相关论文: Vision Transformers that Never Stop Learning

The Transformer architecture has become the state-of-art model for natural language processing tasks and, more recently, also for computer vision tasks, thus defining the Vision Transformer (ViT) architecture. The key feature is the ability…

Memory decay makes it harder for the human brain to recognize visual objects and retain details. Consequently, recorded brain signals become weaker, uncertain, and contain poor visual context over time. This paper presents one of the first…

With Vision Transformers (ViTs) making great advances in a variety of computer vision tasks, recent literature have proposed various variants of vanilla ViTs to achieve better efficiency and efficacy. However, it remains unclear how their…

Vision Transformers (ViTs) achieve state-of-the-art performance on challenging vision tasks, but their deployment on edge devices is severely hindered by the computational complexity and global reduction bottleneck imposed by layer…

Neuroimaging of large populations is valuable to identify factors that promote or resist brain disease, and to assist diagnosis, subtyping, and prognosis. Data-driven models such as convolutional neural networks (CNNs) have increasingly…

Although Vision Transformers (ViTs) have recently demonstrated superior performance in medical imaging problems, they face explainability issues similar to previous architectures such as convolutional neural networks. Recent research…

Attention mechanism has been widely believed as the key to success of vision transformers (ViTs), since it provides a flexible and powerful way to model spatial relationships. However, is the attention mechanism truly an indispensable part…

Developing lifelong learning agents is crucial for artificial general intelligence (AGI). However, deep reinforcement learning (RL) systems often suffer from plasticity loss, where neural networks gradually lose their ability to adapt…

Vision Transformers (ViTs) and MLPs signal further efforts on replacing hand-wired features or inductive biases with general-purpose neural architectures. Existing works empower the models by massive data, such as large-scale pre-training…

Vision transformers have demonstrated remarkable success in classification by leveraging global self-attention to capture long-range dependencies. However, this same mechanism can obscure fine-grained spatial details crucial for tasks such…

Adversarial training (AT) can help improve the robustness of Vision Transformers (ViT) against adversarial attacks by intentionally injecting adversarial examples into the training data. However, this way of adversarial injection inevitably…

Large Vision Language Models (LVLMs) excel in various vision-language tasks. Yet, their robustness to visual variations in position, scale, orientation, and context that objects in natural scenes inevitably exhibit due to changes in…

Transformer-based models have improved visual tracking, but most still cannot run in real time on resource-limited devices, especially for unmanned aerial vehicle (UAV) tracking. To achieve a better balance between performance and…

Despite achieving remarkable performance on various vision-language tasks, Transformer-based Vision-Language Models (VLMs) suffer from redundancy in inputs and parameters, significantly hampering their efficiency in real-world applications.…

Plasticity loss, a critical challenge in neural network training, limits a model's ability to adapt to new tasks or shifts in data distribution. This paper introduces AID (Activation by Interval-wise Dropout), a novel method inspired by…

Biomedical image classification requires capturing of bio-informatics based on specific feature distribution. In most of such applications, there are mainly challenges due to limited availability of samples for diseased cases and imbalanced…

Training Transformers on algorithmic tasks frequently demonstrates an intriguing abrupt learning phenomenon: an extended performance plateau followed by a sudden, sharp improvement. This work investigates the underlying mechanisms for such…

Visual Odometry (VO) is essential to downstream mobile robotics and augmented/virtual reality tasks. Despite recent advances, existing VO methods still rely on heuristic design choices that require several weeks of hyperparameter tuning by…

Unsupervised localization and segmentation are long-standing robot vision challenges that describe the critical ability for an autonomous robot to learn to decompose images into individual objects without labeled data. These tasks are…

Attention is fundamental to both biological and artificial intelligence, yet research on animal attention and AI self attention remains largely disconnected. We propose a Recurrent Vision Transformer (Recurrent ViT) that integrates…