SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2307.09283 · 2023

RepViT: Revisiting Mobile CNN From ViT Perspective

arXiv · PDF · Open in the Atlas

Code that ran

6 of 12 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 3 have no contract verdict; 3 failures of our instrument; 6 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2307.09283.json · badge: /api/ran/2307.09283.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
THU-MIG/RepViT canonical (classifier label)
classifier basis not recorded on the link
3 ran · 3 no recorded run
leondgarse/keras_cv_attention_models community (classifier label)
classifier basis not recorded on the link
3 ran · 3 no recorded run
FunctionStatusWhere it lives
get_plot_cols_rows Ran
ran on a synthesized input
leondgarse/keras_cv_attention_models/keras_cv_attention_models/plot_func.py
code served (permissive licence) · get_code("e16a66a2573bda6b")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple, ndim 1, dtype family int; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

ARGS = {
    "total": 12,
    "rows": -1,
    "ceil_mode": False,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 1, dtype family int — a tuple output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_rel_pos Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
THU-MIG/RepViT/sam/repvit_sam/modeling/image_encoder.py
code served (permissive licence) · get_code("733d7f0bedcb74c2")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned Tensor, ndim 3, dtype family float, shape (3, 4, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn.functional as F

torch.manual_seed(0)

# Create a small relative position embedding tensor
# Shape: (L, C) where L is the sequence length and C is the channel dimension
# Using a small size that will be resized by the function
rel_pos = torch.randn(5, 4)  # 5 positions, 4 channels

# Define query and key sizes
q_size = 3
k_size = 4

ARGS = {
    "q_size": q_size,
    "k_size": k_size,
    "rel_pos": rel_pos,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 3, dtype family float, shape (3, 4, 4) — shape (3, 4, 4) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
put_text_on_image Ran
ran on a synthesized input
leondgarse/keras_cv_attention_models/keras_cv_attention_models/plot_func.py
code served (permissive licence) · get_code("9044d73cb7a0bb47")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ndarray, ndim 3, dtype family int, shape (32, 48, 3) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

# Create a simple RGB image as a numpy array
# Using values in [0, 1] range (normalized)
image = np.random.rand(32, 48, 3)  # 32 height, 48 width, 3 channels (RGB)

# Define all arguments
ARGS = {
    "image": image,
    "text": "Hello",
    "coord": (5, 5),
    "color": (255, 0, 0)
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 3, dtype family int, shape (32, 48, 3) — shape (32, 48, 3) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
stack_and_plot_images Ran
ran on a synthesized input
leondgarse/keras_cv_attention_models/keras_cv_attention_models/plot_func.py
code served (permissive licence) · get_code("03d4c554098904fd")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np
import matplotlib.pyplot as plt

# Create small sample images (RGB images as numpy arrays)
np.random.seed(0)
image1 = np.random.randint(0, 256, size=(32, 32, 3), dtype=np.uint8)
image2 = np.random.randint(0, 256, size=(32, 32, 3), dtype=np.uint8)
image3 = np.random.randint(0, 256, size=(32, 32, 3), dtype=np.uint8)
image4 = np.random.randint(0, 256, size=(32, 32, 3), dtype=np.uint8)

images = [image1, image2, image3, image4]
texts = ["Image 1", "Image 2", "Image 3", "Image 4"]

# Create figure and axes for plotting
fig, ax = plt.subplots(1, 1, figsize=(9, 9))

ARGS = {
    "images": images,
    "texts": texts,
    "margin": 5,
    "margin_value": 0,
    "rows": -1,
    "ax": ax,
    "base_size": 3
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, matplotlib, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
window_partition Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
THU-MIG/RepViT/sam/repvit_sam/modeling/image_encoder.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from LeapLabTHU/EchoWorld, is pointer only (licence: NONE) · get_code("105fa08885dc36cc")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from LeapLabTHU/EchoWorld, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

window_unpartition Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
THU-MIG/RepViT/sam/repvit_sam/modeling/image_encoder.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from yatengLG/ISAT_with_segment_anything, is pointer only (licence: NOASSERTION) · get_code("27be441cc8213e52")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from yatengLG/ISAT_with_segment_anything, and GitHub could not classify the licence of that repository (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

align_input_shape_by_image_data_format Not yet run
unverified (harvested, no recorded run)
leondgarse/keras_cv_attention_models/keras_cv_attention_models/backend.py
code served (permissive licence) · get_code("37f61ffdf6057577")
How it ran

no invocation recorded.

