Related papers: KD-SCFNet: Towards More Accurate and Efficient Sal…
Despite the remarkable advances in visual saliency analysis for natural scene images (NSIs), salient object detection (SOD) for optical remote sensing images (RSIs) still remains an open and challenging problem. In this paper, we propose an…
Fully convolutional networks have shown outstanding performance in the salient object detection (SOD) field. The state-of-the-art (SOTA) methods have a tendency to become deeper and more complex, which easily homogenize their learned deep…
We solve the problem of salient object detection by investigating how to expand the role of pooling in convolutional neural networks. Based on the U-shape architecture, we first build a global guidance module (GGM) upon the bottom-up…
Knowledge distillation(KD) is a widely-used technique to train compact models in object detection. However, there is still a lack of study on how to distill between heterogeneous detectors. In this paper, we empirically find that better FPN…
Deep neural network based methods have made a significant breakthrough in salient object detection. However, they are typically limited to input images with low resolutions ($400\times400$ pixels or less). Little effort has been made to…
The real human attention is an interactive activity between our visual system and our brain, using both low-level visual stimulus and high-level semantic information. Previous image salient object detection (SOD) works conduct their…
Current state-of-the-art object detectors are at the expense of high computational costs and are hard to deploy to low-end devices. Knowledge distillation, which aims at training a smaller student network by transferring knowledge from a…
Video salient object detection (SOD) relies on motion cues to distinguish salient objects from backgrounds, but training such models is limited by scarce video datasets compared to abundant image datasets. Existing approaches that use…
Existing methods for Salient Object Detection in Optical Remote Sensing Images (ORSI-SOD) mainly adopt Convolutional Neural Networks (CNNs) as the backbone, such as VGG and ResNet. Since CNNs can only extract features within certain…
To detect salient objects accurately, existing methods usually design complex backbone network architectures to learn and fuse powerful features. However, the saliency inference module that performs saliency prediction from the fused…
Fully supervised salient object detection (SOD) methods have made considerable progress in performance, yet these models rely heavily on expensive pixel-wise labels. Recently, to achieve a trade-off between labeling burden and performance,…
Detection of violence and weaponized violence in closed-circuit television (CCTV) footage requires a comprehensive approach. In this work, we introduce the \emph{Smart-City CCTV Violence Detection (SCVD)} dataset, specifically designed to…
Fully Convolutional Neural Network (FCN) has been widely applied to salient object detection recently by virtue of high-level semantic feature extraction, but existing FCN based methods still suffer from continuous striding and pooling…
In view of the problems that existing salient object detection (SOD) methods are prone to losing details, blurring edges, and insufficient fusion of single-modal information in complex scenes, this paper proposes a dynamic uncertainty…
Co-Salient Object Detection (CoSOD) aims at discovering salient objects that repeatedly appear in a given query group containing two or more relevant images. One challenging issue is how to effectively capture co-saliency cues by modeling…
Knowledge Distillation (KD) is a widely-used technology to inherit information from cumbersome teacher models to compact student models, consequently realizing model compression and acceleration. Compared with image classification, object…
Salient object detection in optical remote sensing images (ORSI-SOD) has been widely explored for understanding ORSIs. However, previous methods focus mainly on improving the detection accuracy while neglecting the cost in memory and…
The goal of this work is to present a systematic solution for RGB-D salient object detection, which addresses the following three aspects with a unified framework: modal-specific representation learning, complementary cue selection and…
Recent progress on saliency detection is substantial, benefiting mostly from the explosive development of Convolutional Neural Networks (CNNs). Semantic segmentation and saliency detection algorithms developed lately have been mostly based…
In this paper, we attempt to specialize the VLM model for OWOD tasks by distilling its open-world knowledge into a language-agnostic detector. Surprisingly, we observe that the combination of a simple \textbf{knowledge distillation}…