MétaCan
Menu
Back to cohort
Record W3214945533 · doi:10.1016/j.artint.2021.103635

CVPR 2020 continual learning in computer vision competition: Approaches, results, current challenges and future directions

2022· article· en· W3214945533 on OpenAlexaff
Vincenzo Lomonaco, Lorenzo Pellegrini, Pau Rodríguez, M. Caccia, Qi She, Yu Chen, Quentin Jodelet, Ruiping Wang, Zheda Mai, David Vázquez, German I. Parisi, Nikhil Churamani, Marc Pickett, Issam Laradji, Davide Maltoni

Bibliographic record

VenueCINECA IRIS Institutial research information system (University of Pisa) · 2022
Typearticle
Languageen
FieldComputer Science
TopicDomain Adaptation and Few-Shot Learning
Canadian institutionsUniversity of TorontoMila - Quebec Artificial Intelligence Institute
Fundersnot available
KeywordsBenchmarkingComputer scienceArtificial intelligenceForgettingBenchmark (surveying)Task (project management)Field (mathematics)Machine learningSet (abstract data type)Deep learningCompetition (biology)

Abstract

fetched live from OpenAlex

In the last few years, we have witnessed a renewed and fast-growing interest in continual learning with deep neural networks with the shared objective of making current AI systems more adaptive, efficient and autonomous. However, despite the significant and undoubted progress of the field in addressing the issue of catastrophic forgetting, benchmarking different continual learning approaches is a difficult task by itself. In fact, given the proliferation of different settings, training and evaluation protocols, metrics and nomenclature, it is often tricky to properly characterize a continual learning algorithm, relate it to other solutions and gauge its real-world applicability. The first Continual Learning in Computer Vision challenge held at CVPR in 2020 has been one of the first opportunities to evaluate different continual learning algorithms on a common hardware with a large set of shared evaluation metrics and 3 different settings based on the realistic CORe50 video benchmark. In this paper, we report the main results of the competition, which counted more than 79 teams registered and 11 finalists. We also summarize the winning approaches, current challenges and future research directions.

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 machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.029
metaresearch head score (Gemma)0.026
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Not applicable · Consensus signal: Not applicable
GenreCandidate signal: Review · Consensus signal: Review
Teacher disagreement score0.029
Threshold uncertainty score0.152

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0290.026
Meta-epidemiology (narrow)0.0050.001
Meta-epidemiology (broad)0.0040.001
Bibliometrics0.0050.003
Science and technology studies0.0020.002
Scholarly communication0.0070.007
Open science0.0070.006
Research integrity0.0070.006
Insufficient payload (model declined to judge)0.0110.009

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 head0.077
GPT teacher head0.279
Teacher spread0.203 · 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 source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designNot applicable
Domainnot available
GenreReview

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

Citations41
Published2022
Admission routes1
Has abstractyes

Explore more

Same venueCINECA IRIS Institutial research information system (University of Pisa)Same topicDomain Adaptation and Few-Shot LearningFrench-language works237,207