Related papers: Rotation Augmented Distillation for Exemplar-Free …
Exemplar-free incremental learning is extremely challenging due to inaccessibility of data from old tasks. In this paper, we attempt to exploit the knowledge encoded in a previously trained classification model to handle the catastrophic…
In robotic manipulation, acquiring samples is extremely expensive because it often requires interacting with the real world. Traditional image-level data augmentation has shown the potential to improve sample efficiency in various machine…
Deep convolutional neural networks have made significant breakthroughs in medical image classification, under the assumption that training samples from all classes are simultaneously available. However, in real-world medical scenarios,…
Different from fine-tuning models pre-trained on a large-scale dataset of preset classes, class-incremental learning (CIL) aims to recognize novel classes over time without forgetting pre-trained classes. However, a given model will be…
Class-incremental learning is a challenging problem, where the goal is to train a model that can classify data from an increasing number of classes over time. With the advancement of vision-language pre-trained models such as CLIP, they…
Continual learning (CL) aims to train models that can learn a sequence of tasks without forgetting previously acquired knowledge. A core challenge in CL is balancing stability -- preserving performance on old tasks -- and plasticity --…
We propose Algorithm Distillation (AD), a method for distilling reinforcement learning (RL) algorithms into neural networks by modeling their training histories with a causal sequence model. Algorithm Distillation treats learning to…
Not forgetting old class knowledge is a key challenge for class-incremental learning (CIL) when the model continuously adapts to new classes. A common technique to address this is knowledge distillation (KD), which penalizes prediction…
The field of Continual Learning (CL) has inspired numerous researchers over the years, leading to increasingly advanced countermeasures to the issue of catastrophic forgetting. Most studies have focused on the single-class scenario, where…
In recent years, we have witnessed the great advancement of Deep neural networks (DNNs) in image restoration. However, a critical limitation is that they cannot generalize well to real-world degradations with different degrees or types. In…
Deep learning architectures have shown remarkable results in scene understanding problems, however they exhibit a critical drop of performances when they are required to learn incrementally new tasks without forgetting old ones. This…
Most fine-grained fashion image retrieval (FIR) methods assume a static setting, requiring full retraining when new attributes appear, which is costly and impractical for dynamic scenarios. Although pretrained models support zero-shot…
Incremental learning remains a critical challenge in machine learning, as models often struggle with catastrophic forgetting -the tendency to lose previously acquired knowledge when learning new information. These challenges are even more…
Exemplar-based class-incremental learning is to recognize new classes while not forgetting old ones, whose samples can only be saved in limited memory. The ratio fluctuation of new samples to old exemplars, which is caused by the variation…
Reinforcement learning (RL) post-training has recently driven major gains in long chain-of-thought reasoning large language models (LLMs), but the high inference cost of such models motivates distillation into smaller students. Most…
We investigate the problem of incremental learning for object counting, where a method must learn to count a variety of object classes from a sequence of datasets. A na\"ive approach to incremental object counting would suffer from…
For future learning systems, incremental learning is desirable because it allows for: efficient resource usage by eliminating the need to retrain from scratch at the arrival of new data; reduced memory usage by preventing or limiting the…
We consider class incremental learning (CIL) problem, in which a learning agent continuously learns new classes from incrementally arriving training data batches and aims to predict well on all the classes learned so far. The main challenge…
As deep vision models grow increasingly complex to achieve higher performance, deployment efficiency has become a critical concern. Knowledge distillation (KD) mitigates this issue by transferring knowledge from large teacher models to…
The ability to learn from incrementally arriving data is essential for any life-long learning system. However, standard deep neural networks forget the knowledge about the old tasks, a phenomenon called catastrophic forgetting, when trained…