SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2109.07036 · ICCV · 2021

PnP-DETR: Towards Efficient Visual Analysis with Transformers

Jiashi Feng, Li Yuan, Tao Wang, Shuicheng Yan, Yunpeng Chen

arXiv · PDF · Open in the Atlas

Code that ran

1 of 1 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 0 failures of our instrument; 0 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/2109.07036.json · badge: /api/ran/2109.07036.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
twangnh/pnp-detr marked official in Papers with Code
Papers with Code archive
1 ran · 0 no recorded run
FunctionStatusWhere it lives
SortSampler Ran
ran on a synthesized input · constructed an object; no result was computed
twangnh/pnp-detr/models/transformer.py
code served (permissive licence) · get_code("44801132969484cd")
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 an instance of its own class, SortSampler: the run constructed the object and did not call it, so no result was computed. 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
from torch import nn

torch.manual_seed(0)

# Define ARGS dict with all parameters for SortSampler
ARGS = {
    'topk_ratio': 0.5,
    'input_dim': 4,
    'score_pred_net': '2layer-fc-256',
    'kproj_net': '2layer-fc',
    'unsample_abstract_number': 30,
    'pos_embed_kproj': False,
}

# Setup for forward() call - create test data
def create_forward_inputs():
    batch_size = 2
    input_dim = 4
    height = 3
    width = 3
    
    # src: (bs, c, h, w)
    src = torch.randn(batch_size, input_dim, height, width)
    
    # mask: (bs, h*w) - boolean tensor
    mask = torch.zeros(batch_size, height * width, dtype=torch.bool)
    mask[0, :2] = True  # mask out first 2 positions in first batch
    
    # pos_embed: (h*w, bs, c)
    pos_embed = torch.randn(height * width, batch_size, input_dim)
    
    # sample_ratio: float or None
    sample_ratio = 0.5
    
    return src, mask, pos_embed, sample_ratio
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 SortSampler — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a SortSampler 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

Also present in other papers' code

Of 1 samples lifted from this paper's linked repositories, 1 carry a function identity and 0 do not. Of the 1 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 1 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.

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, DETR [3] pioneered the solution of vision tasks with transformers, it directly translates the image feature map into the object detection result. Though effective, translating the full feature map can be costly due to redundant computation on some area like the background. In this work, we encapsulate the idea of reducing spatial redundancy into a novel poll and pool (PnP) sampling module, with which we build an end-to-end PnP-DETR architecture that adaptively allocates its computation spatially to be more efficient. Concretely, the PnP module abstracts the image feature map into fine foreground object feature vectors and a small number of coarse background contextual feature vectors. The transformer models information interaction within the fine-coarse feature space and translates the features into the detection result. Moreover, the PnP-augmented model can instantly achieve various desired trade-offs between performance and computation with a single model by varying the sampled feature length, without requiring to train multiple models as existing methods. Thus it offers greater flexibility for deployment in diverse scenarios with varying computation constraint. We further validate the generalizability of the PnP module on panoptic segmentation and the recent transformer-based image recognition model ViT [7] and show consistent efficiency gain. We believe our method makes a step for efficient visual analysis with transformers, wherein spatial redundancy is commonly observed. Code and models will be available.

For agents

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

get_harvested_code_for_paper("2109.07036")
get_code_for_paper("2109.07036")
have("2109.07036")

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

curl https://syntology.ai/api/ran/2109.07036.json

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

[![Syntology run record](https://syntology.ai/api/ran/2109.07036.svg)](https://syntology.ai/paper/2109.07036)

Connect an agent — have() is free.