Papers › EvDistill: Asynchronous Events to End-task Learning via Bidirectional...

EvDistill: Asynchronous Events to End-task Learning via Bidirectional Reconstruction-guided Cross-modal Knowledge Distillation

24 Nov 2021CVPR 2021 1arXiv:2111.12341archive 2025-07-28

Lin Wang, Yujeong Chae, Sung-Hoon Yoon, Tae-Kyun Kim, Kuk-Jin Yoon

Event cameras sense per-pixel intensity changes and produce asynchronous event streams with high dynamic range and less motion blur, showing advantages over conventional cameras. A hurdle of training event-based models is the lack of large qualitative labeled data. Prior works learning end-tasks mostly rely on labeled or pseudo-labeled datasets obtained from the active pixel sensor (APS) frames; however, such datasets' quality is far from rivaling those based on the canonical images. In this paper, we propose a novel approach, called EvDistill, to learn a student network on the unlabeled and unpaired event data (target modality) via knowledge distillation (KD) from a teacher network trained with large-scale, labeled image data (source modality). To enable KD across the unpaired modalities, we first propose a bidirectional modality reconstruction (BMR) module to bridge both modalities and simultaneously exploit them to distill knowledge via the crafted pairs, causing no extra computation in the inference. The BMR is improved by the end-tasks and KD losses in an end-to-end manner. Second, we leverage the structural similarities of both modalities and adapt the knowledge by matching their distributions. Moreover, as most prior feature KD methods are uni-modality and less applicable to our problem, we propose to leverage an affinity graph KD loss to boost the distillation. Our extensive experiments on semantic segmentation and object recognition demonstrate that EvDistill achieves significantly better results than the prior works and KD with only events and APS frames.

PaperPDFConference PDFCodeCode Syntology ranMethod as code

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

Syntology 17 code samples harvested from 1 repository linked to this paper: 10 ran (of which 6 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 4 where Syntology's instrument failed) · 7 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 17 samples from 1 repository, 10 ran (6 with no instrument failure; 4 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.

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

addisonwang2013/evdistill officialmentioned in papermentioned on GitHubpytorchSyntology: 17 samples, 10 ran (4 instrument-failed) · 7 unverified 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.

Code Syntology ran Syntology

17 samples harvested: 10 ran (of which 6 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 4 where Syntology's instrument failed) · 7 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.

4ran · our draft was wrong
6ran
7unverified

Licence: 17 of the 17 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 addisonwang2013/evdistill. “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”. For 4 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “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.

