However, the notable architectural disparities in the block structure, macro, and micro designs between them have not been adequately examined. In this study, we revisit the efficient design of lightweight CNNs from ViT perspective and emphasize their promising prospect for mobile devices. Specifically, we incrementally enhance the mobile-friendliness of a standard lightweight CNN, \ie, MobileNetV3, by integrating the efficient architectural designs of lightweight ViTs. This ends up with a new family of pure lightweight CNNs, namely RepViT. Extensive experiments show that RepViT outperforms existing state-of-the-art lightweight ViTs and exhibits favorable latency in various vision tasks. Notably, on ImageNet, RepViT achieves over 80\% top-1 accuracy with 1.0 ms latency on an iPhone 12, which is the first time for a lightweight model, to the best of our knowledge. Besides, when RepViT meets SAM, our RepViT-SAM can achieve nearly 10$\times$ faster inference than the advanced MobileSAM. Codes and models are available at \url{https://github.com/THU-MIG/RepViT}.
Forward citations
Cited by 6 Pith papers
-
The Task Shield: Enforcing Task Alignment to Defend Against Indirect Prompt Injection in LLM Agents
Task Shield cuts indirect prompt injection attack success to 2.07% on AgentDojo with GPT-4o by using an LLM to verify that each instruction and tool call contributes to the user's explicit goals.
-
EMOv2: Pushing 5M Vision Model Frontier
A 5M-parameter backbone with shared-weight spanning window attention sets new accuracy records across classification, detection, and generation benchmarks.
-
RapidNet: Multi-Level Dilated Convolution Based Mobile Backbone
A pure CNN mobile backbone using multi-level dilated convolutions reports faster or more accurate results than several mobile ViT, ViG, and hybrid baselines across classification, detection, and segmentation.
-
Efficient Edge-Compatible CNN for Speckle-Based Material Recognition in Laser Cutting Systems
A 341k-parameter MobileNet-style CNN achieves 95.05% accuracy on the 59-class SensiCut speckle material recognition benchmark using single-channel green input.
-
Change of Thought: Adaptive Test-Time Computation
A transformer layer that iteratively refines its attention matrix to a fixed point is claimed to improve accuracy with no extra parameters, but the benchmark evidence is not reproducible.
-
RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations
RecConv recursively decomposes feature maps into multiple scales with shared small-kernel depthwise convolutions to grow the effective receptive field to k times 2^ell at roughly constant FLOPs, yielding the RecNeXt b...
Discussion (0). Continue with ORCID to comment.