SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2002.10025 · ICLR · 2020

Triple Wins: Boosting Accuracy, Robustness and Efficiency Together by Enabling Input-Adaptive Inference

Ting-Kuei Hu, Tianlong Chen, Haotao Wang, Zhangyang Wang

arXiv · PDF · Open in the Atlas

Code that ran

12 of 18 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (3 of them constructed an object rather than computing a result; 4 honoured the contract we drafted, 0 violated it and 6 have no contract verdict; 2 failures of our instrument; 6 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/2002.10025.json · badge: /api/ran/2002.10025.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
gorakraj/earlyexit_onnx community
Papers with Code archive
9 ran · 6 no recorded run
TAMU-VITA/triple-wins marked official in Papers with Code
Papers with Code archive
3 ran · 0 no recorded run
FunctionStatusWhere it lives
Block_V3 Ran
ran on a synthesized input · constructed an object; no result was computed
TAMU-VITA/triple-wins/cifar/models_baseline.py
pointer only (licence: NONE) · get_code("f4f526cd0c092320")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, TAMU-VITA/triple-wins 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.

ChannelScalerLayer Ran
ran on a synthesized input · constructed an object; no result was computed
TAMU-VITA/triple-wins/cifar/models_baseline.py
pointer only (licence: NONE) · get_code("b6b875971ee15fe6")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, TAMU-VITA/triple-wins 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.

InternalClassifier Ran
ran on a synthesized input
gorakraj/earlyexit_onnx/Networks/8. L2Stop/l2stop-master/sdn_stop/architectures/SDNs/ResNet_SDN.py
pointer only (licence: NONE) · get_code("4b34fc3c728d64ca")
How it ran

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

MobileNetV2_CP Ran
ran on a synthesized input · constructed an object; no result was computed
TAMU-VITA/triple-wins/cifar/models_baseline.py
pointer only (licence: NONE) · get_code("ec6ecae0e14e3a1c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, TAMU-VITA/triple-wins 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.

feature_reduction_formula Ran
ran, honoured the contract we drafted
gorakraj/earlyexit_onnx/Networks/8. L2Stop/l2stop-master/sdn_stop/architectures/SDNs/ResNet_SDN.py
pointer only (licence: NONE) · get_code("f79d8861a3c36477")
How it ran

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

get_loader Ran
ran on a synthesized input
gorakraj/earlyexit_onnx/Networks/8. L2Stop/l2stop-master/sdn_stop/architectures/SDNs/ResNet_SDN.py
pointer only (licence: NONE) · get_code("f5036fe874e2e4de")
How it ran

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

get_loss_criterion Ran
ran on a synthesized input
gorakraj/earlyexit_onnx/Networks/8. L2Stop/l2stop-master/sdn_stop/architectures/SDNs/ResNet_SDN.py
pointer only (licence: NONE) · get_code("ff3039ef77961436")
How it ran

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

get_lr Ran
ran, honoured the contract we drafted
gorakraj/earlyexit_onnx/Networks/8. L2Stop/l2stop-master/sdn_stop/architectures/SDNs/ResNet_SDN.py
pointer only (licence: NONE) · get_code("1aca7be4e59a01a0")
How it ran

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

sdn_ic_only_step Ran
ran, honoured the contract we drafted
gorakraj/earlyexit_onnx/Networks/8. L2Stop/l2stop-master/sdn_stop/architectures/SDNs/ResNet_SDN.py
pointer only (licence: NONE) · get_code("84f507ee66e79376")
How it ran

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

sdn_ic_only_step_DS Ran
ran, honoured the contract we drafted
gorakraj/earlyexit_onnx/Networks/8. L2Stop/l2stop-master/sdn_stop/architectures/SDNs/ResNet_SDN.py
pointer only (licence: NONE) · get_code("6f65a35f5e8d93bc")
How it ran

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

sdn_training_step Ran
ran; our contract draft was wrong, not the code
gorakraj/earlyexit_onnx/Networks/8. L2Stop/l2stop-master/sdn_stop/architectures/SDNs/ResNet_SDN.py
pointer only (licence: NONE) · get_code("0f6294604cc0a722")
How it ran

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

sdn_training_step_DS Ran
ran; our contract draft was wrong, not the code
gorakraj/earlyexit_onnx/Networks/8. L2Stop/l2stop-master/sdn_stop/architectures/SDNs/ResNet_SDN.py
pointer only (licence: NONE) · get_code("d0092b78fbcce2b3")
How it ran

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

BasicBlockWOutput Not yet run
unverified (harvested, no recorded run)
gorakraj/earlyexit_onnx/Networks/8. L2Stop/l2stop-master/sdn_stop/architectures/SDNs/ResNet_SDN.py
pointer only (licence: NONE) · get_code("bc9d472adc5e3a89")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, gorakraj/earlyexit_onnx 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. No invocation recorded.

