SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2302.04869 · CVPR · 2022

Reversible Vision Transformers

Jitendra Malik, Chao-Yuan Wu, Karttikeya Mangalam, Christoph Feichtenhofer, Haoqi Fan, Yanghao Li, Bo Xiong

arXiv · PDF · Open in the Atlas

Code that ran

24 of 29 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (5 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 9 have no contract verdict; 15 failures of our instrument; 5 no recorded run), measured 2026-11-21; 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/2302.04869.json · badge: /api/ran/2302.04869.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
facebookresearch/mvit canonical (classifier label)
classifier basis not recorded on the link
12 ran · 3 no recorded run
facebookresearch/SlowFast canonical (classifier label)
classifier basis not recorded on the link
5 ran · 1 no recorded run
open-mmlab/mmclassification canonical (classifier label)
classifier basis not recorded on the link
2 ran · 1 no recorded run
karttikeya/minrev marked official in Papers with Code
Papers with Code archive
5 ran · 0 no recorded run
FunctionStatusWhere it lives
AttentionSubBlock Ran
ran on a synthesized input · constructed an object; no result was computed
karttikeya/minrev/rev.py
pointer only (licence: NONE) · get_code("7a79df18a8737c98")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, karttikeya/minrev 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.

MLPSubblock Ran
ran on a synthesized input · constructed an object; no result was computed
karttikeya/minrev/rev.py
pointer only (licence: NONE) · get_code("907cd8a323eb8319")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, karttikeya/minrev 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.

RevBackProp Ran
ran on a synthesized input · constructed an object; no result was computed
karttikeya/minrev/rev.py
pointer only (licence: NONE) · get_code("27fd09daf2d75017")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, karttikeya/minrev 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.

RevViT Ran
ran on a synthesized input · constructed an object; no result was computed
karttikeya/minrev/rev.py
pointer only (licence: NONE) · get_code("a306e79d47b4c032")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, karttikeya/minrev 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.

ReversibleBlock Ran
ran on a synthesized input · constructed an object; no result was computed
karttikeya/minrev/rev.py
pointer only (licence: NONE) · get_code("2d92c96d4cb34c69")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, karttikeya/minrev 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.

assert_and_infer_cfg Ran
ran on a synthesized input
facebookresearch/mvit/mvit/config/defaults.py
pointer only (licence: Apache-2.0) · get_code("4c9ffd3f576a6936")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, facebookresearch/mvit, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

attention_pool Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
facebookresearch/mvit/mvit/models/attention.py
pointer only (licence: Apache-2.0) · get_code("049db0114a85e508")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, facebookresearch/mvit, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

cal_rel_pos_spatial Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
facebookresearch/SlowFast/slowfast/models/attention.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from rajatmodi62/OccludedActionBenchmark, is pointer only (licence: NONE) · get_code("156d0bf08e703f3c")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, facebookresearch/SlowFast, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

ckpt_to_state_dict Ran
ran; our contract draft was wrong, not the code
open-mmlab/mmclassification/.dev_scripts/ckpt_tree.py
code served (permissive licence) · get_code("a322f2edda4b2d6e")
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 dict. 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

torch.manual_seed(0)

# The function expects a checkpoint dict and an optional key parameter
# The checkpoint should contain state_dict tensors in various possible formats

# Create a sample state dict with model parameters
state_dict_content = {
    'layer1.weight': torch.randn(4, 3),
    'layer1.bias': torch.randn(4),
    'layer2.weight': torch.randn(5, 4),
    'layer2.bias': torch.randn(5),
}

# Test case 1: checkpoint with explicit 'state_dict' key
checkpoint_with_state_dict_key = {
    'state_dict': state_dict_content,
    'epoch': 10,
    'optimizer': {},
}

