Pith. sign in

REVIEW 4 cited by

Dark Experience for General Continual Learning: a Strong, Simple Baseline

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2004.07211 v2 pith:TDFOEXVN submitted 2020-04-15 stat.ML cs.LG

Pietro Buzzega , Matteo Boschini , Angelo Porrello , Davide Abati , Simone Calderara This is my paper
classification stat.MLcs.LG
keywords baselinecontinuallearningsimpleapproachesdarkevaluationexperience
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Continual Learning has inspired a plethora of approaches and evaluation settings; however, the majority of them overlooks the properties of a practical scenario, where the data stream cannot be shaped as a sequence of tasks and offline training is not viable. We work towards General Continual Learning (GCL), where task boundaries blur and the domain and class distributions shift either gradually or suddenly. We address it through mixing rehearsal with knowledge distillation and regularization; our simple baseline, Dark Experience Replay, matches the network's logits sampled throughout the optimization trajectory, thus promoting consistency with its past. By conducting an extensive analysis on both standard benchmarks and a novel GCL evaluation setting (MNIST-360), we show that such a seemingly simple baseline outperforms consolidated approaches and leverages limited resources. We further explore the generalization capabilities of our objective, showing its regularization being beneficial beyond mere performance.

Discussion (0). Sign in to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. OpenAlex reports about 90 citations worldwide. Full citation record

  1. Class Incremental Continual Learning with Self-Organizing Maps and Variational Autoencoders Using Synthetic Replay

    cs.LG 2025-08 conditional novelty 6.0 of 10

    A SOM-VAE generative replay method stores per-unit Gaussian statistics instead of raw data and reports competitive class-incremental accuracy on standard benchmarks.

  2. Gated Adaptation for Continual Learning in Human Activity Recognition

    cs.LG 2026-03 conditional novelty 5.0 of 10

    Channel-wise gating of frozen pretrained features reduces catastrophic forgetting in subject-incremental HAR, reaching ~78% final accuracy on PAMAP2 versus ~57% for full fine-tuning.

  3. Continual Knowledge Consolidation LORA for Domain Incremental Learning

    cs.LG 2025-10 conditional novelty 5.0 of 10

    CONEC-LoRA reports state-of-the-art accuracy on four domain-incremental benchmarks by combining task-shared and task-specific LoRAs with a stochastic classifier and a learned domain-ID selector.

  4. Lightweight Test-Time Adaptation for EMG-Based Gesture Recognition

    cs.LG 2026-01 conditional novelty 4.0 of 10

    Test-time adaptation—adaptive batch norm, replay-regularized feature alignment, and few-shot meta-learning—improves NinaPro DB6 inter-session EMG gesture accuracy from ~57% baseline to ~69–70% unsupervised and ~80% wi...

Pith tools