Related papers: Prototype Memory for Large-scale Face Representati…

Prompt learning is a new learning paradigm which reformulates downstream tasks as similar pretraining tasks on pretrained models by leveraging textual prompts. Recent works have demonstrated that prompt learning is particularly useful for…

This paper introduces a new lifelong learning solution where a single model is trained for a sequence of tasks. The main challenge that vision systems face in this context is catastrophic forgetting: as they tend to adapt to the most…

Multimodal incremental learning needs to digest the information from multiple modalities while concurrently learning new knowledge without forgetting the previously learned information. There are numerous challenges for this task, mainly…

Pose-invariant face recognition has become a challenging problem for modern AI-based face recognition systems. It aims at matching a profile face captured in the wild with a frontal face registered in a database. Existing methods perform…

The creation of altered and manipulated faces has become more common due to the improvement of DeepFake generation methods. Simultaneously, we have seen detection models' development for differentiating between a manipulated and original…

Pretraining reinforcement learning methods with demonstrations has been an important concept in the study of reinforcement learning since a large amount of computing power is spent on online simulations with existing reinforcement learning…

Overfitting is a phenomenon that occurs when a machine learning model is trained for too long and focused too much on the exact fitness of the training samples to the provided training labels and cannot keep track of the predictive rules…

This work analyses the text memorization behavior of large language models (LLMs) when subjected to nucleus sampling. Stochastic decoding methods like nucleus sampling are typically applied to overcome issues such as monotonous and…

In general class-incremental learning, researchers typically use sample sets as a tool to avoid catastrophic forgetting during continuous learning. At the same time, researchers have also noted the differences between class-incremental…

Memory-augmented neural networks consisting of a neural controller and an external memory have shown potentials in long-term sequential learning. Current RAM-like memory models maintain memory accessing every timesteps, thus they do not…

Although person re-identification has achieved an impressive improvement in recent years, the common occlusion case caused by different obstacles is still an unsettled issue in real application scenarios. Existing methods mainly address…

In replay-based methods for continual learning, replaying input samples in episodic memory has shown its effectiveness in alleviating catastrophic forgetting. However, the potential key factor of cross-entropy loss with softmax in causing…

Face recognition under extreme head poses is a challenging task. Ideally, a face recognition system should perform well across different head poses, which is known as pose-invariant face recognition. To achieve pose invariance, current…

We show that the influence of a subset of the training samples can be removed -- or "forgotten" -- from the weights of a network trained on large-scale image classification tasks, and we provide strong computable bounds on the amount of…

This study investigates the mechanisms and factors influencing memorization in fine-tuned large language models (LLMs), with a focus on the medical domain due to its privacy-sensitive nature. We examine how different aspects of the…

Data scarcity remains a fundamental challenge in robot learning. While human demonstrations benefit from abundant motion capture data and vast internet resources, robotic manipulation suffers from limited training examples. To bridge this…

The performance of face recognition system degrades when the variability of the acquired faces increases. Prior work alleviates this issue by either monitoring the face quality in pre-processing or predicting the data uncertainty along with…

In this paper, we introduce a novel framework for memory-efficient and privacy-preserving continual learning in 3D object classification. Unlike conventional memory-based approaches in continual learning that require storing numerous…

Frontier AI systems are making transformative impacts across society, but such benefits are not without costs: models trained on web-scale datasets containing personal and private data raise profound concerns about data privacy and…

In the past few years, large-scale pre-trained vision-language models like CLIP have achieved tremendous success in various fields. Naturally, how to transfer the rich knowledge in such huge pre-trained models to downstream tasks and…