The paper offers a comprehensive survey and proposes a new taxonomy for continual learning strategies in VLMs and MLLMs to combat catastrophic forgetting beyond traditional methods.
Learning multiple layers of features from tiny images,
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
verdicts
UNVERDICTED 4representative citing papers
Spikinghash combines 3D-DWT Spiking WaveMixer, Spiking Self-Attention, and a dynamic soft similarity loss to produce energy-efficient hash codes for DVS data retrieval.
DeCon decouples LTSSL into head-class and tail-class branches that interact and converge, delivering SOTA accuracy on mismatched-distribution benchmarks and outperforming prior methods even on matched distributions.
Comparative study applies UCB-V, UCB-Tuned, UCB-Bayes and UCB-BwK to ADNN early-exit selection on ResNet and MobileViT using CIFAR-10/100, reporting sub-linear regret with UCB-Bayes fastest and UCB-V/UCB-Tuned best on accuracy-energy and accuracy-latency Pareto fronts.
citing papers explorer
-
Continual Learning for VLMs: A Survey and Taxonomy Beyond Forgetting
The paper offers a comprehensive survey and proposes a new taxonomy for continual learning strategies in VLMs and MLLMs to combat catastrophic forgetting beyond traditional methods.
-
Temporal-Aware Spiking Transformer Hashing Based on 3D-DWT
Spikinghash combines 3D-DWT Spiking WaveMixer, Spiking Self-Attention, and a dynamic soft similarity loss to produce energy-efficient hash codes for DVS data retrieval.
-
Decouple then Converge: Handling Unknown Unlabeled Distributions in Long-Tailed Semi-Supervised Learning
DeCon decouples LTSSL into head-class and tail-class branches that interact and converge, delivering SOTA accuracy on mismatched-distribution benchmarks and outperforming prior methods even on matched distributions.
-
A Comparative Analysis on the Performance of Upper Confidence Bound Algorithms in Adaptive Deep Neural Networks
Comparative study applies UCB-V, UCB-Tuned, UCB-Bayes and UCB-BwK to ADNN early-exit selection on ResNet and MobileViT using CIFAR-10/100, reporting sub-linear regret with UCB-Bayes fastest and UCB-V/UCB-Tuned best on accuracy-energy and accuracy-latency Pareto fronts.