Change detection is an essential and widely utilized task in remote sensing that aims to
detect and analyze changes occurring in the same geographical area over time, which has …

Lightweight deep convolutional neural networks (LDCNNs) are vital components of mobile
intelligence, particularly in mobile vision. Although various heavy networks with increasingly …

Visual segmentation seeks to partition images, video frames, or point clouds into multiple
segments or groups. This technique has numerous real-world applications, such as …

Reconstruction-based approaches have achieved remarkable outcomes in anomaly
detection. The exceptional image reconstruction capabilities of recently popular diffusion …

Abstract Recently efficient Vision Transformers have shown great performance with low
latency on resource-constrained devices. Conventionally they use 4x4 patch embeddings …

This paper presents EdgeSAM, an accelerated variant of the Segment Anything Model
(SAM), optimized for efficient execution on edge devices with minimal compromise in …

Deepfake is a technology dedicated to creating highly realistic facial images and videos
under specific conditions, which has significant application potential in fields such as …

This paper considers zero-shot Anomaly Detection (AD), performing AD without reference
images of the test objects. We propose a framework called CLIP-AD to leverage the zero …

Referring Image Segmentation (RIS) is a fundamental vision-language task that outputs
object masks based on text descriptions. Many works have achieved considerable progress …

In this work, we focus on open vocabulary instance segmentation to expand a segmentation
model to classify and segment instance-level novel categories. Previous approaches have …