MétaCan
Menu
Back to cohort
Record W4224255863 · doi:10.24963/ijcai.2022/177

Continual Semantic Segmentation Leveraging Image-level Labels and Rehearsal

2022· article· en· W4224255863 on OpenAlexafffund
Mathieu Pagé Fortin, Brahim Chaib-draa

Bibliographic record

VenueProceedings of the Thirty-First International Joint Conference on Artificial Intelligence · 2022
Typearticle
Languageen
FieldComputer Science
TopicDomain Adaptation and Few-Shot Learning
Canadian institutionsUniversité Laval
FundersNatural Sciences and Engineering Research Council of CanadaCompute Canada
KeywordsForgettingComputer scienceLeverage (statistics)Pascal (unit)Artificial intelligenceSegmentationMachine learningDeep learningDeep neural networks

Abstract

fetched live from OpenAlex

Despite the remarkable progress of deep learning models for semantic segmentation, the success of these models is strongly limited by the following aspects: 1) large datasets with pixel-level annotations must be available and 2) training must be performed with all classes simultaneously. Indeed, in incremental learning scenarios, where new classes are added to an existing framework, these models are prone to catastrophic forgetting of previous classes. To address these two limitations, we propose a weakly-supervised mechanism for continual semantic segmentation that can leverage cheap image-level annotations and a novel rehearsal strategy that intertwines the learning of past and new classes. Specifically, we explore two rehearsal technique variants: 1) imprinting past objects on new images and 2) transferring past representations in intermediate features maps. We conduct extensive experiments on Pascal-VOC by varying the proportion of fully- and weakly-supervised data in various setups and show that our contributions consistently improve the mIoU on both past and novel classes. Interestingly, we also observe that models trained with less data in incremental steps sometimes outperform the same architectures trained with more data. We discuss the significance of these results and propose some hypotheses regarding the dynamics between forgetting and learning.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Theoretical or conceptual · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.694
Threshold uncertainty score0.742

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0010.000
Scholarly communication0.0000.001
Open science0.0010.001
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.089
GPT teacher head0.289
Teacher spread0.199 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one teacher head, not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designTheoretical or conceptual
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations3
Published2022
Admission routes2
Has abstractyes

Explore more

Same venueProceedings of the Thirty-First International Joint Conference on Artificial IntelligenceSame topicDomain Adaptation and Few-Shot LearningFrench-language works237,207