ARGS = {
    'checkpoint': checkpoint_with_state_dict_key,
    'key': None,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
contrastive_forward Ran
ran on a synthesized input
facebookresearch/SlowFast/slowfast/models/contrastive.py
pointer only (licence: Apache-2.0) · get_code("b5b248acb6375fcc")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, facebookresearch/SlowFast, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

convert_to_one_hot Ran
ran; our contract draft was wrong, not the code
facebookresearch/mvit/mvit/datasets/mixup.py
pointer only (licence: Apache-2.0) · get_code("547be2babaca4859")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, facebookresearch/mvit, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

drop_path Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
facebookresearch/SlowFast/slowfast/models/common.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from rajatmodi62/OccludedActionBenchmark, is pointer only (licence: NONE) · get_code("bcc1cdae3bb3212c")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, facebookresearch/SlowFast, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

filter_models_by_task Ran
ran; our contract draft was wrong, not the code
open-mmlab/mmclassification/.dev_scripts/generate_readme.py
code served (permissive licence) · get_code("8eebff71c1cabe84")
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 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
import torch.nn as nn

torch.manual_seed(0)

class Result:
    def __init__(self, task):
        self.task = task

class Model:
    def __init__(self, results=None):
        self.results = results

# Create models with different result configurations
model1 = Model(results=None)  # No results, should match when task is None
model2 = Model(results=[Result(task='classification')])  # Has results with specific task
model3 = Model(results=[Result(task='segmentation')])  # Has results with different task
model4 = Model(results=[Result(task='detection')])  # Has results with another task

models = [model1, model2, model3, model4]

# Test with task='classification' to filter models
task = 'classification'

ARGS = {
    'models': models,
    'task': task
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
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
get_ld_param_groups Ran
ran on a synthesized input
facebookresearch/mvit/mvit/models/optimizer.py
pointer only (licence: Apache-2.0) · get_code("366cdd880af84645")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, facebookresearch/mvit, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

get_loss_func Ran
ran; our contract draft was wrong, not the code
facebookresearch/mvit/mvit/models/losses.py
pointer only (licence: Apache-2.0) · get_code("836ddfc4a5544d55")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, facebookresearch/mvit, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

get_param_groups Ran
ran on a synthesized input
facebookresearch/mvit/mvit/models/optimizer.py
pointer only (licence: Apache-2.0) · get_code("4b81f68c735859d7")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, facebookresearch/mvit, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

get_rel_pos Ran
ran; our contract draft was wrong, not the code
facebookresearch/SlowFast/slowfast/models/attention.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from rajatmodi62/OccludedActionBenchmark, is pointer only (licence: NONE) · get_code("5fc6c9c916e0ebc7")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, facebookresearch/SlowFast, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

l2_loss Ran
ran; our contract draft was wrong, not the code
facebookresearch/SlowFast/slowfast/models/contrastive.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from rajatmodi62/OccludedActionBenchmark, is pointer only (licence: NONE) · get_code("1ef3753d70ebb220")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, facebookresearch/SlowFast, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

mixup_target Ran
ran; our contract draft was wrong, not the code
facebookresearch/mvit/mvit/datasets/mixup.py
pointer only (licence: Apache-2.0) · get_code("fd3e5fd51b6d7296")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, facebookresearch/mvit, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

multiple_samples_collate Ran
ran; our contract draft was wrong, not the code
facebookresearch/mvit/mvit/datasets/loader.py
pointer only (licence: Apache-2.0) · get_code("4927733091f71100")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, facebookresearch/mvit, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

rand_bbox Ran
ran; our contract draft was wrong, not the code
facebookresearch/mvit/mvit/datasets/mixup.py
pointer only (licence: Apache-2.0) · get_code("f18f66adc8c6b70f")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, facebookresearch/mvit, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

shear_x Ran
ran; our contract draft was wrong, not the code
facebookresearch/mvit/mvit/datasets/rand_augment.py
pointer only (licence: Apache-2.0) · get_code("e866e1196986f728")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, facebookresearch/mvit, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

shear_y Ran
ran; our contract draft was wrong, not the code
facebookresearch/mvit/mvit/datasets/rand_augment.py
pointer only (licence: Apache-2.0) · get_code("7b2503c99c9447fb")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, facebookresearch/mvit, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

translate_x_rel Ran
ran; our contract draft was wrong, not the code
facebookresearch/mvit/mvit/datasets/rand_augment.py
pointer only (licence: Apache-2.0) · get_code("323759f906fbb394")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, facebookresearch/mvit, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

