Related papers: Frequency-Adaptive Discrete Cosine-ViT-ResNet Arch…

Few-shot learning in remote sensing remains challenging due to three factors: the scarcity of labeled data, substantial domain shifts, and the multi-scale nature of geospatial objects. To address these issues, we introduce Adaptive…

Deep neural networks achieve remarkable performance in many computer vision tasks. Most state-of-the-art (SOTA) semantic segmentation and object detection approaches reuse neural network architectures designed for image classification as…

High-throughput material screening for the discovery and design of novel functional materials requires automatized analyses of theoretical and experimental data. Here we study the subject of human-free analyses of one-dimensional…

Pan-sharpening involves reconstructing missing high-frequency information in multi-spectral images with low spatial resolution, using a higher-resolution panchromatic image as guidance. Although the inborn connection with frequency domain,…

Convolutional neural networks (CNNs) learn filters in order to capture local correlation patterns in feature space. We propose to learn these filters as combinations of preset spectral filters defined by the Discrete Cosine Transform (DCT).…

Vision Transformer (ViT) self-attention mechanism is characterized by feature collapse in deeper layers, resulting in the vanishing of low-level visual features. However, such features can be helpful to accurately represent and identify…

Salient object detection (SOD) in remote sensing images faces significant challenges due to large variations in object sizes, the computational cost of self-attention mechanisms, and the limitations of CNN-based extractors in capturing…

This paper introduces VDLF-Net, which attaches a compact VAE to a multi-scale CNN backbone. Latent vectors and softmax-gate support the backbone feature maps, while $\ell_2$-normalized embeddings from the gated maps contribute toward…

Dataset bias remains a significant barrier towards solving real world computer vision tasks. Though deep convolutional networks have proven to be a competitive approach for image classification, a question remains: have these models have…

In existing CNN based detectors, the backbone network is a very important component for basic feature extraction, and the performance of the detectors highly depends on it. In this paper, we aim to achieve better detection performance by…

Learning subtle representation about object parts plays a vital role in fine-grained visual recognition (FGVR) field. The vision transformer (ViT) achieves promising results on computer vision due to its attention mechanism. Nonetheless,…

Few-shot learning aims to recognize novel concepts by leveraging prior knowledge learned from a few samples. However, for visually intensive tasks such as few-shot semantic segmentation, pixel-level annotations are time-consuming and…

In recent years, the integration of advanced imaging techniques and deep learning methods has significantly advanced computer-aided diagnosis (CAD) systems for breast cancer detection and classification. Transformers, which have shown great…

We develop techniques for refining representations for fine-grained classification and segmentation tasks in a self-supervised manner. We find that fine-tuning methods based on instance-discriminative contrastive learning are not as…

Fine-grained classification of microscopic image data with limited samples is an open problem in computer vision and biomedical imaging. Deep learning based vision systems mostly deal with high number of low-resolution images, whereas…

In this paper, we propose a novel Discrete Cosine Transform (DCT)-based neural network layer which we call DCT-perceptron to replace the $3\times3$ Conv2D layers in the Residual neural Network (ResNet). Convolutional filtering operations…

Although deep models have greatly improved the accuracy and robustness of image segmentation, obtaining segmentation results with highly accurate boundaries and fine structures is still a challenging problem. In this paper, we propose a…

Dense optical flow estimation is challenging when there are large displacements in a scene with heterogeneous motion dynamics, occlusion, and scene homogeneity. Traditional approaches to handle these challenges include hierarchical and…

Modern on-device neural network applications must operate under resource constraints while adapting to unpredictable domain shifts. However, this combined challenge-model compression and domain adaptation-remains largely unaddressed, as…

X-ray computed tomography (CT) using sparse projection views is a recent approach to reduce the radiation dose. However, due to the insufficient projection views, an analytic reconstruction approach using the filtered back projection (FBP)…