AI Paper Atlas

Research map / Continual learning / Online and replay-based

Batch Model Consolidation: A Multi-Task Model Consolidation Framework

Iordanis Fostiropoulos, Jiaye Zhu, Laurent Itti

CVPR 2023 · Continual learning › Online and replay-based · approach: Unified and unsupervised continual frameworks · 3 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use BMC instead of DMCContinual learning on Split-CIFAR-100 (10 tasks) · Split-CIFAR-100 (10 tasks)mean accuracy: 36.2 -> 66.5Improved
Use BMC instead of GDumbContinual learning on Split-CIFAR-100 (20 tasks) · Split-CIFAR-100 (20 tasks)mean accuracy: 22.1 -> 67.4Improved
Use BMC instead of DER++Continual learning on Split-Tiny-ImageNet (10 tasks) · Split-Tiny-ImageNet (10 tasks)mean accuracy: 39.0 -> 49.4Improved
Use BMC instead of ERContinual learning on Stream · Stream (71 tasks)mean accuracy: 41.4 -> 70.4Improved
Train tasks in parallel across experts and consolidate them in batchesBMC on Stream · Stream (71 tasks)relative training time: 100% -> 78%Improved
Increase the number of experts consolidated per step (ablation)BMC · Permuted-MNIST (128 tasks)mean accuracyImproved
Replace intermediate-feature distillation with logit KD (ablation)BMC consolidation loss · Permuted-MNIST (128 tasks)mean accuracyHurt
Replace intermediate-feature distillation with penultimate-representation distillation (ablation)BMC consolidation or stability loss · Permuted-MNIST (128 tasks)mean accuracyNo clear effect
Replace intermediate-feature distillation with EWC (ablation)BMC stability loss · Permuted-MNIST (128 tasks)mean accuracyHurt
Use random sampling instead of gradient-based buffer sampling (ablation)BMC buffer construction · Permuted-MNIST (128 tasks)mean accuracyImproved
Increase the stability coefficient (ablation)BMC · Permuted-MNIST (128 tasks)mean accuracy: 4.12e-2Improved
Increase the consolidation coefficient (ablation)BMC · Permuted-MNIST (128 tasks)mean accuracy: 9.39e-2Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy