Related papers: Mask DINO: Towards A Unified Transformer-based Fra…

Retinal vessel segmentation plays an imaportant role in the field of retinal image analysis because changes in retinal vascular structure can aid in the diagnosis of diseases such as hypertension and diabetes. In recent research, numerous…

Model calibration measures the agreement between the predicted probability estimates and the true correctness likelihood. Proper model calibration is vital for high-risk applications. Unfortunately, modern deep neural networks are poorly…

Semantic segmentation is essential in computer vision for various applications, yet traditional approaches face significant challenges, including the high cost of annotation and extensive training for supervised learning. Additionally, due…

The prevalence of skin melanoma is rapidly increasing as well as the recorded death cases of its patients. Automatic image segmentation tools play an important role in providing standardized computer-assisted analysis for skin melanoma…

Convolutional neural networks typically encode an input image into a series of intermediate features with decreasing resolutions. While this structure is suited to classification tasks, it does not perform well for tasks requiring…

Utilizing visual place recognition (VPR) technology to ascertain the geographical location of publicly available images is a pressing issue for real-world VPR applications. Although most current VPR methods achieve favorable results under…

Much of the recent efforts on salient object detection (SOD) have been devoted to producing accurate saliency maps without being aware of their instance labels. To this end, we propose a new pipeline for end-to-end salient instance…

In this work, we leverage informative embeddings from foundational models for unsupervised anomaly detection in medical imaging. For small datasets, a memory-bank of normative features can directly be used for anomaly detection which has…

Object segmentation requires both object-level information and low-level pixel data. This presents a challenge for feedforward networks: lower layers in convolutional nets capture rich spatial information, while upper layers encode…

Range-view based LiDAR segmentation methods are attractive for practical applications due to their direct inheritance from efficient 2D CNN architectures. In literature, most range-view based methods follow the per-pixel classification…

Pixel-level annotation demands expensive human efforts and limits the performance of deep networks that usually benefits from more such training data. In this work we aim to achieve high quality instance and semantic segmentation results…

Camouflaged Object Detection (COD) is a critical aspect of computer vision aimed at identifying concealed objects, with applications spanning military, industrial, medical and monitoring domains. To address the problem of poor detail…

The problem of video object segmentation can become extremely challenging when multiple instances co-exist. While each instance may exhibit large scale and pose variations, the problem is compounded when instances occlude each other causing…

Segmenting unknown or anomalous object instances is a critical task in autonomous driving applications, and it is approached traditionally as a per-pixel classification problem. However, reasoning individually about each pixel without…

Moving object segmentation plays a crucial role in understanding dynamic scenes involving multiple moving objects, while the difficulties lie in taking into account both spatial texture structures and temporal motion cues. Existing methods…

Ultrasound image segmentation is pivotal for clinical diagnosis, yet challenged by speckle noise and imaging artifacts. Recently, DINOv3 has shown remarkable promise in medical image segmentation with its powerful representation…

Open Set Object Detection has seen rapid development recently, but it continues to pose significant challenges. Language-based methods, grappling with the substantial modal disparity between textual and visual modalities, require extensive…

Instance segmentation is one of the fundamental vision tasks. Recently, fully convolutional instance segmentation methods have drawn much attention as they are often simpler and more efficient than two-stage approaches like Mask R-CNN. To…

Unsupervised object discovery is becoming an essential line of research for tackling recognition problems that require decomposing an image into entities, such as semantic segmentation and object detection. Recently, object-centric methods…

We present a mask-piloted Transformer which improves masked-attention in Mask2Former for image segmentation. The improvement is based on our observation that Mask2Former suffers from inconsistent mask predictions between consecutive decoder…