Accurately ranking the vast number of candidate detections is crucial for dense object detectors to achieve high performance. Prior work uses the classification score or a combination of classification and predicted localization scores to rank candidates. However, neither option results in a reliable ranking, thus degrading detection performance. In this paper, we propose to learn an Iou-aware Classification Score (IACS) as a joint representation of object presence confidence and localization accuracy. We show that dense object detectors can achieve a more accurate ranking of candidate detections based on the IACS. We design a new loss function, named Varifocal Loss, to train a dense object detector to predict the IACS, and propose a new star-shaped bounding box feature representation for IACS prediction and bounding box refinement. Combining these two new components and a bounding box refinement branch, we build an IoU-aware dense object detector based on the FCOS+ATSS architecture, that we call VarifocalNet or VFNet for short. Extensive experiments on MS COCO show that our VFNet consistently surpasses the strong baseline by $\sim$2.0 AP with different backbones. Our best model VFNet-X-1200 with Res2Net-101-DCN achieves a single-model single-scale AP of 55.1 on COCO test-dev, which is state-of-the-art among various object detectors.Code is available at https://github.com/hyz-xmaster/VarifocalNet .
Without densely tiled anchor boxes or grid points in the image, sparse R-CNN achieves promising results through a set of object queries and proposal boxes updated in the cascaded training manner. However, due to the sparse nature and the one-to-one relation between the query and its attending region, it heavily depends on the self attention, which is usually inaccurate in the early training stage. Moreover, in a scene of dense objects, the object query interacts with many irrelevant ones, reducing its uniqueness and harming the performance. This paper proposes to use IoU between different boxe…
Object detection in densely packed scenes is a new area where standard object detectors fail to train well. Dense object detectors like RetinaNet trained on large and dense datasets show great performance. We train a standard object detector on a small, normally packed dataset with data augmentation techniques. This dataset is 265 times smaller than the standard dataset, in terms of number of annotations. This low data baseline achieves satisfactory results (mAP=0.56) at standard IoU of 0.5. We also create a varied benchmark for generic SKU product detection by providing full annotations for m…
Image co-segmentation has attracted a lot of attentions in computer vision community. In this paper, we propose a new approach to image co-segmentation through introducing the dense connections into the decoder path of Siamese U-net and presenting a new edge enhanced 3D IOU loss measured over distance maps. Considering the rigorous mapping between the signed normalized distance map (SNDM) and the binary segmentation mask, we estimate the SNDMs directly from original images and use them to determine the segmentation results. We apply the Siamese U-net for solving this problem and improve its ef…
Generalization vs. Specialization: Evaluating Segment Anything Model (SAM3) Zero-Shot Segmentation Against Fine-Tuned YOLO Detectors
Cornell University, Department of Biological and Environmental Engineering（康奈尔大学生物与环境工程系）；University of the Peloponnese, Department of Informatics and Telecommunications（希腊皮埃里亚大学信息与电信系）
Tencent（腾讯）；The Chinese University of Hong Kong（香港中文大学）
We present a new two-stage 3D object detection framework, named sparse-to-dense 3D Object Detector (STD). The first stage is a bottom-up proposal generation network that uses raw point cloud as input to generate accurate proposals by seeding each point with a new spherical anchor. It achieves a high recall with less computation compared with prior works. Then, PointsPool is applied for generating proposal features by transforming their interior point features from sparse expression to compact representation, which saves even more computation time. In box prediction, which is the second stage, …
Bridging Cross-task Protocol Inconsistency for Distillation in Dense Object Detection
College of Computer Science & Technology, Zhejiang University（浙江大学计算机科学与技术学院）；Polytechnic Institute, Zhejiang University（浙江大学理工学院）；Hikvision Research Institute（海康威视研究院）；ZJU – UIUC Institute, Zhejiang University（浙江大学-伊利诺伊大学厄巴纳-香槟分校研究院）；Shanghai Institute for Advanced Study of Zhejiang University（浙江大学上海高等研究院）
CDV AI Research（CDV人工智能研究院）；Valeo Vision Systems（法雷奥视觉系统公司）；Valeo R&D DVS（法雷奥研发DVS中心）；Nile University（尼罗河大学）
Motion is a dominant cue in automated driving systems. Optical flow is typically computed to detect moving objects and to estimate depth using triangulation. In this paper, our motivation is to leverage the existing dense optical flow to improve the performance of semantic segmentation. To provide a systematic study, we construct four different architectures which use RGB only, flow only, RGBF concatenated and two-stream RGB + flow. We evaluate these networks on two automotive datasets namely Virtual KITTI and Cityscapes using the state-of-the-art flow estimator FlowNet v2. We also make use of…
