Related papers: Spatial Coherence Loss: All Objects Matter in Sali…
Learning discriminative representations is a central goal of supervised deep learning. While cross-entropy (CE) remains the dominant objective for classification, it does not explicitly enforce desirable geometric properties in the…
We provide a comprehensive evaluation of salient object detection (SOD) models. Our analysis identifies a serious design bias of existing SOD datasets which assumes that each image contains at least one clearly outstanding salient object in…
Deep learning based salient object detection has recently achieved great success with its performance greatly outperforms any other unsupervised methods. However, annotating per-pixel saliency masks is a tedious and inefficient procedure.…
Change detection, i.e. identification per pixel of changes for some classes of interest from a set of bi-temporal co-registered images, is a fundamental task in the field of remote sensing. It remains challenging due to unrelated forms of…
Salient object detection (SOD) remains an important task in computer vision, with applications ranging from image segmentation to autonomous driving. Fully convolutional network (FCN)-based methods have made remarkable progress in visual…
Semantic objects are unevenly distributed over images. In this paper, we study the spatial disequilibrium problem of modern object detectors and propose to quantify this ``spatial bias'' by measuring the detection performance over zones.…
Existing self-supervised learning (SSL) methods primarily learn object-invariant representations but often neglect the spatial structure and relationships among object parts. To address this limitation, we introduce Spatial Prediction (SP),…
Current methods aggregate multi-level features or introduce edge and skeleton to get more refined saliency maps. However, little attention is paid to how to obtain the complete salient object in cluttered background, where the targets are…
Camouflaged object detection (COD), segmenting objects that are elegantly blended into their surroundings, is a valuable yet challenging task. Existing deep-learning methods often fall into the difficulty of accurately identifying the…
Parts provide a good intermediate representation of objects that is robust with respect to the camera, pose and appearance variations. Existing works on part segmentation is dominated by supervised approaches that rely on large amounts of…
A key problem in salient object detection is how to effectively model the semantic properties of salient objects in a data-driven manner. In this paper, we propose a multi-task deep saliency model based on a fully convolutional neural…
This paper focuses on camouflaged object detection (COD), which is a task to detect objects hidden in the background. Most of the current COD models aim to highlight the target object directly while outputting ambiguous camouflaged…
Although current salient object detection (SOD) works have achieved significant progress, they are limited when it comes to the integrity of the predicted salient regions. We define the concept of integrity at both a micro and macro level.…
Recently salient object detection has witnessed remarkable improvement owing to the deep convolutional neural networks which can harvest powerful features for images. In particular, state-of-the-art salient object detection methods enjoy…
We propose a new setting that relaxes an assumption in the conventional Co-Salient Object Detection (CoSOD) setting by allowing the presence of "noisy images" which do not show the shared co-salient object. We call this new setting…
Existing scene understanding systems mainly focus on recognizing the visible parts of a scene, ignoring the intact appearance of physical objects in the real-world. Concurrently, image completion has aimed to create plausible appearance for…
Developing a new Salient Object Detection (SOD) model involves selecting an ImageNet pre-trained backbone and creating novel feature refinement modules to use backbone features. However, adding new components to a pre-trained backbone needs…
SAM is a segmentation model recently released by Meta AI Research and has been gaining attention quickly due to its impressive performance in generic object segmentation. However, its ability to generalize to specific scenes such as…
Most learning-based approaches to category-level 6D pose estimation are design around normalized object coordinate space (NOCS). While being successful, NOCS-based methods become inaccurate and less robust when handling objects of a…
The latest deep learning-based approaches have shown promising results for the challenging task of inpainting missing regions of an image. However, the existing methods often generate contents with blurry textures and distorted structures…