Related papers: Synthesize then Compare: Detecting Failures and An…

Anomaly detection in visual data refers to the problem of differentiating abnormal appearances from normal cases. Supervised approaches have been successfully applied to different domains, but require an abundance of labeled data. Due to…

This paper proposes to use set features for detecting anomalies in samples that consist of unusual combinations of normal elements. Many leading methods discover anomalies by detecting an unusual part of a sample. For example,…

Semantic segmentation is fundamental to vision systems requiring pixel-level scene understanding, yet deploying it on resource-constrained devices demands efficient architectures. Although existing methods achieve real-time inference…

In the past several years, road anomaly segmentation is actively explored in the academia and drawing growing attention in the industry. The rationale behind is straightforward: if the autonomous car can brake before hitting an anomalous…

Reflections in natural images commonly cause false positives in automated detection systems. These false positives can lead to significant impairment of accuracy in the tasks of detection, counting and segmentation. Here, inspired by the…

Convolutional neural networks (CNNs) show outstanding performance in many image processing problems, such as image recognition, object detection and image segmentation. Semantic segmentation is a very challenging task that requires…

Feature fusion modules from encoder and self-attention module have been adopted in semantic segmentation. However, the computation of these modules is costly and has operational limitations in real-time environments. In addition,…

Recently, learning-based image synthesis has enabled to generate high-resolution images, either applying popular adversarial training or a powerful perceptual loss. However, it remains challenging to successfully leverage synthetic data for…

This paper introduces an efficient sub-model ensemble framework aimed at enhancing the interpretability of medical deep learning models, thus increasing their clinical applicability. By generating uncertainty maps, this framework enables…

3D panoptic segmentation is a challenging perception task that requires both semantic segmentation and instance segmentation. In this task, we notice that images could provide rich texture, color, and discriminative information, which can…

State-of-the-art semantic or instance segmentation deep neural networks (DNNs) are usually trained on a closed set of semantic classes. As such, they are ill-equipped to handle previously-unseen objects. However, detecting and localizing…

This paper introduces a novel synthetic dataset that captures urban scenes under a variety of weather conditions, providing pixel-perfect, ground-truth-aligned images to facilitate effective feature alignment across domains. Additionally,…

Reconstruction-based methods play an important role in unsupervised anomaly detection in images. Ideally, we expect a perfect reconstruction for normal samples and poor reconstruction for abnormal samples. Since the generalizability of deep…

Semantic segmentation of night-time images holds significant importance in computer vision, particularly for applications like night environment perception in autonomous driving systems. However, existing methods tend to parse night-time…

Topological correctness is critical for segmentation of tubular structures, which pervade in biomedical images. Existing topological segmentation loss functions are primarily based on the persistent homology of the image. They match the…

Aerial-to-ground image synthesis is an emerging and challenging problem that aims to synthesize a ground image from an aerial image. Due to the highly different layout and object representation between the aerial and ground images, existing…

Mirror detection aims to identify the mirror regions in the given input image. Existing works mainly focus on integrating the semantic features and structural features to mine specific relations between mirror and non-mirror regions, or…

One of the fundamental challenges in the design of perception systems for autonomous vehicles is validating the performance of each algorithm under a comprehensive variety of operating conditions. In the case of vision-based semantic…

Consistency regularization describes a class of approaches that have yielded ground breaking results in semi-supervised classification problems. Prior work has established the cluster assumption - under which the data distribution consists…

Semantic anomalies are contextually invalid or unusual combinations of familiar visual elements that can cause undefined behavior and failures in system-level reasoning for autonomous systems. This work explores semantic anomaly detection…