Papers › RISE: Randomized Input Sampling for Explanation of Black-box Models

RISE: Randomized Input Sampling for Explanation of Black-box Models

19 Jun 2018arXiv:1806.07421archive 2025-07-28

Vitali Petsiuk, Abir Das, Kate Saenko

Deep neural networks are being used increasingly to automate data analysis and decision making, yet their decision-making process is largely unclear and is difficult to explain to the end users. In this paper, we address the problem of Explainable AI for deep neural networks that take images as input and output a class probability. We propose an approach called RISE that generates an importance map indicating how salient each pixel is for the model's prediction. In contrast to white-box approaches that estimate pixel importance using gradients or other internal network state, RISE works on black-box models. It estimates importance empirically by probing the model with randomly masked versions of the input image and obtaining the corresponding outputs. We compare our approach to state-of-the-art importance extraction methods using both an automatic deletion/insertion metric and a pointing metric based on human-annotated object segments. Extensive experiments on several benchmark datasets show that our approach matches or exceeds the performance of other methods, including white-box approaches. Project page: http://cs-people.bu.edu/vpetsiuk/rise/

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

No sample from the archive's official repository (eclique/RISE) is linked to this paper; the 34 samples below come from 4 community repositories. Syntology harvested code from eclique/RISE for another paper.

eclique/RISE: Syntology's graph links these samples to New Definitions and Evaluations for Saliency Methods: Staying Intrinsic, Complete and Sound (arXiv:2211.02912; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method.

Syntology 34 code samples harvested from 4 repositories linked to this paper: 32 ran (of which 0 constructed an object rather than computing a result; 32 with no instrument failure: 1 honoured, 0 violated, 31 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: community (archive-listed): 34 samples from 4 repositories, 32 ran (32 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 5 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

13 repositories listed; official and paper-mentioned ones first.

eclique/RISE officialmentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to New Definitions and Evaluations for Saliency Methods: Staying Intrinsic, Complete and Sound (arXiv:2211.02912; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
dbash/zerowaste mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Bootstrapping Semantic Segmentation with Regional Contrast (arXiv:2104.04465; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
ftorres11/saliencysense mentioned on GitHubpytorchMITSyntology: 17 samples, 16 ran (0 instrument-failed) · 1 unverified report
hysts/pytorch_D-RISE mentioned on GitHubpytorchMITSyntology: not harvested report
myurasov/RISE mentioned on GitHubSyntology: not harvested report
openvinotoolkit/datumaro mentioned on GitHubtfMITSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
openvinotoolkit/openvino_xai mentioned on GitHubpytorchApache-2.0Syntology: 8 samples, 8 ran (0 instrument-failed) · 0 unverified report
palatos/RISE_tf mentioned on GitHubtfSyntology: not harvested report
tristangomez44/metrics-saliency-maps mentioned on GitHubpytorchSyntology: not harvested report
vlue-c/PyTorch-Explanations mentioned on GitHubpytorchMITSyntology: 7 samples, 6 ran (0 instrument-failed) · 1 unverified report
vlue-c/Visual-Explanation-Methods-PyTorch mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Learning Important Features Through Propagating Activation Differences (arXiv:1704.02685; that paper's own run record: 8 ran (of which 2 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified); nothing checks that they implement this paper's method. report
wickstrom/relax mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to RELAX: Representation Learning Explainability (arXiv:2112.10161; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
yiskw713/RISE mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization (arXiv:1610.02391; that paper's own run record: 90 ran (of which 32 constructed an object rather than computing a result; 62 with no instrument failure: 6 honoured, 4 violated, 52 with no contract checked; 28 where Syntology's instrument failed) · 51 unverified); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

34 samples harvested: 32 ran (of which 0 constructed an object rather than computing a result; 32 with no instrument failure: 1 honoured, 0 violated, 31 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
31ran
2unverified

Licence: 10 of the 34 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 4 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

