Related papers: Forgetting to Remember: A Scalable Incremental Lea…
The recent proliferation of large-scale text-to-image models has led to growing concerns that such models may be misused to generate harmful, misleading, and inappropriate content. Motivated by this issue, we derive a technique inspired by…
Multi-level deep-features have been driving state-of-the-art methods for aesthetics and image quality assessment (IQA). However, most IQA benchmarks are comprised of artificially distorted images, for which features derived from ImageNet…
Incremental Task learning (ITL) is a category of continual learning that seeks to train a single network for multiple tasks (one after another), where training data for each task is only available during the training of that task. Neural…
Recent advancements in image quality assessment (IQA), driven by sophisticated deep neural network designs, have significantly improved the ability to approach human perceptions. However, most existing methods are obsessed with fitting the…
Deep learning models suffer from catastrophic forgetting of the classes in the older phases as they get trained on the classes introduced in the new phase in the class-incremental learning setting. In this work, we show that the effect of…
Recent advancements in multimodal large language models have enhanced document understanding by integrating textual and visual information. However, existing models exhibit incompleteness within their paradigm in real-world scenarios,…
One notable weakness of current machine learning algorithms is the poor ability of models to solve new problems without forgetting previously acquired knowledge. The Continual Learning paradigm has emerged as a protocol to systematically…
Multimodal large language models (MLLMs) deployed on devices must adapt to continuously changing visual scenarios such as variations in background and perspective, to effectively perform complex visual tasks. To investigate catastrophic…
Full-reference (FR) image quality assessment (IQA) evaluates the visual quality of a distorted image by measuring its perceptual difference with pristine-quality reference, and has been widely used in low-level vision tasks. Pairwise…
While large language models (LLMs) exhibit remarkable capabilities, they increasingly face demands to unlearn memorized privacy-sensitive, copyrighted, or harmful content. Existing unlearning methods primarily focus on \emph{single-shot}…
Deep pretrained language models have achieved great success in the way of pretraining first and then fine-tuning. But such a sequential transfer learning paradigm often confronts the catastrophic forgetting problem and leads to sub-optimal…
As neural networks are increasingly deployed in dynamic environments, they face the challenge of catastrophic forgetting, the tendency to overwrite previously learned knowledge when adapting to new tasks, resulting in severe performance…
In class-incremental learning, an agent with limited resources needs to learn a sequence of classification tasks, forming an ever growing classification problem, with the constraint of not being able to access data from previous tasks. The…
Visual Question Answering (VQA) requires models to reason over multimodal information, combining visual and textual data. With the development of continual learning, significant progress has been made in retaining knowledge and adapting to…
We present IQA-Spider, the first image quality assessment (IQA) framework that unifies reasoning, grounding, and referring into a single LMM-based framework for multi-granularity quality understanding. Existing LMM-based IQA methods…
Continual learning aims to provide intelligent agents capable of learning multiple tasks sequentially with neural networks. One of its main challenging, catastrophic forgetting, is caused by the neural networks non-optimal ability to learn…
Language model continual learning (CL) has recently attracted significant interest for its ability to adapt large language models (LLMs) to dynamic real-world scenarios without retraining. A major challenge in this domain is catastrophic…
Deep neural networks often severely forget previously learned knowledge when learning new knowledge. Various continual learning (CL) methods have been proposed to handle such a catastrophic forgetting issue from different perspectives and…
Measuring the perceptual quality of images automatically is an essential task in the area of computer vision, as degradations on image quality can exist in many processes from image acquisition, transmission to enhancing. Many Image Quality…
Current no-reference image quality assessment (NR-IQA) models for enhanced images often struggle to generalize, as they tend to overfit to the distinct patterns of specific enhancement algorithms rather than evaluating genuine perceptual…