Related papers: FA-RPN: Floating Region Proposals for Face Detecti…
This paper proposes anchor pruning for object detection in one-stage anchor-based detectors. While pruning techniques are widely used to reduce the computational cost of convolutional neural networks, they tend to focus on optimizing the…
The increasing computational demands of modern neural networks present deployment challenges on resource-constrained devices. Network pruning offers a solution to reduce model size and computational cost while maintaining performance.…
We consider detecting objects in an image by iteratively selecting from a set of arbitrarily shaped candidate regions. Our generic approach, which we term visual chunking, reasons about the locations of multiple object instances in an image…
Millimeter-wave radars are being increasingly integrated into commercial vehicles to support new advanced driver-assistance systems by enabling robust and high-performance object detection, localization, as well as recognition - a key…
Photos of faces captured in unconstrained environments, such as large crowds, still constitute challenges for current face recognition approaches as often faces are occluded by objects or people in the foreground. However, few studies have…
High quality object proposals are crucial in visual tracking algorithms that utilize region proposal network (RPN). Refinement of these proposals, typically by box regression and classification in parallel, has been popularly adopted to…
Learning pyramidal feature representations is crucial for recognizing object instances at different scales. Feature Pyramid Network (FPN) is the classic architecture to build a feature pyramid with high-level semantics throughout. However,…
This paper focuses on network pruning for image retrieval acceleration. Prevailing image retrieval works target at the discriminative feature learning, while little attention is paid to how to accelerate the model inference, which should be…
Recent object detection systems rely on two critical steps: (1) a set of object proposals is predicted as efficiently as possible, and (2) this set of candidate proposals is then passed to an object classifier. Such approaches have been…
In object detection, determining which anchors to assign as positive or negative samples, known as anchor assignment, has been revealed as a core procedure that can significantly affect a model's performance. In this paper we propose a…
A standard pipeline of current face recognition frameworks consists of four individual steps: locating a face with a rough bounding box and several fiducial landmarks, aligning the face image using a pre-defined template, extracting…
The region proposal task is to generate a set of candidate regions that contain an object. In this task, it is most important to propose as many candidates of ground-truth as possible in a fixed number of proposals. In a typical image,…
Conventional remote sensing image retrieval (RSIR) systems usually perform single-label retrieval where each image is annotated by a single label representing the most significant semantic content of the image. This assumption, however,…
Understanding the world in 3D is a critical component of urban autonomous driving. Generally, the combination of expensive LiDAR sensors and stereo RGB imaging has been paramount for successful 3D object detection algorithms, whereas…
R-CNN style methods are sorts of the state-of-the-art object detection methods, which consist of region proposal generation and deep CNN classification. However, the proposal generation phase in this paradigm is usually time consuming,…
Recently, image representation built upon Convolutional Neural Network (CNN) has been shown to provide effective descriptors for image search, outperforming pre-CNN features as short-vector representations. Yet such models are not…
This paper proposes a few-shot method based on Faster R-CNN and representation learning for object detection in aerial images. The two classification branches of Faster R-CNN are replaced by prototypical networks for online adaptation to…
Due to the effective performance of multi-scale feature fusion, Path Aggregation FPN (PAFPN) is widely employed in YOLO detectors. However, it cannot efficiently and adaptively integrate high-level semantic information with low-level…
Object detection in optical remote sensing images is an important and challenging task. In recent years, the methods based on convolutional neural networks have made good progress. However, due to the large variation in object scale, aspect…
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…