AI Paper Atlas

Research map / Continual learning / Online and replay-based

Transfer without Forgetting

Matteo Boschini, Lorenzo Bonicelli, Angelo Porrello, Giovanni Bellitto, Matteo Pennisi, Simone Palazzo, Concetto Spampinato, Simone Calderara

ECCV 2022 · Continual learning › Online and replay-based · approach: Theoretical analysis of forgetting · 49 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
add L_FP feature-preservation loss on top of L_CL (ablation)TwF · Split CIFAR-100 (pretrain Tiny ImageNet), Class-IL, buffer 500final average accuracy (%): 44.01 -> 55.50Improved
add L_FP on top of L_CL (ablation)TwF · Split CIFAR-10 (pretrain CIFAR-100), Class-IL, buffer 500final average accuracy (%): 75.79 -> 83.29Improved
add L_FP on top of L_CL (ablation)TwF · Split CUB-200 (pretrain ImageNet), Class-IL, buffer 400final average accuracy (%): 56.53 -> 59.06Improved
add L_AUX on top of L_CL and L_FP (ablation)TwF · Split CIFAR-100 (pretrain Tiny ImageNet), Class-IL, buffer 500final average accuracy (%): 55.50 -> 56.83Improved
add L_AUX on top of L_CL and L_FP (ablation)TwF · Split CIFAR-10 (pretrain CIFAR-100), Class-IL, buffer 5120final average accuracy (%): 89.53 -> 89.55No clear effect
add L_CL (replay classification loss) to L_FP (ablation)TwF · Split CIFAR-10 (pretrain CIFAR-100), Class-IL, buffer 500final average accuracy (%): 62.63 -> 83.65Improved
add replay buffer to TwF with only L_FP and L_AUX (ablation)TwF · Split CUB-200 (pretrain ImageNet), Class-IL, buffer 1000final average accuracy (%): 38.43 -> 59.67Improved
use TwF feature preservation instead of oEwC with no replay (ablation)TwF vs oEwC · Split CIFAR-100 (pretrain Tiny ImageNet), Class-ILfinal average accuracy (%): 10.95 -> 49.74Improved
replace DER++ and iCaRL baselines by TwF under dissimilar pretraining (SVHN)TwF vs DER++ · Split CIFAR-100 (pretrain SVHN), Class-IL, buffer 500final average accuracy (%): 36.46 -> 43.56Improved
add EwC regularizer on pretraining weights to DER++DER++ · Split CIFAR-100 (pretrain Tiny ImageNet)final average accuracy (%)Improved
dedicate part of the buffer to pretraining images in DER++DER++ · Split CIFAR-100 (pretrain Tiny ImageNet), buffer 2000final average accuracy (%)Improved
use CO2L instead of ER on Split CUB-200CO2L · Split CUB-200 (pretrain ImageNet), Class-IL, buffer 400final average accuracy (%): 45.82 -> 8.96Hurt

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