addisonwang2013/evdistill official repository 17 samples, 10 ran (4 instrument-failed) · 7 unverified
EDSRConv modeling/deeplab.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 3a07013be7ddb70a · report fixture: returned EDSRConv · level recorded 2026-09-22
FutureResult modeling/deeplab.py ran no licence file found · pointer only · 9e8c636cac1d847f · report fixture: returned FutureResult · level recorded 2026-09-22
SyncMaster modeling/deeplab.py ran no licence file found · pointer only · 93f1be24e0653bc8 · report fixture: returned SyncMaster · level recorded 2026-09-22
SynchronizedBatchNorm2d in 7 papers modeling/deeplab.py ran · metamorphic tier: deterministic no licence file found · pointer only · e6f91e80712a76dd · report fixture: returned SynchronizedBatchNorm2d · level recorded 2026-09-22
Upsample in 77 papers modeling/deeplab.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 618ccc4e9e5629b2 · report fixture: returned Upsample · level recorded 2026-09-22
_SynchronizedBatchNorm in 7 papers modeling/deeplab.py ran · metamorphic tier: deterministic no licence file found · pointer only · 9f557ce8389a603f · report fixture: returned _SynchronizedBatchNorm · level recorded 2026-09-22
build_aspp in 10 papers modeling/deeplab.py ran · our draft was wrong no licence file found · pointer only · ef8cd9ec7017137d · report fixture: signature backbone:str/0/str, output_stride:int/0/int, BatchNorm:callable/0/? · returned ASPP · level recorded 2026-09-22
build_backbone in 29 papers modeling/deeplab.py ran · our draft was wrong no licence file found · pointer only · 8157861ceb8eb470 · report fixture: returned MockResNet101 · level recorded 2026-09-22
build_decoder in 18 papers modeling/deeplab.py ran · our draft was wrong no licence file found · pointer only · 23ce2fc66128ad4c · report fixture: signature num_classes:int/0/int, backbone:str/0/str, BatchNorm:callable/0/? · returned Decoder · level recorded 2026-09-22
build_im_recon_decoder modeling/deeplab.py ran · our draft was wrong no licence file found · pointer only · 5e5f8123e17483ef · report fixture: signature num_classes:int/0/int, backbone:str/0/str, BatchNorm:callable/0/? · returned Decoder · level recorded 2026-09-22
ASPP in 23 papers modeling/deeplab.py unverified no licence file found · pointer only · fced7a51f0af7316 · report
ASPP_Nodropout modeling/deeplab.py unverified no licence file found · pointer only · 89524076ef47e188 · report
Decoder in 210 papers modeling/deeplab.py unverified no licence file found · pointer only · f5402b45ac78ab62 · report
Decoder_DTL modeling/deeplab.py unverified no licence file found · pointer only · 6dad7760a37b19c3 · report
Decoder_Nodropout modeling/deeplab.py unverified no licence file found · pointer only · d12c50019a4b5875 · report
DeepLab_Dual_V3 modeling/deeplab.py unverified no licence file found · pointer only · e2b82e4055074f54 · report
_ASPPModule in 7 papers modeling/deeplab.py unverified no licence file found · pointer only · 5e90ce39dc46a1c4 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for EvDistill (graph method: EvDistill). 20 bricks; individually on a fixture: 13 ran (of which 7 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 1 violated, 7 with no contract checked; 4 where Syntology's instrument failed) · 7 unverified. The assembly has not been run end-to-end.

  1. DeepLab_Dual_V3 entry · level 0 · unverified · e2b82e4055074f54
  2. EDSRConv helper · level 1 · ran · 3a07013be7ddb70a
  3. SynchronizedBatchNorm2d helper · level 1 · ran · e6f91e80712a76dd
  4. Upsample helper · level 1 · ran · 618ccc4e9e5629b2
  5. build_aspp helper · level 1 · ran · our draft was wrong · ef8cd9ec7017137d
  6. build_backbone helper · level 1 · ran · our draft was wrong · 8157861ceb8eb470
  7. build_decoder helper · level 1 · ran · our draft was wrong · 23ce2fc66128ad4c
  8. build_im_recon_decoder helper · level 1 · ran · our draft was wrong · 5e5f8123e17483ef
  9. _SynchronizedBatchNorm helper · level 1 · ran · 9f557ce8389a603f
  10. ASPP helper · level 0 · unverified · fced7a51f0af7316
  11. ASPP_Nodropout helper · level 0 · unverified · 89524076ef47e188
  12. Decoder helper · level 0 · unverified · f5402b45ac78ab62
  13. Decoder_DTL helper · level 0 · unverified · 6dad7760a37b19c3
  14. Decoder_Nodropout helper · level 0 · unverified · d12c50019a4b5875
  15. SyncMaster helper · level 1 · ran · 93f1be24e0653bc8
  16. _sum_ft helper · level 1 · ran · violated contract · 3151cee68a1020dc
  17. _unsqueeze_ft helper · level 1 · ran · honoured contract · 1efd43bcf31727c0
  18. _ASPPModule helper · level 0 · unverified · 5e90ce39dc46a1c4
  19. FutureResult helper · level 1 · ran · 9e8c636cac1d847f
  20. SlavePipe helper · level 1 · ran · e75aa93b78286d50

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2111.12341") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Event-based Object SegmentationKnowledge DistillationObject RecognitionSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Event-based Object Segmentation MVSEC-SEG Evdistill mIoU 0.29 #7 of 8 Archive leaderboard report
Event-based Object Segmentation RGBE-SEG Evdistill mIoU 0.27 #7 of 8 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.

Methods

Knowledge Distillation

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