attention_pool Not yet run
unverified (harvested, no recorded run)
facebookresearch/SlowFast/slowfast/models/attention.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from rajatmodi62/OccludedActionBenchmark, is pointer only (licence: NONE) · get_code("a4723eab8df61dbe")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, facebookresearch/SlowFast, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

cal_rel_pos_spatial Not yet run
unverified (harvested, no recorded run)
facebookresearch/mvit/mvit/models/attention.py
pointer only (licence: Apache-2.0) · get_code("5de56fec3ce10382")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, facebookresearch/mvit, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

construct_loader Not yet run
unverified (harvested, no recorded run)
facebookresearch/mvit/mvit/datasets/loader.py
pointer only (licence: Apache-2.0) · get_code("7ca72f77bea1e546")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, facebookresearch/mvit, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

construct_optimizer Not yet run
unverified (harvested, no recorded run)
facebookresearch/mvit/mvit/models/optimizer.py
pointer only (licence: Apache-2.0) · get_code("8e7aad946e7f3346")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, facebookresearch/mvit, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

get_flops_params Not yet run
unverified (harvested, no recorded run)
open-mmlab/mmclassification/.dev_scripts/fill_metafile.py
code served (permissive licence) · get_code("9abd4b00a0d36a31")
How it ran

no invocation recorded.

