SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 136710433 · ECCV · 2022

Self-slimmed Vision Transformer

Yu Qiao, Kunchang Li, Yali Wang, Guanglu Song, Yu Liu, Zhuofan Zong, Biao Leng

Code that ran

2 of 3 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; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 1 failure of our instrument; 1 no recorded run), measured 2026-11-22; 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/136710433.json · badge: /api/ran/136710433.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
Sense-X/SiT canonical (classifier label)
classifier basis: census
2 ran · 1 no recorded run
FunctionStatusWhere it lives
build_transform Ran
ran; our contract draft was wrong, not the code
Sense-X/SiT/datasets.py
code served (permissive licence) · get_code("3bc74137ab36aa79")
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 Compose. 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 torch
import numpy as np
from torchvision import transforms

torch.manual_seed(0)

class ArgsConfig:
    def __init__(self):
        self.input_size = 224
        self.color_jitter = 0.4
        self.aa = "rand-m9-mstd0.5"
        self.train_interpolation = "bicubic"
        self.reprob = 0.25
        self.remode = "pixel"
        self.recount = 2

ARGS = {
    "is_train": True,
    "args": ArgsConfig()
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, timm, torch, torchvision — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Compose — a Compose output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Compose output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not 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
get_dpr Ran
ran, honoured the contract we drafted
Sense-X/SiT/models/lvvit.py
code served (permissive licence) · get_code("b240fa8e2e8f8ec6")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned list, ndim 1, dtype family float; 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 torch

torch.manual_seed(0)

# Test case 1: linear decay (default)
drop_path_rate_1 = 0.1
depth_1 = 12
drop_path_decay_1 = 'linear'

# Test case 2: fix decay
drop_path_rate_2 = 0.2
depth_2 = 8
drop_path_decay_2 = 'fix'

# Test case 3: custom list
drop_path_rate_3 = [0.0, 0.05, 0.1, 0.15, 0.2]
depth_3 = 5
drop_path_decay_3 = 'custom'

# Use test case 1 for ARGS
ARGS = {
    'drop_path_rate': drop_path_rate_1,
    'depth': depth_1,
    'drop_path_decay': drop_path_decay_1
}
Setup block drafted by
a language model, Claude Sonnet 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 list, ndim 1, dtype family float — a list 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
build_dataset Not yet run
unverified (harvested, no recorded run)
Sense-X/SiT/datasets.py
code served (permissive licence) · get_code("9153241c4331eb1a")
How it ran

no invocation recorded.

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 2 later) and 0 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
build_transform 37 other papers
8 dated earlier, 17 later, 12 same year, order not determinable
2104.05707 (2021-04)
LocalViT: Analyzing Locality in Vision Transformers
2104.13840 (2021-04)
Twins: Revisiting the Design of Spatial Attention in Vision Transformers
2106.00515 (2021-06)
KVT: k-NN Attention for Boosting Vision Transformers
and 34 more not named here
build_dataset 25 other papers
5 dated earlier, 15 later, 5 same year, order not determinable
2104.05707 (2021-04)
LocalViT: Analyzing Locality in Vision Transformers
2106.00515 (2021-06)
KVT: k-NN Attention for Boosting Vision Transformers
2106.01401 (2021-06)
Container: Context Aggregation Network
and 22 more not named here
get_dpr 2 other papers
1 dated earlier, 1 same year, order not determinable
2104.10858 (2021-04)
All Tokens Matter: Token Labeling for Training Better Vision Transformers
2206.07662 (2022-06)
SP-ViT: Learning 2D Spatial Priors for Vision Transformers

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

Vision transformers (ViTs) have become the popular structures and outperformed convolutional neural networks (CNNs) on various vision tasks. However, such powerful transformers bring a huge computation burden, because of the exhausting token-to-token comparison. The previous works focus on dropping insignificant tokens to reduce the computational cost of ViTs. But when the dropping ratio increases, this hard manner will inevitably discard the vital tokens, which limits its efficiency. To solve the issue, we propose a generic self-slimmed learning approach for vanilla ViTs, namely SiT. Specifically, we first design a novel Token Slimming Module (TSM), which can boost the inference efficiency of ViTs by dynamic token aggregation. As a general method of token hard dropping, our TSM softly integrates redundant tokens into fewer informative ones. It can dynamically zoom visual attention without cutting off discriminative token relations in the images, even with a high slimming ratio. Furthermore, we introduce a concise Feature Recalibration Distillation (FRD) framework, wherein we design a reverse version of TSM (RTSM) to recalibrate the unstructured token in a flexible auto-encoder manner. Due to the similar structure between teacher and student, our FRD can effectively leverage structure knowledge for better convergence. Finally, we conduct extensive experiments to evaluate our SiT. It demonstrates that our method can speed up ViTs by 1.7× with negligible accuracy drop, and even speed up ViTs by 3.6× while maintaining 97% of their performance. Surprisingly, by simply arming LV-ViT with our SiT, we achieve new state-of-the-art performance on ImageNet. Code is available at https://github.com/Sense-X/SiT.

For agents

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

get_harvested_code_for_paper("136710433")
get_code_for_paper("136710433")
have("136710433")

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

curl https://syntology.ai/api/ran/136710433.json

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

[![Syntology run record](https://syntology.ai/api/ran/136710433.svg)](https://syntology.ai/paper/136710433)

Connect an agent — have() is free.