ResNet_SDN Not yet run
unverified (harvested, no recorded run)
gorakraj/earlyexit_onnx/Networks/8. L2Stop/l2stop-master/sdn_stop/architectures/SDNs/ResNet_SDN.py
pointer only (licence: NONE) · get_code("e62a922e2ca01bbe")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, gorakraj/earlyexit_onnx 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. No invocation recorded.

accuracy Not yet run
unverified (harvested, no recorded run)
gorakraj/earlyexit_onnx/Networks/8. L2Stop/l2stop-master/sdn_stop/architectures/SDNs/ResNet_SDN.py
pointer only (licence: NONE) · get_code("0ae2381aa39b7e94")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, gorakraj/earlyexit_onnx 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. No invocation recorded.

sdn_get_detailed_results Not yet run
unverified (harvested, no recorded run)
gorakraj/earlyexit_onnx/Networks/8. L2Stop/l2stop-master/sdn_stop/architectures/SDNs/ResNet_SDN.py
pointer only (licence: NONE) · get_code("2cca158ee7052b0e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, gorakraj/earlyexit_onnx 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. No invocation recorded.

sdn_test Not yet run
unverified (harvested, no recorded run)
gorakraj/earlyexit_onnx/Networks/8. L2Stop/l2stop-master/sdn_stop/architectures/SDNs/ResNet_SDN.py
pointer only (licence: NONE) · get_code("2e45239eb5fb93a7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, gorakraj/earlyexit_onnx 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. No invocation recorded.

sdn_train Not yet run
unverified (harvested, no recorded run)
gorakraj/earlyexit_onnx/Networks/8. L2Stop/l2stop-master/sdn_stop/architectures/SDNs/ResNet_SDN.py
pointer only (licence: NONE) · get_code("e7ce5602ca2a2ea8")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, gorakraj/earlyexit_onnx 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. No invocation recorded.

Also present in other papers' code

Of 18 samples lifted from this paper's linked repositories, 18 carry a function identity and 0 do not. Of the 18 distinct functions with an identity, 4 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 4 later) and 14 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
accuracy
brick of this paper's assembly: helper
2 other papers
2 later
2010.02432 (2020-10)
A Panda? No, It's a Sloth: Slowdown Attacks on Adaptive Multi-Exit Neural Network Inference
136710691 (2022 (year only))
Meta-GF: Training Dynamic-Depth Neural Networks Harmoniously
feature_reduction_formula
brick of this paper's assembly: helper
2 other papers
2 later
2010.02432 (2020-10)
A Panda? No, It's a Sloth: Slowdown Attacks on Adaptive Multi-Exit Neural Network Inference
136710691 (2022 (year only))
Meta-GF: Training Dynamic-Depth Neural Networks Harmoniously
get_loader
brick of this paper's assembly: helper
1 other paper
1 later
2010.02432 (2020-10)
A Panda? No, It's a Sloth: Slowdown Attacks on Adaptive Multi-Exit Neural Network Inference
sdn_training_step_DS
brick of this paper's assembly: helper
1 other paper
1 later
2006.05082 (2020-06)
Learning to Stop While Learning to Predict

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

Deep networks were recently suggested to face the odds between accuracy (on clean natural images) and robustness (on adversarially perturbed images) (Tsipras et al., 2019). Such a dilemma is shown to be rooted in the inherently higher sample complexity (Schmidt et al., 2018) and/or model capacity (Nakkiran, 2019), for learning a high-accuracy and robust classifier. In view of that, give a classification task, growing the model capacity appears to help draw a win-win between accuracy and robustness, yet at the expense of model size and latency, therefore posing challenges for resource-constrained applications. Is it possible to co-design model accuracy, robustness and efficiency to achieve their triple wins? This paper studies multi-exit networks associated with input-adaptive efficient inference, showing their strong promise in achieving a "sweet point" in cooptimizing model accuracy, robustness and efficiency. Our proposed solution, dubbed Robust Dynamic Inference Networks (RDI-Nets), allows for each input (either clean or adversarial) to adaptively choose one of the multiple output layers (early branches or the final one) to output its prediction. That multi-loss adaptivity adds new variations and flexibility to adversarial attacks and defenses, on which we present a systematical investigation. We show experimentally that by equipping existing backbones with such robust adaptive inference, the resulting RDI-Nets can achieve better accuracy and robustness, yet with over 30% computational savings, compared to the defended original models.

For agents

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

get_harvested_code_for_paper("2002.10025")
get_code_for_paper("2002.10025")
have("2002.10025")

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

curl https://syntology.ai/api/ran/2002.10025.json

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

[![Syntology run record](https://syntology.ai/api/ran/2002.10025.svg)](https://syntology.ai/paper/2002.10025)

Connect an agent — have() is free.