Related papers: Decoupling Semantics and Fingerprints: A Universal…

Detecting out-of-distribution (OOD) inputs is a principal task for ensuring the safety of deploying deep-neural-network classifiers in open-set scenarios. OOD samples can be drawn from arbitrary distributions and exhibit deviations from…

Attribution map visualization has arisen as one of the most effective techniques to understand the underlying inference process of Convolutional Neural Networks. In this task, the goal is to compute an score for each image pixel related…

Due to its noninvasive character, optical coherence tomography (OCT) has become a popular diagnostic method in clinical settings. However, the low-coherence interferometric imaging procedure is inevitably contaminated by heavy speckle…

Existing semantic segmentation approaches either aim to improve the object's inner consistency by modeling the global context, or refine objects detail along their boundaries by multi-scale feature fusion. In this paper, a new paradigm for…

Out-of-distribution (OOD) detection is crucial when deploying deep neural networks in the real world to ensure the reliability and safety of their applications. One main challenge in OOD detection is that neural network models often produce…

Automatic font generation without human experts is a practical and significant problem, especially for some languages that consist of a large number of characters. Existing methods for font generation are often in supervised learning. They…

Unsupervised learning enables modeling complex images without the need for annotations. The representation learned by such models can facilitate any subsequent analysis of large image datasets. However, some generative factors that cause…

LiDAR-based 3D object detection and panoptic segmentation are two crucial tasks in the perception systems of autonomous vehicles and robots. In this paper, we propose All-in-One Perception Network (AOP-Net), a LiDAR-based multi-task…

Deepfake detection remains a challenging task due to the difficulty of generalizing to new types of forgeries. This problem primarily stems from the overfitting of existing detection methods to forgery-irrelevant features and…

This paper presents GridNet, a new Convolutional Neural Network (CNN) architecture for semantic image segmentation (full scene labelling). Classical neural networks are implemented as one stream from the input to the output with subsampling…

The task of detecting morphed face images has become highly relevant in recent years to ensure the security of automatic verification systems based on facial images, e.g. automated border control gates. Detection methods based on Deep…

Extracting structured representations from raw visual data is an important and long-standing challenge in machine learning. Recently, techniques for unsupervised learning of object-centric representations have raised growing interest. In…

With growing abilities of generative models, artificial content detection becomes an increasingly important and difficult task. However, all popular approaches to this problem suffer from poor generalization across domains and generative…

Visual surface inspection is a challenging task owing to the highly diverse appearance of target surfaces and defective regions. Previous attempts heavily rely on vast quantities of training examples with manual annotation. However, in some…

Keypoint detection is the foundation of many computer vision tasks, including image registration, structure-from-motion, 3D reconstruction, visual odometry, and SLAM. Traditional detectors (SIFT, ORB, BRISK, FAST, etc.) and learning-based…

The fidelity of Generative Adversarial Networks (GAN) inversion is impeded by Out-Of-Domain (OOD) areas (e.g., background, accessories) in the image. Detecting the OOD areas beyond the generation ability of the pre-trained model and…

In recent years, advanced image editing and generation methods have rapidly evolved, making detecting and locating forged image content increasingly challenging. Most existing image forgery detection methods rely on identifying the edited…

In this paper, we propose a very deep fully convolutional encoding-decoding framework for image restoration such as denoising and super-resolution. The network is composed of multiple layers of convolution and de-convolution operators,…

Image-to-image translation (i2i) networks suffer from entanglement effects in presence of physics-related phenomena in target domain (such as occlusions, fog, etc), lowering altogether the translation quality, controllability and…

Variable scene layouts and coexisting objects across scenes make indoor scene recognition still a challenging task. Leveraging object information within scenes to enhance the distinguishability of feature representations has emerged as a…