Generative Feature Replay For Class-Incremental Learning

Liu, Xialei; Wu, Chenshen; Menta, Mikel; Herranz, Luis; Raducanu, Bogdan; Bagdanov, Andrew D.; Jui, Shangling; Weijer, Joost van de

doi:10.1109/cvprw50498.2020.00121

Cited by 106 publications

(100 citation statements)

References 25 publications

Supporting

Mentioning

100

Contrasting

Order By: Relevance

“…As storage is limited and Generative Adversarial Networks (GANs) develope, generative replay [46] is proposed as a memory of previous data and its feasibility has been validate on several works [47]- [51]. Although quality of the generation model is a bottleneck, many works [47], [50], [52]- [55] have proved that an elaborately designed generation model practically outperforms mainstream lifelong methods such as EWC, LwF, MAS [56], PathNet [57], and iCaRL [44] et al…”

Section: Related Workmentioning

confidence: 99%

Lifelong Vehicle Trajectory Prediction Framework Based on Generative Replay

Bao¹,

Chen²,

Wang³

et al. 2021

Preprint

View full text Add to dashboard Cite

Accurate trajectory prediction of vehicles is essential for reliable autonomous driving. To maintain consistent performance as a vehicle driving around different cities, it is crucial to adapt to changing traffic circumstances and achieve lifelong trajectory prediction model. To realize it, catastrophic forgetting is a main problem to be addressed. In this paper, a divergence measurement method based on conditional Kullback-Leibler divergence is proposed first to evaluate spatiotemporal dependency difference among varied driving circumstances. Then based on generative replay, a novel lifelong vehicle trajectory prediction framework is developed. The framework consists of a conditional generation model and a vehicle trajectory prediction model. The conditional generation model is a generative adversarial network conditioned on position configuration of vehicles. After learning and merging trajectory distribution of vehicles across different cities, the generation model replays trajectories with prior samplings as inputs, which alleviates catastrophic forgetting. The vehicle trajectory prediction model is trained by the replayed trajectories and achieves consistent prediction performance on visited cities. A lifelong experiment setup is established on four open datasets including five tasks. Spatiotemporal dependency divergence is calculated for different tasks. Even though these divergence, the proposed framework exhibits lifelong learning ability and achieves consistent performance on all tasks.

show abstract

Section: Related Workmentioning

confidence: 99%

Lifelong Vehicle Trajectory Prediction Framework Based on Generative Replay

Bao¹,

Chen²,

Wang³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…The generator is trained to output instances that follow the same data distribution such that when a new task arrives, the solver trains on the synthetic data outputted by the generator along with the new data in order to alleviate catastrophic forgetting. Despite their flexibility and biological appeal, Generative Replay-based methods have three major disadvantages, namely, training a generative model on a stream of changing synthetic and real data is challenging [28], GR models tend to fall short when dealing with complex datasets [1], and the time required to train the model on a new task increases linearly since the model has to generate and rehearse 𝑡 − 1 tasks. Many variants have been proposed to address these issues.…”

Section: Continual Learningmentioning

confidence: 99%

“…Many variants have been proposed to address these issues. Conditional GANs operate in constant time but have lower accuracy [25], while others depend on non-incremental pre-trained networks [28,47].…”

Section: Continual Learningmentioning

confidence: 99%

Latent-Insensitive autoencoders for Anomaly Detection

Battikh¹,

Lenskiy²

2021

Preprint

View full text Add to dashboard Cite

Reconstruction-based approaches to anomaly detection tend to fall short when applied to complex datasets with target classes that possess high interclass variance [11,33]. Similar to the idea of self-taught learning [34] used in transfer learning, many domains are rich with similar unlabeled datasets that could be leveraged as a proxy for out-of-distribution samples. In this paper we introduce Latent-Insensitive Autoencoder (LIS-AE) where unlabeled data from a similar domain is utilized as negative examples to shape the latent layer (bottleneck) of a regular autoencoder such that it is only capable of reconstructing one task. Since the underlying goal of LIS-AE is to only reconstruct in-distribution samples, this makes it naturally applicable in the domain of class-incremental learning. We treat class-incremental learning as multiple anomaly detection tasks by adding a different latent layer for each class and use other available classes in task as negative examples to shape each latent layer. We test our model in multiple anomaly detection and class-incremental settings presenting quantitative and qualitative analysis showcasing the accuracy and the flexibility of our model for both anomaly detection and class-incremental learning.

show abstract

“…This type of methods prevent forgetting by including data from previous tasks, stored either in an episodic memory or via a generative model. There are two main strategies: exemplar rehearsal [4,9,16,27,32] and pseudo-rehearsal [29,31]. The former stores a small amount of training samples (also called exemplars) from previous tasks.…”

Section: Incremental Learningmentioning

confidence: 99%

HCV: Hierarchy-Consistency Verification for Incremental Implicitly-Refined Classification

Wang¹,

Liu²,

Herranz³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Human beings learn and accumulate hierarchical knowledge over their lifetime. This knowledge is associated with previous concepts for consolidation and hierarchical construction. However, current incremental learning methods lack the ability to build a concept hierarchy by associating new concepts to old ones. A more realistic setting tackling this problem is referred to as Incremental Implicitly-Refined Classification (IIRC), which simulates the recognition process from coarse-grained categories to fine-grained categories. To overcome forgetting in this benchmark, we propose Hierarchy-Consistency Verification (HCV) as an enhancement to existing continual learning methods. Our method incrementally discovers the hierarchical relations between classes. We then show how this knowledge can be exploited during both training and inference. Experiments on three setups of varying difficulty demonstrate that our HCV module improves performance of existing continual learning methods under this IIRC setting by a large margin. Code is available in https://github.com/wangkai930418/HCV_IIRC.

show abstract

Generative Feature Replay For Class-Incremental Learning

Cited by 106 publications

References 25 publications

Lifelong Vehicle Trajectory Prediction Framework Based on Generative Replay

Lifelong Vehicle Trajectory Prediction Framework Based on Generative Replay

Latent-Insensitive autoencoders for Anomaly Detection

HCV: Hierarchy-Consistency Verification for Incremental Implicitly-Refined Classification

Contact Info

Product

Resources

About