Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,657 papers · 148 categories

Trend · papers per month

1234 · Aug 202019922001200920172026
44 results for Class-incremental

Paper tackles class-incremental time series classification with dual-stream feature extraction.

problem Class-incremental continual learning for multivariate time series data.
method Dual-stream feature extraction pipeline combining deep temporal embedding features and statistical features.
result Competitive average accuracy across multiple datasets with low forgetting rates.

A new generative classification strategy outperforms existing methods in class-incremental learning.

problem Incrementally training deep neural networks to recognize new classes is challenging.
method Proposes learning the joint distribution p(x,y) and performing classification using Bayes' rule, implemented with variational autoencoders and importance sampling.
result Performs very well on continual learning benchmarks, outperforming existing baselines.

Paper tackles few-shot class-incremental learning with a neural gas network.

problem Incrementally learn new classes from very few labelled samples without forgetting old classes.
method Proposes TOPIC framework using a neural gas network to preserve class topology and adapt to new samples.
result Significantly outperforms other methods on CIFAR100, miniImageNet, and CUB200 datasets.

PEC improves class-incremental learning by measuring prediction error.

problem Challenges in class-incremental learning, particularly forgetting and class imbalance.
method Prediction Error-based Classification (PEC) measures prediction error of a model trained on data from a class.
result PEC outperforms other methods in class-incremental learning across multiple benchmarks.

Paper proposes a new method to select memory data for online class-incremental learning.

problem Selecting which buffered images to replay for online class-incremental learning.
method Adversarial Shapley value scoring method to preserve latent decision boundaries.
result Proposed ASER method provides competitive or improved performance compared to state-of-the-art methods.

Paper tackles class-incremental learning by combining self-supervised learning to mitigate prior information loss.

problem Catastrophic forgetting and prior information loss in class-incremental learning.
method Combining self-supervised learning with class-incremental learning to mitigate prior information loss.
result Proposed method outperforms state-of-the-art methods.

In class-incremental learning, a model learns continuously from a sequential data stream in which new classes occur. Existing methods often rely on static architectures that are manually crafted. These methods can be prone to capacity saturation because a neural network's ability to generalize to new concepts is limite…

2019-09-14abs ↗pdf ↗

FedGTEA learns new tasks in federated learning with task embeddings and alignment.

problem Federated class-incremental learning with task-specific knowledge and model uncertainty.
method Cardinality-Agnostic Task Encoder (CATE) for Gaussian task embeddings, 2-Wasserstein distance for inter-task alignment.
result FedGTEA achieves superior classification performance and mitigates forgetting.

Gen1S learns novel classes with 1-shot data using residual space and generative models.

problem Learning new classes with limited data in a growing dataset.
method Mapping embeddings to a residual space, using generative models to learn multi-modal distribution, and applying it as a structural prior.
result Consistent improvement over state-of-the-art methods in recognizing novel classes.

CILF learns adaptive embeddings for class-incremental learning with novel class detection and model update.

problem Handling unknown classes and model update in streaming data with new classes.
method CILF uses decoupled prototype based loss for intra-class and inter-class structure improvement, and a learnable curriculum clustering operator for adaptive embedding.
result CILF effectively detects multiple novel classes and mitigates embedding confusion, while updating the model without catastrophic forgetting.

Improves few-shot learning for hierarchical data using hyperbolic space.

problem Few-shot class-incremental learning for hierarchical data.
method Contrastive learning in hyperbolic space, Poincaré ball model, hyperbolic contrastive loss, maximum entropy distribution.
result Effective improvement of coarse and fine class accuracies in few-shot conditions.

A major open problem on the road to artificial intelligence is the development of incrementally learning systems that learn about more and more concepts over time from a stream of data. In this work, we introduce a new training strategy, iCaRL, that allows learning in such a class-incremental way: only the training dat…

2016-11-23abs ↗pdf ↗

Paper tackles graph class-incremental learning with task profiling and prompting.

problem Challenges in separating classes from different tasks in graph CIL.
method Laplacian smoothing-based task profiling and graph prompting approach.
result 100% task ID prediction accuracy and significant performance improvement.