Also present in other papers' code

Of 29 samples lifted from this paper's linked repositories, 29 carry a function identity and 0 do not. Of the 29 distinct functions with an identity, 18 are also present in other papers whose code we hold (10 with at least one paper dated earlier, 0 the same month, 18 later) and 11 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
shear_x 27 other papers
11 dated earlier, 16 later
1811.12814 (2018-11)
Graph-Based Global Reasoning Networks
2109.03508 (2021-09)
RepNAS: Searching for Efficient Re-parameterizing Blocks
2109.06165 (2021-09)
CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptation
and 24 more not named here
shear_y 27 other papers
11 dated earlier, 16 later
1811.12814 (2018-11)
Graph-Based Global Reasoning Networks
2109.03508 (2021-09)
RepNAS: Searching for Efficient Re-parameterizing Blocks
2109.06165 (2021-09)
CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptation
and 24 more not named here
translate_x_rel 26 other papers
11 dated earlier, 15 later
1811.12814 (2018-11)
Graph-Based Global Reasoning Networks
2109.03508 (2021-09)
RepNAS: Searching for Efficient Re-parameterizing Blocks
2109.06165 (2021-09)
CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptation
and 23 more not named here
rand_bbox 14 other papers
5 dated earlier, 9 later
2109.03508 (2021-09)
RepNAS: Searching for Efficient Re-parameterizing Blocks
2111.06377 (2021-11)
Masked Autoencoders Are Scalable Vision Learners
2206.13559 (2022-06)
ST-Adapter: Parameter-Efficient Image-to-Video Transfer Learning
and 11 more not named here
get_loss_func 13 other papers
7 dated earlier, 6 later
1812.03982 (2018-12)
SlowFast Networks for Video Recognition
2105.11731 (2021-05)
ST-HOI: A Spatial-Temporal Baseline for Human-Object Interaction Detection in Videos
2106.09703 (2021-06)
MaCLR: Motion-aware Contrastive Learning of Representations for Videos
and 10 more not named here
drop_path 11 other papers
6 dated earlier, 5 later
2106.09703 (2021-06)
MaCLR: Motion-aware Contrastive Learning of Representations for Videos
2110.06915 (2021-10)
Object-Region Video Transformers
2110.07058 (2021-10)
Ego4D: Around the World in 3,000 Hours of Egocentric Video
and 8 more not named here
attention_pool 8 other papers
5 dated earlier, 3 later
2106.09703 (2021-06)
MaCLR: Motion-aware Contrastive Learning of Representations for Videos
2110.06915 (2021-10)
Object-Region Video Transformers
136950068 (2022 (year only))
Efficient Video Transformers with Spatial-Temporal Token Selection
and 5 more not named here
attention_pool 3 other papers
3 later · 1 only as an assembly brick
2402.11301 (2024-02)
ReViT: Enhancing Vision Transformers Feature Diversity with Attention Residual Connections
2406.20092 (2024-06)
Efficient Large Multi-modal Models via Visual Context Compression
2601.22674 (2026-01)
VisionTrim: Unified Vision Token Compression for Training-Free MLLM Acceleration
cal_rel_pos_spatial 3 other papers
3 later · 1 only as an assembly brick
2402.11301 (2024-02)
ReViT: Enhancing Vision Transformers Feature Diversity with Attention Residual Connections
2406.20092 (2024-06)
Efficient Large Multi-modal Models via Visual Context Compression
2601.22674 (2026-01)
VisionTrim: Unified Vision Token Compression for Training-Free MLLM Acceleration
convert_to_one_hot 3 other papers
1 dated earlier, 2 later
2206.13559 (2022-06)
ST-Adapter: Parameter-Efficient Image-to-Video Transfer Learning
2306.07703 (2023-06)
E2E-LOAD: End-to-End Long-form Online Action Detection
2402.11301 (2024-02)
ReViT: Enhancing Vision Transformers Feature Diversity with Attention Residual Connections
get_rel_pos 3 other papers
3 later
2401.11174 (2024-01)
Pixel-Wise Recognition for Holistic Surgical Scene Understanding
2403.05856 (2024-03)
POV: Prompt-Oriented View-Agnostic Learning for Egocentric Hand-Object Interaction in the Multi-View World
2410.19553 (2024-10)
On Occlusions in Video Action Detection: Benchmark Datasets And Training Recipes
cal_rel_pos_spatial 2 other papers
2 later
2401.11174 (2024-01)
Pixel-Wise Recognition for Holistic Surgical Scene Understanding
2410.19553 (2024-10)
On Occlusions in Video Action Detection: Benchmark Datasets And Training Recipes
mixup_target 2 other papers
1 dated earlier, 1 later
2206.13559 (2022-06)
ST-Adapter: Parameter-Efficient Image-to-Video Transfer Learning
2402.11301 (2024-02)
ReViT: Enhancing Vision Transformers Feature Diversity with Attention Residual Connections
multiple_samples_collate 2 other papers
1 dated earlier, 1 later
2301.00184 (2023-01)
Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?
2410.10589 (2024-10)
MoTE: Reconciling Generalization with Specialization for Visual-Language to Video Knowledge Transfer
ckpt_to_state_dict 1 other paper
1 later
2406.04801 (2024-06)
MoE Jetpack: From Dense Checkpoints to Adaptive Mixture of Experts for Vision Tasks
filter_models_by_task 1 other paper
1 later
2406.04801 (2024-06)
MoE Jetpack: From Dense Checkpoints to Adaptive Mixture of Experts for Vision Tasks
get_flops_params 1 other paper
1 later
2406.04801 (2024-06)
MoE Jetpack: From Dense Checkpoints to Adaptive Mixture of Experts for Vision Tasks
l2_loss 1 other paper
1 later
2410.19553 (2024-10)
On Occlusions in Video Action Detection: Benchmark Datasets And Training Recipes

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 2026-11-21.

Repositories linked to this paper

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

Abstract

We present Reversible Vision Transformers, a memory efficient architecture design for visual recognition. By decoupling the GPU memory footprint from the depth of the model, Reversible Vision Transformers enable memory efficient scaling of transformer architectures. We adapt two popular models, namely Vision Transformer and Multiscale Vision Transformers, to reversible variants and benchmark extensively across both model sizes and tasks of image classification, object detection and video classification. Reversible Vision Transformers achieve a reduced memory footprint of up to 15.5× at identical model complexity, parameters and accuracy, demonstrating the promise of reversible vision transformers as an efficient backbone for resource limited training regimes. Finally, we find that the additional computational burden of recomputing activations is more than overcome for deeper models, where throughput can increase up to 3.9× over their non-reversible counterparts. Code and models are available at https:// github.com/facebookresearch/mvit.

For agents

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

get_harvested_code_for_paper("2302.04869")
get_code_for_paper("2302.04869")
have("2302.04869")

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

curl https://syntology.ai/api/ran/2302.04869.json

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

[![Syntology run record](https://syntology.ai/api/ran/2302.04869.svg)](https://syntology.ai/paper/2302.04869)

Connect an agent — have() is free.