ftorres11/saliencysense community (archive-listed) 17 samples, 16 ran (0 instrument-failed) · 1 unverified
binary_gumbel_softmax casme/archs.py ran MIT (permissive) · c75a899b50d166b6 · report fixture: signature logits:Tensor/2/float, tau:float/0/float, hard:bool/0/bool, epsilon:float/0/float · returned Tensor · level recorded 2026-09-25
cam_targetter models/utils.py ran MIT (permissive) · 3ff2de20bf374daa · report fixture: signature model:callable/0/? · returned list · level recorded 2026-09-26
get_mask in 119 papers
census: 9 implementations from 10 papers, 9 distinct outputs across 7 buckets, one shared input per bucket
casme/model_basics.py ran MIT (permissive) · a2f9db8c0650f2df · report fixture: signature input_:Tensor/2/float, model:dict/0/?, use_p:NoneType/0/?, class_ids:NoneType/0/?, get_output:bool/0/bool, no_sigmoid:bool/0/bool · returned Tensor · level recorded 2026-09-25
get_masked_images casme/casme_utils.py ran MIT (permissive) · 544506b6b4e94b6e · report fixture: signature images:Tensor/4/float, binary_mask:Tensor/4/float, gray_scale:int/0/int, return_mask:bool/0/bool · returned tuple · level recorded 2026-09-25
get_masked_images_v2 casme/casme_utils.py ran fingerprinted MIT (permissive) · b257e814f0b02a0e · report fixture: signature batch_x:Tensor/2/float, mask:Tensor/2/float · returned tuple · level recorded 2026-09-25
get_masks_and_check_predictions casme/model_basics.py ran MIT (permissive) · 1eef12cb27f7130e · report fixture: signature input_:Tensor/4/float, target:Tensor/1/int, model:dict/0/?, erode_k:int/0/int, dilate_k:int/0/int, use_p:NoneType/0/?, no_sigmoid:bool/0/bool · returned tuple · level recorded 2026-09-25
ifnone in 6 papers lib/IBA_utils.py ran · honoured contract MIT (permissive) · 6f4763ec77290638 · report fixture: signature a:NoneType/0/?, b:int/0/int · returned int · level recorded 2026-09-22
ignore_superclass_signature casme/core.py ran MIT (permissive) · 9c25a48e312acd33 · report fixture: signature f:callable/0/? · returned function · level recorded 2026-09-25
imagenet_tester lib/data.py ran MIT (permissive) · 5591ec5f001d8f12 · report fixture: signature resize:int/0/int, crop_size:int/0/int · returned Compose · level recorded 2026-09-26
insert_into_sequential lib/IBA.py ran MIT (permissive) · 2051b0d0f5da07d3 · report fixture: signature sequential:callable/0/?, layer:callable/0/?, idx:int/0/int · returned Sequential · level recorded 2026-09-25
outlier_deprocessor lib/data.py ran fingerprinted MIT (permissive) · c65481685dc3709c · report fixture: signature grad_batch:Tensor/4/float · returned Tensor · level recorded 2026-09-26
replace_prefix casme/archs.py ran fingerprinted MIT (permissive) · afc608bf21aa9f05 · report fixture: signature s:str/0/str, prefix:str/0/str · returned str · level recorded 2026-09-25
resnet50shared casme/archs.py ran MIT (permissive) · f067739c23018f46 · report fixture: signature pretrained:bool/0/bool, path:NoneType/0/? · returned ResNet · level recorded 2026-09-25
smooth_deprocessor lib/data.py ran fingerprinted MIT (permissive) · cb904fc4d37fb3ae · report fixture: signature grad_batch:Tensor/4/float · returned Tensor · level recorded 2026-09-26
tensor_to_np_img lib/IBA.py ran MIT (permissive) · 62b5772d8033fdab · report fixture: signature img_t:Tensor/3/float · returned ndarray · level recorded 2026-09-25
to_unit_interval lib/IBA_utils.py ran fingerprinted MIT (permissive) · e5e556749746630d · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-25
load_monkeys lib/IBA_utils.py unverified MIT (permissive) · 9a306d4046aceb10 · report
openvinotoolkit/datumaro community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
loglevel src/datumaro/cli/__main__.py ran MIT recorded; this copy not marked cleared · pointer only · 28e1a63b82c1d344 · report fixture: signature name:str/0/str · returned int · level recorded 2026-09-26
remove_plugin_type src/datumaro/components/cli_plugin.py ran fingerprinted MIT recorded; this copy not marked cleared · pointer only · 09c5cbd7a761b5cc · report fixture: signature s:str/0/str · returned str · level recorded 2026-09-26
openvinotoolkit/openvino_xai community (archive-listed) 8 samples, 8 ran (0 instrument-failed) · 0 unverified
colormap in 14 papers openvino_xai/explainer/visualizer.py ran Apache-2.0 recorded; this copy not marked cleared · pointer only · ad36990c6e8e7653 · report fixture: signature saliency_map:ndarray/3/int, colormap_type:int/0/int · returned ndarray · level recorded 2026-09-26
