Papers › RECALL: Replay-based Continual Learning in Semantic Segmentation

RECALL: Replay-based Continual Learning in Semantic Segmentation

8 Aug 2021ICCV 2021 10arXiv:2108.03673archive 2025-07-28

Andrea Maracani, Umberto Michieli, Marco Toldo, Pietro Zanuttigh

Deep networks allow to obtain outstanding results in semantic segmentation, however they need to be trained in a single shot with a large amount of data. Continual learning settings where new classes are learned in incremental steps and previous training data is no longer available are challenging due to the catastrophic forgetting phenomenon. Existing approaches typically fail when several incremental steps are performed or in presence of a distribution shift of the background class. We tackle these issues by recreating no longer available data for the old classes and outlining a content inpainting scheme on the background class. We propose two sources for replay data. The first resorts to a generative adversarial network to sample from the class space of past learning steps. The second relies on web-crawled data to retrieve images containing examples of old classes from online databases. In both scenarios no samples of past steps are stored, thus avoiding privacy concerns. Replay data are then blended with new samples during the incremental steps. Our approach, RECALL, outperforms state-of-the-art methods.

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 18 code samples harvested from 1 repository linked to this paper: 13 ran (of which 1 constructed an object rather than computing a result; 11 with no instrument failure: 2 honoured, 0 violated, 9 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified. Where Syntology's instrument failed: 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 18 samples from 1 repository, 13 ran (11 with no instrument failure; 2 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 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.

lttm/recall officialmentioned in papermentioned on GitHubtfMITSyntology: 18 samples, 13 ran (2 instrument-failed) · 5 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

18 samples harvested: 13 ran (of which 1 constructed an object rather than computing a result; 11 with no instrument failure: 2 honoured, 0 violated, 9 with no contract checked; 2 where Syntology's instrument failed) · 5 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.

2ran · honoured contract
2ran; the contract check could not run
9ran
5unverified

Licence: 0 of the 18 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 lttm/recall. “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.

lttm/recall official repository 18 samples, 13 ran (2 instrument-failed) · 5 unverified
Model in 227 papers model_resnet.py ran MIT (permissive) · a3f7331bbdb98e59 · report fixture: returned Model · level recorded 2026-09-22
add in 19 papers model_resnet.py ran · honoured contract MIT (permissive) · a96ff10f26036567 · report fixture: signature x_l:list/1/EagerTensor, name:str/0/str · returned EagerTensor · level recorded 2026-09-22
get_classes_accuracy metrics.py ran MIT (permissive) · 92fa3b85dd6d9930 · report fixture: signature confusion_matrix:ndarray/2/float, classes:list/1/int · returned list · level recorded 2026-09-25
get_classes_iou metrics.py ran MIT (permissive) · 8e11a0aa76c799b6 · report fixture: signature confusion_matrix:ndarray/2/float, classes:list/1/int · returned list · level recorded 2026-09-26
get_mean_pixel_accuracy metrics.py ran MIT (permissive) · 48bc91b33344e330 · report fixture: signature confusion_matrix:Tensor/2/float, classes:list/1/int · returned Tensor · level recorded 2026-09-25
im2int gan/generate_gan.py ran MIT (permissive) · 7045941346cccb6f · report fixture: signature image:EagerTensor/3/float · returned EagerTensor · level recorded 2026-09-25
interleave_datasets data_loader.py ran MIT (permissive) · e74234eaa6937655 · report fixture: signature dataset1:_BatchDataset/0/?, dataset2:_BatchDataset/0/?, r1:int/0/int, r2:int/0/int, batch_size:int/0/int, buffer_size:int/0/int, repeat:bool/0/bool, shuffle:bool/0/bool · returned _BatchDataset · level recorded 2026-09-26
max_pool2d model_resnet.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive) · ded213268c033a96 · report fixture: signature x:EagerTensor/4/float, kernel_size:int/0/int, stride:int/0/int, name:str/0/str · returned EagerTensor · level recorded 2026-09-22
preprocess_validation_op preprocessing.py ran MIT (permissive) · 94725ecbda96c654 · report fixture: signature image:EagerTensor/3/int, label:EagerTensor/3/int, subtract_mean:bool/0/bool, mean:EagerTensor/3/float · returned tuple · level recorded 2026-09-25
relu in 58 papers
census: 8 implementations from 11 papers, 4 distinct outputs across 2 buckets, one shared input per bucket
model_resnet.py ran · honoured contract fingerprinted MIT (permissive) · 37e49142da9ee0cd · report fixture: signature x:EagerTensor/2/float, name:str/0/str · returned EagerTensor · level recorded 2026-09-22
resize_image_op preprocessing.py ran MIT (permissive) · 423a14145bc09771 · report fixture: signature image:EagerTensor/3/int, size:int/0/int, subtract_mean:bool/0/bool, mean:EagerTensor/3/float · returned EagerTensor · level recorded 2026-09-25
serialize_sample data_loader.py ran MIT (permissive) · 2e9c72ac0591430c · report fixture: signature image:bytes/0/?, label:bytes/0/? · returned bytes · level recorded 2026-09-25
upsampling model_resnet.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive) · 5d9c5fe9e4c597a9 · report fixture: signature inputs:EagerTensor/4/float, output_shape:tuple/1/int · returned EagerTensor · level recorded 2026-09-22
ASPP in 23 papers model_resnet.py unverified MIT (permissive) · 7130868dd7f4080f · report
batch_norm in 46 papers model_resnet.py unverified MIT (permissive) · 54d981e50a6f3e0f · report
conv2d in 119 papers model_resnet.py unverified MIT (permissive) · 22aa81d960081ea7 · report
dilated_conv2d model_resnet.py unverified MIT (permissive) · 391774518dbd2cc0 · report
preprocess_training_op preprocessing.py unverified MIT (permissive) · 3cdee8d3ea4218a4 · 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 RECALL (graph method: RECALL). 9 bricks; individually on a fixture: 5 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified. The assembly has not been run end-to-end.

  1. Model entry · level 1 · ran · a3f7331bbdb98e59
  2. ASPP model · level 0 · unverified · 7130868dd7f4080f
  3. add model · level 1 · ran · honoured contract · a96ff10f26036567
  4. batch_norm model · level 0 · unverified · 54d981e50a6f3e0f
  5. conv2d model · level 0 · unverified · 22aa81d960081ea7
  6. dilated_conv2d model · level 0 · unverified · 391774518dbd2cc0
  7. max_pool2d model · level 1 · ran; the contract check could not run (RAISES) · ded213268c033a96
  8. relu model · level 1 · ran · honoured contract · 37e49142da9ee0cd
  9. upsampling helper · level 1 · ran; the contract check could not run (RAISES) · 5d9c5fe9e4c597a9

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="2108.03673") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Continual LearningSemantic Segmentation

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Inpainting

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