Related papers: Fully Attentional Networks with Self-emerging Toke…

The quadratic computational complexity of softmax transformers has become a bottleneck in long-context scenarios. In contrast, linear attention model families provide a promising direction towards a more efficient sequential model. These…

Large-scale pre-trained Vision-Language Models (VLMs) have demonstrated strong few-shot learning capabilities. However, these methods typically learn holistic representations where an image's domain-invariant structure is implicitly…

Traditional semantic segmentation tasks require a large number of labels and are difficult to identify unlearned categories. Few-shot semantic segmentation (FSS) aims to use limited labeled support images to identify the segmentation of new…

Few-shot class-incremental learning (FSCIL) has recently attracted extensive attention in various areas. Existing FSCIL methods highly depend on the robustness of the feature backbone pre-trained on base classes. In recent years, different…

Fine-grained visual classification (FGVC) which aims at recognizing objects from subcategories is a very challenging task due to the inherently subtle inter-class differences. Most existing works mainly tackle this problem by reusing the…

Lane detection is a crucial perception task for all levels of automated vehicles (AVs) and Advanced Driver Assistance Systems, particularly in mixed-traffic environments where AVs must interact with human-driven vehicles (HDVs) and…

Transformer-based methods have demonstrated strong potential in hyperspectral pansharpening by modeling long-range dependencies. However, their effectiveness is often limited by redundant token representations and a lack of multi-scale…

Recent Vision-Language Models (VLMs) have demonstrated remarkable multimodal understanding capabilities, yet the redundant visual tokens incur prohibitive computational overhead and degrade inference efficiency. Prior studies typically…

In this work, we propose a novel methodology for self-supervised learning for generating global and local attention-aware visual features. Our approach is based on training a model to differentiate between specific image transformations of…

While linear-complexity attention mechanisms offer a promising alternative to Softmax attention for overcoming the quadratic bottleneck, training such models from scratch remains prohibitively expensive. Inheriting weights from pretrained…

Synthesising a text-to-image model of high-quality images by guiding the generative model through the Text description is an innovative and challenging task. In recent years, AttnGAN based on the Attention mechanism to guide GAN training…

Large Language Models (LLMs) have excelled in various tasks but perform better in high-resource scenarios, which presents challenges in low-resource scenarios. Data scarcity and the inherent difficulty of adapting LLMs to specific tasks…

Recent Vision Transformer~(ViT) models have demonstrated encouraging results across various computer vision tasks, thanks to their competence in modeling long-range dependencies of image patches or tokens via self-attention. These models,…

The remarkable performance of Vision Transformers (ViTs) typically requires an extremely large training cost. Existing methods have attempted to accelerate the training of ViTs, yet typically disregard method universality with accuracy…

We propose Vision Token Turing Machines (ViTTM), an efficient, low-latency, memory-augmented Vision Transformer (ViT). Our approach builds on Neural Turing Machines and Token Turing Machines, which were applied to NLP and sequential visual…

Vision Transformers (ViTs) with self-attention modules have recently achieved great empirical success in many vision tasks. Due to non-convex interactions across layers, however, theoretical learning and generalization analysis is mostly…

Vision Transformer (ViT) has gained increasing attention in the computer vision community in recent years. However, the core component of ViT, Self-Attention, lacks explicit spatial priors and bears a quadratic computational complexity,…

Attention-based neural networks such as the Vision Transformer (ViT) have recently attained state-of-the-art results on many computer vision benchmarks. Scale is a primary ingredient in attaining excellent results, therefore, understanding…

Vision-language models (VLMs) such as CLIP exhibit strong Out-of-distribution (OOD) detection capabilities by aligning visual and textual representations. Recent CLIP-based test-time adaptation methods further improve detection performance…

Vision transformers (ViT) have been shown to allow for more flexible feature detection and can outperform convolutional neural network (CNN) when pre-trained on sufficient data. Due to their promising feature detection capabilities, we…