Efficiently preserves old class knowledge in memory-limited settings.

problem Catastrophic forgetting in class-incremental learning.
method Memory-efficient exemplar preserving scheme and domain-compatible feature extractors.
result Low-fidelity exemplar samples can replace high-fidelity ones with less memory cost.

This paper tackles few-shot classification by improving GAN-based data augmentation.

problem Improving few-shot classification performance using GANs with limited data.
method Fine-tuning GANs for few-shot classification, addressing training and evaluation challenges.
result Semi-supervised fine-tuning is a more effective approach for few-shot classification with limited data.

SpaceNet improves continual learning by intelligently compressing neural connections.

problem Catastrophic forgetting in sequential learning tasks.
method SpaceNet trains sparse deep neural networks adaptively, compressing task-specific connections.
result SpaceNet outperforms existing methods in class incremental learning scenarios.

A new method improves continual learning by replaying pseudo data and using orthogonal weight modification.

problem Catastrophic forgetting in class incremental learning.
method Generative replay with orthogonal weight modification.
result Our method achieves substantial improvement over conventional generative replay and OWM.

Develops a framework for continual learning in anomaly detection.

problem Deterioration of monitoring performance due to new defect categories.
method Pseudo replay-based class incremental learning with oversampling.
result Enhanced monitoring performance and flexibility in model architecture.

It was recently shown that architectural, regularization and rehearsal strategies can be used to train deep models sequentially on a number of disjoint tasks without forgetting previously acquired knowledge. However, these strategies are still unsatisfactory if the tasks are not disjoint but constitute a single increme…

2018-06-22abs ↗pdf ↗

In most machine learning algorithms, training data is assumed to be independent and identically distributed (iid). When it is not the case, the algorithm's performances are challenged, leading to the famous phenomenon of catastrophic forgetting. Algorithms dealing with it are gathered in the Continual Learning research…

2019-12-06abs ↗pdf ↗

Lifelong learning with deep neural networks is well-known to suffer from catastrophic forgetting: the performance on previous tasks drastically degrades when learning a new task. To alleviate this effect, we propose to leverage a large stream of unlabeled data easily obtainable in the wild. In particular, we design a n…

2019-03-29abs ↗pdf ↗

Standard artificial neural networks suffer from the well-known issue of catastrophic forgetting, making continual or lifelong learning difficult for machine learning. In recent years, numerous methods have been proposed for continual learning, but due to differences in evaluation protocols it is difficult to directly c…

2019-04-15abs ↗pdf ↗

This paper tackles federated incremental learning with dynamic memory allocation for improved model performance in non-IID data.

problem Catastrophic forgetting in federated healthcare systems with non-IID data.
method Dynamic memory allocation strategy based on data replay mechanism.
result Significant performance improvements in medical image datasets compared to baseline models.

CL-BRUNO model tackles continual learning with scalable Bayesian updates.

problem Deploying CL methods to real-world decision-making problems due to computational cost and lack of uncertainty quantification.
method Probabilistic, Neural Process-based CL model using deep-generative models for scalable and tractable Bayesian update and prediction.
result CL-BRUNO outperforms existing methods on natural image and biomedical data sets.

As we enter into the big data age and an avalanche of images have become readily available, recognition systems face the need to move from close, lab settings where the number of classes and training data are fixed, to dynamic scenarios where the number of categories to be recognized grows continuously over time, as we…

2016-04-08abs ↗pdf ↗

Flashback Learning balances model stability and plasticity in continual learning.

problem Balancing model stability and plasticity in continual learning.
method Flashback Learning (FL) uses a bidirectional regularization approach to balance stability and plasticity.
result FL improves model accuracy by up to 4.91% in Class-Incremental and 3.51% in Task-Incremental settings.

TKIL improves class-balanced performance in incremental learning.

problem Catastrophic forgetting in sequential learning tasks.
method Introduces Tangent Kernel for Incremental Learning (TKIL) based on Neural Tangent Kernel (NTK).
result TKIL achieves better overall accuracy and variance across classes.

Proposes efficient model for continual learning that grows model over task-specific parameters.

problem Limited transfer learning ability and forgetting of earlier knowledge in existing methods.
method Filter and channel expansion method that grows model over previous task parameters.
result Better knowledge transfer and improved performance in task incremental learning.