Related papers: SCHEME: Scalable Channel Mixer for Vision Transfor…

Vision Transformer(ViT) is now dominating many vision tasks. The drawback of quadratic complexity of its token-wise multi-head self-attention (MHSA), is extensively addressed via either token sparsification or dimension reduction (in…

The complexity of scene parsing grows with the number of object and scene classes, which is higher in unrestricted open scenes. The biggest challenge is to model the spatial relation between scene elements while succeeding in identifying…

Token-mixing multi-layer perceptron (MLP) models have shown competitive performance in computer vision tasks with a simple architecture and relatively small computational cost. Their success in maintaining computation efficiency is mainly…

Lane detection is a fundamental task in autonomous driving, and has achieved great progress as deep learning emerges. Previous anchor-based methods often design dense anchors, which highly depend on the training dataset and remain fixed…

Multi-layer perceptrons (MLPs) conventionally follow a narrow-wide-narrow design where skip connections operate at the input/output dimensions while processing occurs in expanded hidden spaces. We challenge this convention by proposing…

Transformers are powerful neural architectures that allow integrating different modalities using attention mechanisms. In this paper, we leverage the neural transformer architectures for multi-channel speech recognition systems, where the…

Ground-based cloud image segmentation is a critical research domain for photovoltaic power forecasting. Current deep learning approaches primarily focus on encoder-decoder architectural refinements. However, existing methodologies exhibit…

The feature maps of vision encoders are fundamental to myriad modern AI tasks, ranging from core perception algorithms (e.g. semantic segmentation, object detection, depth perception, etc.) to modern multimodal understanding in…

Extracting robust feature representation is critical for object re-identification to accurately identify objects across non-overlapping cameras. Although having a strong representation ability, the Vision Transformer (ViT) tends to overfit…

Image dehazing is a typical task in the low-level vision field. Previous studies verified the effectiveness of the large convolutional kernel and attention mechanism in dehazing. However, there are two drawbacks: the multi-scale properties…

Clustering is a core task in machine learning with wide-ranging applications in data mining and pattern recognition. However, its unsupervised nature makes it inherently challenging. Many existing clustering algorithms suffer from critical…

To address the limitations of Transformer decoders in capturing edge details, recognizing local textures and modeling spatial continuity, this paper proposes a novel decoder framework specifically designed for medical image segmentation,…

Convolutional neural networks have enabled major progresses in addressing pixel-level prediction tasks such as semantic segmentation, depth estimation, surface normal prediction and so on, benefiting from their powerful capabilities in…

While current Vision Transformer (ViT) adapter methods have shown promising accuracy, their inference speed is implicitly hindered by inefficient memory access operations, e.g., standard normalization and frequent reshaping. In this work,…

Low-dose CT (LDCT) images are often accompanied by significant noise, which negatively impacts image quality and subsequent diagnostic accuracy. To address the challenges of multi-scale feature fusion and diverse noise distribution patterns…

Transformer framework has been showing superior performances in visual object tracking for its great strength in information aggregation across the template and search image with the well-known attention mechanism. Most recent advances…

As we push the boundaries of performance in various vision tasks, the models grow in size correspondingly. To keep up with this growth, we need very aggressive pruning techniques for efficient inference and deployment on edge devices.…

We propose an end-to-end-trainable attention module for convolutional neural network (CNN) architectures built for image classification. The module takes as input the 2D feature vector maps which form the intermediate representations of the…

The evolution of Vision Transformers has led to their widespread adaptation to different domains. Despite large-scale success, there remain significant challenges including their reliance on extensive computational and memory resources for…

Transformers have been extensively studied in medical image segmentation to build pairwise long-range dependence. Yet, relatively limited well-annotated medical image data makes transformers struggle to extract diverse global features,…