Related papers: Fast-ParC: Capturing Position Aware Global Feature…
We propose a new method to create compact convolutional neural networks (CNNs) by exploiting sparse convolutions. Different from previous works that learn sparsity in models, we directly employ hand-crafted kernels with regular sparse…
Vision Transformer (ViT) extends the application range of transformers from language processing to computer vision tasks as being an alternative architecture against the existing convolutional neural networks (CNN). Since the…
Rotation invariance is essential for precise, object-level segmentation in UAV aerial imagery, where targets can have arbitrary orientations and exhibit fine-scale details. Conventional segmentation architectures like U-Net rely on…
Vision Transformers (ViT) have recently emerged as a powerful alternative to convolutional networks (CNNs). Although hybrid models attempt to bridge the gap between these two architectures, the self-attention layers they rely on induce a…
Hybrid vision transformers combine the elements of conventional neural networks (NN) and vision transformers (ViT) to enable lightweight and accurate detection. However, several challenges remain for their efficient deployment on…
After their initial success in natural language processing, transformer architectures have rapidly gained traction in computer vision, providing state-of-the-art results for tasks such as image classification, detection, segmentation, and…
We present a technique for adding global context to deep convolutional networks for semantic segmentation. The approach is simple, using the average feature for a layer to augment the features at each location. In addition, we study several…
Convolutional Neural Networks (CNNs) have demonstrated state-of-the-art performance on many visual recognition tasks. However, the combination of convolution and pooling operations only shows invariance to small local location changes in…
Transformer with self-attention has led to the revolutionizing of natural language processing field, and recently inspires the emergence of Transformer-style architecture design with competitive results in numerous computer vision tasks.…
Recently, plain vision Transformers (ViTs) have shown impressive performance on various computer vision tasks, thanks to their strong modeling capacity and large-scale pretraining. However, they have not yet conquered the problem of image…
Convolutional Neural Networks (CNNs) have dominated computer vision for years, due to its ability in capturing locality and translation invariance. Recently, many vision transformer architectures have been proposed and they show promising…
Convolutional Neural Networks (CNNs) are extremely efficient, since they exploit the inherent translation-invariance of natural images. However, translation is just one of a myriad of useful spatial transformations. Can the same efficiency…
The recent amalgamation of transformer and convolutional designs has led to steady improvements in accuracy and efficiency of the models. In this work, we introduce FastViT, a hybrid vision transformer architecture that obtains the…
Reducing latency is a roaring trend in recent super-resolution (SR) research. While recent progress exploits various convolutional blocks, attention modules, and backbones to unlock the full potentials of the convolutional neural network…
In recent years, vision transformers (ViTs) have emerged as powerful and promising techniques for computer vision tasks such as image classification, object detection, and segmentation. Unlike convolutional neural networks (CNNs), which…
Modern convolutional neural networks apply the same operations on every pixel in an image. However, not all image regions are equally important. To address this inefficiency, we propose a method to dynamically apply convolutions conditioned…
The transformer model has gained widespread adoption in computer vision tasks in recent times. However, due to the quadratic time and memory complexity of self-attention, which is proportional to the number of input tokens, most existing…
Over the past decade, most methods in visual place recognition (VPR) have used neural networks to produce feature representations. These networks typically produce a global representation of a place image using only this image itself and…
Age estimation from facial images is a complex and multifaceted challenge in computer vision. In this study, we present a novel hybrid architecture that combines ConvNeXt, a state-of-the-art advancement of convolutional neural networks…
Vision Transformers (ViTs) have demonstrated strong performance across a range of computer vision tasks by modeling long-range spatial interactions via self-attention. However, channel-wise mixing in ViTs remains static, relying on fixed…