National University of Defense Technology（国防科技大学）；College of Electronic Science and Technology, National University of Defense Technology（国防科技大学电子科学学院）
Single-frame infrared small target (SIRST) detection aims at separating small targets from clutter backgrounds. With the advances of deep learning, CNN-based methods have yielded promising results in generic object detection due to their powerful modeling capability. However, existing CNN-based methods cannot be directly applied for infrared small targets since pooling layers in their networks could lead to the loss of targets in deep layers. To handle this problem, we propose a dense nested attention network (DNANet) in this paper. Specifically, we design a dense nested interactive module (DN…
The critical challenge in tracking-by-detection framework is how to avoid drift problem during online learning, where the robust features for a variety of appearance changes are difficult to be learned and a reasonable intersection over union (IoU) threshold that defines the true/false positives is hard to set. This paper presents the TCDCaps method to address the problems above via a cascaded dense capsule architecture. To get robust features, we extend original capsules with dense-connected routing, which are referred as DCaps. Depending on the preservation of part-whole relationships in the…
In training object detector based on convolutional neural networks, selection of effective positive examples for training is an important factor. However, when training an anchor-based detectors with sparse annotations on an image, effort to find effective positive examples can hinder training performance. When using the anchor-based training for the ground truth bounding box to collect positive examples under given IoU, it is often possible to include objects from other classes in the current training class, or objects that are needed to be trained can only be sampled as negative examples. We…
Queensland University of Technology（昆士兰科技大学）；Data61, CSIRO（联邦科学与工业研究组织数据61研究所）
Monitoring coral reefs using underwater vehicles increases the range of marine surveys and availability of historical ecological data by collecting significant quantities of images. Analysis of this imagery can be automated using a model trained to perform semantic segmentation, however it is too costly and time-consuming to densely label images for training supervised models. In this letter, we leverage photo-quadrat imagery labeled by ecologists with sparse point labels. We propose a point label aware method for propagating labels within superpixel regions to obtain augmented ground truth fo…
Dense pixel-wise classification maps output by deep neural networks are of extreme importance for scene understanding. However, these maps are often partially inaccurate due to a variety of possible factors. Therefore, we propose to interactively refine them within a framework named DISCA (Deep Image Segmentation with Continual Adaptation). It consists of continually adapting a neural network to a target image using an interactive learning process with sparse user annotations as ground-truth. We show through experiments on three datasets using synthesized annotations the benefits of the approa…
Aerospace Information Research Institute, Chinese Academy of Sciences（中国科学院空天信息创新研究院）；University of Chinese Academy of Sciences（中国科学院大学）；German Aerospace Center (DLR)（德国航空航天中心）；Technical University of Munich (TUM)（慕尼黑工业大学）
Change detection is the process of identifying pixelwise differences in bitemporal co-registered images. It is of great significance to Earth observations. Recently, with the emergence of deep learning (DL), the power and feasibility of deep convolutional neural network (CNN)-based methods have been shown in the field of change detection. However, there is still a lack of effective supervision for change feature learning. In this work, a feature constraint change detection network (FCCDN) is proposed. We constrain features both in bitemporal feature extraction and feature fusion. More specific…
University of Science and Technology of China（中国科学技术大学）；Department of Computer Vision Technology (VIS), Baidu Inc., China（百度公司计算机视觉技术部（VIS））
3D object detection is an essential task in autonomous driving and robotics. Though great progress has been made, challenges remain in estimating 3D pose for distant and occluded objects. In this paper, we present a novel framework named ZoomNet for stereo imagery-based 3D detection. The pipeline of ZoomNet begins with an ordinary 2D object detection model which is used to obtain pairs of left-right bounding boxes. To further exploit the abundant texture cues in RGB images for more accurate disparity estimation, we introduce a conceptually straight-forward module -- adaptive zooming, which sim…
Shanghai Jiao Tong University（上海交通大学）；Ant Group（蚂蚁集团）；Heriot-Watt University Malaysia（赫瑞-瓦特大学马来西亚校区）
Pedestrian detection in a crowd is a challenging task due to a high number of mutually-occluding human instances, which brings ambiguity and optimization difficulties to the current IoU-based ground truth assignment procedure in classical object detection methods. In this paper, we develop a unique perspective of pedestrian detection as a variational inference problem. We formulate a novel and efficient algorithm for pedestrian detection by modeling the dense proposals as a latent variable while proposing a customized Auto Encoding Variational Bayes (AEVB) algorithm. Through the optimization o…