convert_targets_to_numpy openvino_xai/explainer/utils.py ran fingerprinted Apache-2.0 recorded; this copy not marked cleared · pointer only · e3c80d43208cb814 · report fixture: signature targets:list/1/int · returned ndarray · level recorded 2026-09-26
explains_all openvino_xai/explainer/utils.py ran fingerprinted Apache-2.0 recorded; this copy not marked cleared · pointer only · b88181348223ac7a · report fixture: signature targets:int/0/int · returned bool · level recorded 2026-09-26
get_min_max openvino_xai/common/utils.py ran fingerprinted Apache-2.0 recorded; this copy not marked cleared · pointer only · 20fcc158d33e1d1c · report fixture: signature saliency_map:ndarray/2/float · returned tuple · level recorded 2026-09-26
get_target_indices openvino_xai/explainer/utils.py ran Apache-2.0 recorded; this copy not marked cleared · pointer only · 911b3dde6c0f7336 · report fixture: signature targets:ndarray/1/int, label_names:NoneType/0/? · returned ndarray · level recorded 2026-09-26
overlay in 7 papers openvino_xai/explainer/visualizer.py ran Apache-2.0 recorded; this copy not marked cleared · pointer only · 4d8d016663759432 · report fixture: signature saliency_map:ndarray/3/int, input_image:ndarray/3/int, overlay_weight:float/0/float, cast_to_uint8:bool/0/bool · returned ndarray · level recorded 2026-09-26
resize in 108 papers
census: 10 implementations from 14 papers, 5 distinct outputs across 2 buckets, one shared input per bucket
openvino_xai/explainer/visualizer.py ran Apache-2.0 recorded; this copy not marked cleared · pointer only · eabd217e202d8b8b · report fixture: signature saliency_map:ndarray/3/float, output_size:tuple/1/int · returned ndarray · level recorded 2026-09-26
scaling in 16 papers openvino_xai/common/utils.py ran Apache-2.0 recorded; this copy not marked cleared · pointer only · 161696665a9b902a · report fixture: signature saliency_map:ndarray/3/float, cast_to_uint8:bool/0/bool, max_value:int/0/int · returned ndarray · level recorded 2026-09-26
vlue-c/PyTorch-Explanations community (archive-listed) 7 samples, 6 ran (0 instrument-failed) · 1 unverified
default_transform torchvex/cam/hook.py ran fingerprinted MIT (permissive) · 3d00a41f874efe78 · report fixture: signature feature:Tensor/2/float · returned Tensor · level recorded 2026-09-26
get_gaussian_filter torchvex/metrics/causal.py ran MIT (permissive) · 98736d68924d20ac · report fixture: signature size:int/0/int, sig:float/0/float · returned Tensor · level recorded 2026-09-26
imagenet_transform torchvex/utils/dataset.py ran MIT (permissive) · aa308fe2fc8d575e · report fixture: signature centercrop:bool/0/bool · returned Compose · level recorded 2026-09-26
make_blurred_circular_mask torchvex/meaningful_perturbation/mask.py ran MIT (permissive) · a317e3f45ccf837b · report fixture: signature image:Tensor/4/float, rads:Tensor/1/int · returned Tensor · level recorded 2026-09-26
make_subset_from_fnames torchvex/utils/dataset.py ran MIT (permissive) · 51ae8cf08b64ff6f · report fixture: signature dset:StandInDataset/0/?, fnames:list/1/str · returned Subset · level recorded 2026-09-26
total_variation in 14 papers torchvex/meaningful_perturbation/mask.py ran MIT (permissive) · b0396293b38da996 · report fixture: signature inputs:Tensor/4/float, beta:int/0/int · returned Tensor · level recorded 2026-09-26
gaussian_filter in 21 papers torchvex/meaningful_perturbation/mask.py unverified MIT (permissive) · 049ca000aec357e1 · report

Tasks

Explainable Artificial Intelligence (XAI)Feature ImportanceImage AttributionImage CaptioningImage ClassificationInterpretability Techniques for Deep LearningInterpretable Machine Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Attribution CUB-200-2011 RISE Deletion AUC score (ResNet-101) 0.0665 #3 of 8 Archive leaderboard report
Image Attribution CUB-200-2011 RISE Insertion AUC score (ResNet-101) 0.7193 #3 of 8 Archive leaderboard report
Image Attribution CelebA RISE Deletion AUC score (ArcFace ResNet-101) 0.1444 #2 of 8 Archive leaderboard report
Image Attribution CelebA RISE Insertion AUC score (ArcFace ResNet-101) 0.5703 #2 of 8 Archive leaderboard report
Image Attribution VGGFace2 RISE Deletion AUC score (ArcFace ResNet-101) 0.1375 #3 of 8 Archive leaderboard report
Image Attribution VGGFace2 RISE Insertion AUC score (ArcFace ResNet-101) 0.6530 #3 of 8 Archive leaderboard report
Interpretability Techniques for Deep Learning CelebA RISE Insertion AUC score 0.5703 #1 of 7 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections