Related papers: StairNet: Top-Down Semantic Aggregation for Accura…
Existing single-stage detectors for locating objects in point clouds often treat object localization and category classification as separate tasks, so the localization accuracy and classification confidence may not well align. To address…
Recent salient object detection (SOD) models predominantly rely on heavyweight backbones, incurring substantial computational cost and hindering their practical application in various real-world settings, particularly on edge devices. This…
Infrared small target detection is a technique for finding small targets from infrared clutter background. Due to the dearth of high-level semantic information, small infrared target features are weakened in the deep layers of the CNN,…
Downsampling is widely adopted to achieve a good trade-off between accuracy and latency for visual recognition. Unfortunately, the commonly used pooling layers are not learned, and thus cannot preserve important information. As another…
Scale-sensitive object detection remains a challenging task, where most of the existing methods could not learn it explicitly and are not robust to scale variance. In addition, the most existing methods are less efficient during training or…
Existing state-of-the-art salient object detection networks rely on aggregating multi-level features of pre-trained convolutional neural networks (CNNs). Compared to high-level features, low-level features contribute less to performance but…
Small object detection (SOD) remains challenging due to extremely limited pixels and ambiguous object boundaries. These characteristics lead to challenging annotation, limited availability of large-scale high-quality datasets, and…
In LiDAR-based 3D object detection for autonomous driving, the ratio of the object size to input scene size is significantly smaller compared to 2D detection cases. Overlooking this difference, many 3D detectors directly follow the common…
Recent object detection models require large amounts of annotated data for training a new classes of objects. Few-shot object detection (FSOD) aims to address this problem by learning novel classes given only a few samples. While…
A vision-language foundation model pretrained on very large-scale image-text paired data has the potential to provide generalizable knowledge representation for downstream visual recognition and detection tasks, especially on supplementing…
With the goal of identifying pixel-wise salient object regions from each input image, salient object detection (SOD) has been receiving great attention in recent years. One kind of mainstream SOD methods is formed by a bottom-up feature…
A major bottleneck of pedestrian detection lies on the sharp performance deterioration in the presence of small-size pedestrians that are relatively far from the camera. Motivated by the observation that pedestrians of disparate spatial…
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…
Category-level pose estimation is a challenging task with many potential applications in computer vision and robotics. Recently, deep-learning-based approaches have made great progress, but are typically hindered by the need for large…
Domain adaptive object detection (DAOD) aims to alleviate transfer performance degradation caused by the cross-domain discrepancy. However, most existing DAOD methods are dominated by outdated and computationally intensive two-stage Faster…
State-of-the-art (SoTA) models have improved the accuracy of object detection with a large margin via a FP (feature pyramid). FP is a top-down aggregation to collect semantically strong features to improve scale invariance in both two-stage…
Object detection problem solving has developed greatly within the past few years. There is a need for lighter models in instances where hardware limitations exist, as well as a demand for models to be tailored to mobile devices. In this…
Recently, a lot of single stage detectors using multi-scale features have been actively proposed. They are much faster than two stage detectors that use region proposal networks (RPN) without much degradation in the detection performances.…
State-of-the-art detection systems are generally evaluated on their ability to exhaustively retrieve objects densely distributed in the image, across a wide variety of appearances and semantic categories. Orthogonal to this, many real-life…
Detecting small objects over large areas remains a significant challenge in satellite imagery analytics. Among the challenges is the sheer number of pixels and geographical extent per image: a single DigitalGlobe satellite image encompasses…