build_sam_vit_b Not yet run
unverified (harvested, no recorded run)
THU-MIG/RepViT/sam/repvit_sam/build_sam.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from yatengLG/ISAT_with_segment_anything, is pointer only (licence: NOASSERTION) · get_code("f9bc5f31ce61cee8")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from yatengLG/ISAT_with_segment_anything, and GitHub could not classify the licence of that repository (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

build_sam_vit_h Not yet run
unverified (harvested, no recorded run)
THU-MIG/RepViT/sam/repvit_sam/build_sam.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from yatengLG/ISAT_with_segment_anything, is pointer only (licence: NOASSERTION) · get_code("6b77c1f11fff3ed6")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from yatengLG/ISAT_with_segment_anything, and GitHub could not classify the licence of that repository (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

build_sam_vit_l Not yet run
unverified (harvested, no recorded run)
THU-MIG/RepViT/sam/repvit_sam/build_sam.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from yatengLG/ISAT_with_segment_anything, is pointer only (licence: NOASSERTION) · get_code("3f8890e695469246")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from yatengLG/ISAT_with_segment_anything, and GitHub could not classify the licence of that repository (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

in_train_phase Not yet run
unverified (harvested, no recorded run)
leondgarse/keras_cv_attention_models/keras_cv_attention_models/backend.py
code served (permissive licence) · get_code("0bf53c29bb7ba1f9")
How it ran

no invocation recorded.

numpy_image_resize Not yet run
unverified (harvested, no recorded run)
leondgarse/keras_cv_attention_models/keras_cv_attention_models/backend.py
code served (permissive licence) · get_code("e461556a7330926c")
How it ran

no invocation recorded.

Also present in other papers' code

Of 12 samples lifted from this paper's linked repositories, 12 carry a function identity and 0 do not. Of the 12 distinct functions with an identity, 6 are also present in other papers whose code we hold (6 with at least one paper dated earlier, 6 the same month, 6 later) and 6 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
get_rel_pos 47 other papers
9 dated earlier, 2 the same month, 36 later · 5 only as an assembly brick
2304.02643 (2023-04)
Segment Anything
2304.06790 (2023-04)
Inpaint Anything: Segment Anything Meets Image Inpainting
2304.12306 (2023-04)
Segment Anything in Medical Images
and 44 more not named here
window_partition 47 other papers
9 dated earlier, 2 the same month, 36 later · 1 only as an assembly brick
2304.02643 (2023-04)
Segment Anything
2304.06790 (2023-04)
Inpaint Anything: Segment Anything Meets Image Inpainting
2304.12306 (2023-04)
Segment Anything in Medical Images
and 44 more not named here
window_unpartition 46 other papers
9 dated earlier, 2 the same month, 35 later · 1 only as an assembly brick
2304.02643 (2023-04)
Segment Anything
2304.06790 (2023-04)
Inpaint Anything: Segment Anything Meets Image Inpainting
2304.12306 (2023-04)
Segment Anything in Medical Images
and 43 more not named here
build_sam_vit_h 37 other papers
6 dated earlier, 2 the same month, 29 later · 2 only as an assembly brick
2304.06790 (2023-04)
Inpaint Anything: Segment Anything Meets Image Inpainting
2304.12306 (2023-04)
Segment Anything in Medical Images
2305.01586 (2023-05)
An Alternative to WSSS? An Empirical Study of the Segment Anything Model (SAM) on Weakly-Supervised Semantic Segmentation Problems
and 34 more not named here
build_sam_vit_b 34 other papers
6 dated earlier, 2 the same month, 26 later
2304.06790 (2023-04)
Inpaint Anything: Segment Anything Meets Image Inpainting
2304.12306 (2023-04)
Segment Anything in Medical Images
2305.01586 (2023-05)
An Alternative to WSSS? An Empirical Study of the Segment Anything Model (SAM) on Weakly-Supervised Semantic Segmentation Problems
and 31 more not named here
build_sam_vit_l 34 other papers
6 dated earlier, 2 the same month, 26 later
2304.06790 (2023-04)
Inpaint Anything: Segment Anything Meets Image Inpainting
2304.12306 (2023-04)
Segment Anything in Medical Images
2305.01586 (2023-05)
An Alternative to WSSS? An Empirical Study of the Segment Anything Model (SAM) on Weakly-Supervised Semantic Segmentation Problems
and 31 more not named here

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

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}.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2307.09283")
get_code_for_paper("2307.09283")
have("2307.09283")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2307.09283.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2307.09283.svg)](https://syntology.ai/paper/2307.09283)

Connect an agent — have() is free.