Related papers: Probing Image Compression For Class-Incremental Le…

Recent work has shown that learned image compression strategies can outperform standard hand-crafted compression algorithms that have been developed over decades of intensive research on the rate-distortion trade-off. With growing…

Continual learning (CL) is a major challenge of machine learning (ML) and describes the ability to learn several tasks sequentially without catastrophic forgetting (CF). Recent works indicate that CL is a complex topic, even more so when…

While learning based compression techniques for images have outperformed traditional methods, they have not been widely adopted in machine learning pipelines. This is largely due to lack of standardization and lack of retention of salient…

We introduce an approach for incremental learning that preserves feature descriptors of training images from previously learned classes, instead of the images themselves, unlike most existing work. Keeping the much lower-dimensional feature…

Large Language Models (LLMs) need to adapt to the continuous changes in data, tasks, and user preferences. Due to their massive size and the high costs associated with training, LLMs are not suitable for frequent retraining. However,…

Class-incremental continual learning is an important area of research, as static deep learning methods fail to adapt to changing tasks and data distributions. In previous works, promising results were achieved using replay and compressed…

Anomaly Detection is a relevant problem that arises in numerous real-world applications, especially when dealing with images. However, there has been little research for this task in the Continual Learning setting. In this work, we…

Simultaneous localization and mapping (SLAM) with implicit neural representations has received extensive attention due to the expressive representation power and the innovative paradigm of continual learning. However, deploying such a…

Image compression is a fundamental technology for Internet communication engineering. However, a high compression rate with general methods may degrade images, resulting in unreadable texts. In this paper, we propose an image compression…

In this paper we present an end-to-end meta-learned system for image compression. Traditional machine learning based approaches to image compression train one or more neural network for generalization performance. However, at inference…

Food image classification is challenging for real-world applications since existing methods require static datasets for training and are not capable of learning from sequentially available new food images. Online continual learning aims to…

Continual learning for Semantic Segmentation (CSS) is a rapidly emerging field, in which the capabilities of the segmentation model are incrementally improved by learning new classes or new domains. A central challenge in Continual Learning…

Transferring large amount of high resolution images over limited bandwidth is an important but very challenging task. Compressing images using extremely low bitrates (<0.1 bpp) has been studied but it often results in low quality images of…

Recent deep learning-based methods for lossy image compression achieve competitive rate-distortion performance through extensive end-to-end training and advanced architectures. However, emerging applications increasingly prioritize semantic…

Continual Learning (CL) is a field dedicated to devise algorithms able to achieve lifelong learning. Overcoming the knowledge disruption of previously acquired concepts, a drawback affecting deep learning models and that goes by the name of…

Image compression is one of the most fundamental techniques and commonly used applications in the image and video processing field. Earlier methods built a well-designed pipeline, and efforts were made to improve all modules of the pipeline…

To deploy machine learning models on-device, practitioners use compression algorithms to shrink and speed up models while maintaining their high-quality output. A critical aspect of compression in practice is model comparison, including…

Catastrophic forgetting remains a key challenge in Continual Learning (CL). In replay-based CL with severe memory constraints, performance critically depends on the sample selection strategy for the replay buffer. Most existing approaches…

Image compression aims to reduce the information redundancy in images. Most existing neural image compression methods rely on side information from hyperprior or context models to eliminate spatial redundancy, but rarely address the channel…

Large Language Models (LLMs) have been shown to be able to learn different tasks without explicit finetuning when given many input-output examples / demonstrations through In-Context Learning (ICL). Increasing the number of examples, called…