Related papers: DSIC: Dynamic Sample-Individualized Connector for …

Multi-head detectors typically employ a features-fused-pyramid-neck for multi-scale detection and are widely adopted in the industry. However, this approach faces feature misalignment when representations from different hierarchical levels…

Scene graph generation aims to capture detailed spatial and semantic relationships between objects in an image, which is challenging due to incomplete labelling, long-tailed relationship categories, and relational semantic overlap. Existing…

Deep neural networks face many problems in the field of hyperspectral image classification, lack of effective utilization of spatial spectral information, gradient disappearance and overfitting as the model depth increases. In order to…

Click-through rate prediction plays an important role in the field of recommender system and many other applications. Existing methods mainly extract user interests from user historical behaviors. However, behavioral sequences only contain…

Keypoint detection plays an important role in a wide range of applications. However, predicting keypoints of small objects such as human hands is a challenging problem. Recent works fuse feature maps of deep Convolutional Neural Networks…

We propose Deeply Supervised Object Detectors (DSOD), an object detection framework that can be trained from scratch. Recent advances in object detection heavily depend on the off-the-shelf models pre-trained on large-scale classification…

Multi-modal salient object detection (MSOD) aims to boost saliency detection performance by integrating visible sources with depth or thermal infrared ones. Existing methods generally design different fusion schemes to handle certain issues…

Salient object detection plays an important role in many downstream tasks. However, complex real-world scenes with varying scales and numbers of salient objects still pose a challenge. In this paper, we directly address the problem of…

Multiple-instance Learning (MIL) is commonly used to undertake computational pathology (CPath) tasks, and the use of multi-scale patches allows diverse features across scales to be learned. Previous studies using multi-scale features in…

Multi-scale features have been proven highly effective for object detection but often come with huge and even prohibitive extra computation costs, especially for the recent Transformer-based detectors. In this paper, we propose Iterative…

In natural images, the scales (thickness) of object skeletons may dramatically vary among objects and object parts, making object skeleton detection a challenging problem. We present a new convolutional neural network (CNN) architecture by…

The world is covered with millions of buildings, and precisely knowing each instance's position and extents is vital to a multitude of applications. Recently, automated building footprint segmentation models have shown superior detection…

Convolution Neural Network (CNN) has gained tremendous success in computer vision tasks with its outstanding ability to capture the local latent features. Recently, there has been an increasing interest in extending convolution operations…

Infrared Small Target Detection (IRSTD) system aims to identify small targets in complex backgrounds. Due to the convolution operation in Convolutional Neural Networks (CNNs), applying traditional CNNs to IRSTD presents challenges, since…

Dynamic feature selection (DFS) is a machine learning framework in which features are acquired sequentially for individual samples under budget constraints. The exponential growth in the number of possible feature acquisition paths forces a…

Person Re-identification (ReID) is to identify the same person across different cameras. It is a challenging task due to the large variations in person pose, occlusion, background clutter, etc How to extract powerful features is a…

Fine-grained Visual Classification (FGVC) aims to identify objects from subcategories. It is a very challenging task because of the subtle inter-class differences. Existing research applies large-scale convolutional neural networks or…

We present Deeply Supervised Object Detector (DSOD), a framework that can learn object detectors from scratch. State-of-the-art object objectors rely heavily on the off-the-shelf networks pre-trained on large-scale classification datasets…

Recent advances in camera equipped drone applications and their widespread use increased the demand on vision based object detection algorithms for aerial images. Object detection process is inherently a challenging task as a generic…

Collection of massive well-annotated samples is effective in improving object detection performance but is extremely laborious and costly. Instead of data collection and annotation, the recently proposed Cut-Paste methods [12, 15] show the…