Pith. sign in

REVIEW 4 cited by

A Model or 603 Exemplars: Towards Memory-Efficient Class-Incremental Learning

Not yet reviewed by Pith; the record is open.

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 2205.13218 v2 pith:OY4NTDJF submitted 2022-05-26 cs.LG cs.CV

classification cs.LGcs.CV
keywords memorymodeldifferentsizeexemplarsfindlayersmemo
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Real-world applications require the classification model to adapt to new classes without forgetting old ones. Correspondingly, Class-Incremental Learning (CIL) aims to train a model with limited memory size to meet this requirement. Typical CIL methods tend to save representative exemplars from former classes to resist forgetting, while recent works find that storing models from history can substantially boost the performance. However, the stored models are not counted into the memory budget, which implicitly results in unfair comparisons. We find that when counting the model size into the total budget and comparing methods with aligned memory size, saving models do not consistently work, especially for the case with limited memory budgets. As a result, we need to holistically evaluate different CIL methods at different memory scales and simultaneously consider accuracy and memory size for measurement. On the other hand, we dive deeply into the construction of the memory buffer for memory efficiency. By analyzing the effect of different layers in the network, we find that shallow and deep layers have different characteristics in CIL. Motivated by this, we propose a simple yet effective baseline, denoted as MEMO for Memory-efficient Expandable MOdel. MEMO extends specialized layers based on the shared generalized representations, efficiently extracting diverse representations with modest cost and maintaining representative exemplars. Extensive experiments on benchmark datasets validate MEMO's competitive performance. Code is available at: https://github.com/wangkiw/ICLR23-MEMO

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. Full citation record

  1. Continual Hyperbolic Learning of Instances and Classes

    cs.CV 2025-06 conditional novelty 6.0 of 10

    HyperCLIC embeds the instance-class hierarchy in hyperbolic space and uses hyperbolic classification and distillation losses to continuously learn both fine-grained instances and coarse-grained classes on EgoObjects, ...

  2. 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.

  3. ECC-SNN: Cost-Effective Edge-Cloud Collaboration for Spiking Neural Networks

    cs.DC 2025-05 conditional novelty 5.0 of 10

    A cloud-ANN/edge-SNN collaboration with entropy-based offloading and on-device incremental learning improves image classification accuracy while reducing energy and latency.

  4. CIFNet: An Analytic Neural Learning Framework for Efficient and Calibrated Class-Incremental Learning

    cs.LG 2025-09 conditional novelty 4.0 of 10

    CIFNet does class-incremental learning with a frozen feature extractor and closed-form classifier updates, reducing training energy by up to 37x while roughly matching baseline accuracy in small-task settings.

Pith tools