REVIEW 8 cited by
Representational Continuity for Unsupervised Continual 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
Continual learning (CL) aims to learn a sequence of tasks without forgetting the previously acquired knowledge. However, recent CL advances are restricted to supervised continual learning (SCL) scenarios. Consequently, they are not scalable to real-world applications where the data distribution is often biased and unannotated. In this work, we focus on unsupervised continual learning (UCL), where we learn the feature representations on an unlabelled sequence of tasks and show that reliance on annotated data is not necessary for continual learning. We conduct a systematic study analyzing the learned feature representations and show that unsupervised visual representations are surprisingly more robust to catastrophic forgetting, consistently achieve better performance, and generalize better to out-of-distribution tasks than SCL. Furthermore, we find that UCL achieves a smoother loss landscape through qualitative analysis of the learned representations and learns meaningful feature representations. Additionally, we propose Lifelong Unsupervised Mixup (LUMP), a simple yet effective technique that interpolates between the current task and previous tasks' instances to alleviate catastrophic forgetting for unsupervised representations.
Forward citations
Cited by 8 Pith papers
-
FedLAB: Traceable Semantic Codebooks for Federated Multimodal Graph Foundation Learning
FedLAB organizes multimodal graph knowledge into typed hierarchical codebooks for modality evidence, node semantics, and topology context via federated semantic barycenter pre-training, improving performance by up to ...
-
Unsupervised Continual Clustering via Forward-Backward Knowledge Distillation
FBCC introduces unsupervised continual clustering via a teacher-student forward-backward distillation process that outperforms baselines on clustering accuracy while reducing catastrophic forgetting.
-
MoRe: Modular Representations for Principled Continual Representation Learning on Sequential Data
MoRe identifies modular structure in representations themselves to enable principled reuse, alignment, and expansion of modules during continual adaptation on sequential data.
-
Class Incremental Continual Learning with Self-Organizing Maps and Variational Autoencoders Using Synthetic Replay
A SOM-VAE generative replay method stores per-unit Gaussian statistics instead of raw data and reports competitive class-incremental accuracy on standard benchmarks.
-
MoRe: Modular Representations for Principled Continual Representation Learning on Sequential Data
MoRe identifies modular representations in sequential data for continual learning with identifiability guarantees, enabling principled adaptation without disrupting old modules.
-
MoRe: Modular Representations for Principled Continual Representation Learning on Sequential Data
MoRe decomposes representations into identifiable hierarchical modules to enable principled continual adaptation on sequential data.
-
Unsupervised Video Continual Learning via Non-Parametric Deep Embedded Clustering
A non-parametric mean-shift clustering method over pretrained video transformer features enables unsupervised continual learning on video datasets without labels or task boundaries.
-
Seeing Clearly, Forgetting Deeply: Revisiting Fine-Tuned Video Generators for Driving Simulation
Fine-tuning video generators on driving data can improve visual fidelity while degrading how accurately the model predicts the movement of cars and pedestrians.
Discussion (0). Sign in to comment.