Related papers: Prompt-Based Exemplar Super-Compression and Regene…

Most provably-efficient learning algorithms introduce optimism about poorly-understood states and actions to encourage exploration. We study an alternative approach for efficient exploration, posterior sampling for reinforcement learning…

Exemplar-free class-incremental learning enables models to learn new classes over time without storing data from old ones. As multimodal graph-structured data becomes increasingly prevalent, existing methods struggle with challenges like…

Recently, images that distort or fabricate facts using generative models have become a social concern. To cope with continuous evolution of generative artificial intelligence (AI) models, model attribution (MA) is necessary beyond just…

The learning objective of vision-language approach of CLIP does not effectively account for the noisy many-to-many correspondences found in web-harvested image captioning datasets, which contributes to its compute and data inefficiency. To…

In this study, we propose an enhanced image restoration model, SUPIR, based on the integration of two low-rank adaptive (LoRA) modules with the Stable Diffusion XL (SDXL) framework. Our method leverages the advantages of LoRA to fine-tune…

This paper studies class incremental learning (CIL) of continual learning (CL). Many approaches have been proposed to deal with catastrophic forgetting (CF) in CIL. Most methods incrementally construct a single classifier for all classes of…

We present Distill CLIP (DCLIP), a fine-tuned variant of the CLIP model that enhances multimodal image-text retrieval while preserving the original model's strong zero-shot classification capabilities. CLIP models are typically constrained…

Class-incremental learning (CIL) in medical image-guided diagnosis requires retaining prior diagnostic knowledge while adapting to newly emerging disease categories, which is critical for scalable clinical deployment. This problem is…

Deep Neural Network (DNN) has achieved great success on datasets of closed class set. However, new classes, like new categories of social media topics, are continuously added to the real world, making it necessary to incrementally learn.…

Recently, prompt tuning methods for pre-trained models have demonstrated promising performance in Class Incremental Learning (CIL). These methods typically involve learning task-specific prompts and predicting the task ID to select the…

Exemplar-free class-incremental learning is very challenging due to the negative effect of catastrophic forgetting. A balance between stability and plasticity of the incremental process is needed in order to obtain good accuracy for past as…

Online class-incremental continual learning is a specific task of continual learning. It aims to continuously learn new classes from data stream and the samples of data stream are seen only once, which suffers from the catastrophic…

The escalating adoption of high-resolution, large-field-of-view imagery amplifies the need for efficient compression methodologies. Conventional techniques frequently fail to preserve critical image details, while data-driven approaches…

Semantic segmentation of microscopic cell images using deep learning is an important technique, however, it requires a large number of images and ground truth labels for training. To address the above problem, we consider an efficient…

Recently, perceptual image compression has achieved significant advancements, delivering high visual quality at low bitrates for natural images. However, for screen content, existing methods often produce noticeable artifacts when…

In the field of class incremental learning (CIL), generative replay has become increasingly prominent as a method to mitigate the catastrophic forgetting, alongside the continuous improvements in generative models. However, its application…

Few-shot class-incremental learning (FSCIL) presents a core challenge in continual learning, requiring models to rapidly adapt to new classes with very limited samples while mitigating catastrophic forgetting. Recent prompt-based methods,…

Aiming to incrementally learn new classes with only few samples while preserving the knowledge of base (old) classes, few-shot class-incremental learning (FSCIL) faces several challenges, such as overfitting and catastrophic forgetting.…

Real-world data streams naturally include the repetition of previous concepts. From a Continual Learning (CL) perspective, repetition is a property of the environment and, unlike replay, cannot be controlled by the agent. Nowadays, the…

Algorithm selection is commonly used to predict the best solver from a portfolio per per-instance. In many real scenarios, instances arrive in a stream: new instances become available over time, while the number of class labels can also…