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
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
Forward citations
Cited by 4 Pith papers
-
Continual Hyperbolic Learning of Instances and Classes
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, ...
-
Continual Knowledge Consolidation LORA for Domain Incremental Learning
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.
-
ECC-SNN: Cost-Effective Edge-Cloud Collaboration for Spiking Neural Networks
A cloud-ANN/edge-SNN collaboration with entropy-based offloading and on-device incremental learning improves image classification accuracy while reducing energy and latency.
-
CIFNet: An Analytic Neural Learning Framework for Efficient and Calibrated Class-Incremental Learning
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.
Discussion (0). Sign in to comment.