Related papers: DeRPN: Taking a further step toward more general o…

In this paper we propose novel Deformable Part Networks (DPNs) to learn {\em pose-invariant} representations for 2D object recognition. In contrast to the state-of-the-art pose-aware networks such as CapsNet \cite{sabour2017dynamic} and STN…

Deep Convolutional Neural Networks (DCNNs) commonly use generic `max-pooling' (MP) layers to extract deformation-invariant features, but we argue in favor of a more refined treatment. First, we introduce epitomic convolution as a building…

In recent years, object detection in deep learning has experienced rapid development. However, most existing object detection models perform well only on closed-set datasets, ignoring a large number of potential objects whose categories are…

Model efficiency has become increasingly important in computer vision. In this paper, we systematically study neural network architecture design choices for object detection and propose several key optimizations to improve efficiency.…

In this work, we introduce a novel method for calculating the 6DoF pose of an object using a single RGB-D image. Unlike existing methods that either directly predict objects' poses or rely on sparse keypoints for pose recovery, our approach…

Convolutional neural networks (CNNs) have attracted increasing attention in the remote sensing community. Most CNNs only take the last fully-connected layers as features for the classification of remotely sensed images, discarding the other…

Traditional semantic image search methods aim to retrieve images that match the meaning of the text query. However, these methods typically search for objects on the whole image, without considering the localization of objects within the…

Object detection has been one of the most active topics in computer vision for the past years. Recent works have mainly focused on pushing the state-of-the-art in the general-purpose COCO benchmark. However, the use of such detection…

Sparse R-CNN is a recent strong object detection baseline by set prediction on sparse, learnable proposal boxes and proposal features. In this work, we propose to improve Sparse R-CNN with two dynamic designs. First, Sparse R-CNN adopts a…

Despite significant success of deep learning in object detection tasks, the standard training of deep neural networks requires access to a substantial quantity of annotated images across all classes. Data annotation is an arduous and…

The introduction of DETR represents a new paradigm for object detection. However, its decoder conducts classification and box localization using shared queries and cross-attention layers, leading to suboptimal results. We observe that…

In this paper, we revisit the limitations of anchor-based lane detection methods, which have predominantly focused on fixed anchors that stem from the edges of the image, disregarding their versatility and quality. To overcome the…

Arbitrary shape text detection is a challenging task due to the high variety and complexity of scenes texts. In this paper, we propose a novel unified relational reasoning graph network for arbitrary shape text detection. In our method, an…

This paper introduces AdaptoVision, a novel convolutional neural network (CNN) architecture designed to efficiently balance computational complexity and classification accuracy. By leveraging enhanced residual units, depth-wise separable…

Detecting partially occluded objects is a difficult task. Our experimental results show that deep learning approaches, such as Faster R-CNN, are not robust at object detection under occlusion. Compositional convolutional neural networks…

Learning multi-scale representations is the common strategy to tackle object scale variation in dense prediction tasks. Although existing feature pyramid networks have greatly advanced visual recognition, inherent design defects inhibit…

Rotated object detection aims to identify and locate objects in images with arbitrary orientation. In this scenario, the oriented directions of objects vary considerably across different images, while multiple orientations of objects exist…

Almost all of the current top-performing object detection networks employ region proposals to guide the search for object instances. State-of-the-art region proposal methods usually need several thousand proposals to get high recall, thus…

Recent one-stage object detectors follow a per-pixel prediction approach that predicts both the object category scores and boundary positions from every single grid location. However, the most suitable positions for inferring different…

Deep Convolutional Neural Networks (DCNN) have been proven to be effective for various computer vision problems. In this work, we demonstrate its effectiveness on a continuous object orientation estimation task, which requires prediction of…