Time-frequency localization of bird calls in dense soundscapes
Acoustic Research Laboratory, National University of Singapore（新加坡国立大学声学研究实验室）；Tropical Marine Science Institute, National University of Singapore（新加坡国立大学热带海洋科学研究所）；School of Marine Science and Technology, Northwestern Polytechnical University（西北工业大学航海学院）
Edge detection has long been an important problem in the field of computer vision. Previous works have explored category-agnostic or category-aware edge detection. In this paper, we explore edge detection in the context of object instances. Although object boundaries could be easily derived from segmentation masks, in practice, instance segmentation models are trained to maximize IoU to the ground-truth mask, which means that segmentation boundaries are not enforced to precisely align with ground-truth edge boundaries. Thus, the task of instance edge detection itself is different and critical.…
SRIBD CUHKSZ（香港中文大学（深圳）机器人与人工智能研究院）；Bournemouth University（伯恩茅斯大学）；Technical University of Munich（慕尼黑工业大学）
Semantic scene understanding from point clouds is particularly challenging as the points reflect only a sparse set of the underlying 3D geometry. Previous works often convert point cloud into regular grids (e.g. voxels or bird-eye view images), and resort to grid-based convolutions for scene understanding. In this work, we introduce RfD-Net that jointly detects and reconstructs dense object surfaces directly from raw point clouds. Instead of representing scenes with regular grids, our method leverages the sparsity of point cloud data and focuses on predicting shapes that are recognized with hi…
Institute of Electronics, Chinese Academy of Sciences（中国科学院电子学研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Shanghai Jiao Tong University（上海交通大学）
Object detection has been a building block in computer vision. Though considerable progress has been made, there still exist challenges for objects with small size, arbitrary direction, and dense distribution. Apart from natural images, such issues are especially pronounced for aerial images of great importance. This paper presents a novel multi-category rotation detector for small, cluttered and rotated objects, namely SCRDet. Specifically, a sampling fusion network is devised which fuses multi-layer feature with effective anchor sampling, to improve the sensitivity to small objects. Meanwhil…
University of Oxford（牛津大学）；CASIA（中国科学院自动化研究所）；Five AI（Five AI公司）
Unsupervised video object segmentation has often been tackled by methods based on recurrent neural networks and optical flow. Despite their complexity, these kinds of approaches tend to favour short-term temporal dependencies and are thus prone to accumulating inaccuracies, which cause drift over time. Moreover, simple (static) image segmentation models, alone, can perform competitively against these methods, which further suggests that the way temporal dependencies are modelled should be reconsidered. Motivated by these observations, in this paper we explore simple yet effective strategies to…
In computer vision, object detection is one of most important tasks, which underpins a few instance-level recognition tasks and many downstream applications. Recently one-stage methods have gained much attention over two-stage approaches due to their simpler design and competitive performance. Here we propose a fully convolutional one-stage object detector (FCOS) to solve object detection in a per-pixel prediction fashion, analogue to other dense prediction problems such as semantic segmentation. Almost all state-of-the-art object detectors such as RetinaNet, SSD, YOLOv3, and Faster R-CNN rely…
Rotated object detection in aerial images is a meaningful yet challenging task as objects are densely arranged and have arbitrary orientations. The eight-parameter (coordinates of box vectors) methods in rotated object detection usually use ln-norm losses (L1 loss, L2 loss, and smooth L1 loss) as loss functions. As ln-norm losses are mainly based on non-scale-invariant Minkowski distance, using ln-norm losses will lead to inconsistency with the detection metric rotational Intersection-over-Union (IoU) and training instability. To address the problems, we use Mahalanobis distance to calculate l…
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；College of Information Engineering, Shanghai Maritime University（上海海事大学信息工程学院）；School of Computer Science and Technology, East China Normal University（华东师范大学计算机科学与技术学院）；School of Automation and Electrical Engineering, University of Science and Technology Beijing（北京科技大学自动化与电气工程学院）
Anchor-free detectors basically formulate object detection as dense classification and regression. For popular anchor-free detectors, it is common to introduce an individual prediction branch to estimate the quality of localization. The following inconsistencies are observed when we delve into the practices of classification and quality estimation. Firstly, for some adjacent samples which are assigned completely different labels, the trained model would produce similar classification scores. This violates the training objective and leads to performance degradation. Secondly, it is found that d…
Deep learning has led to great progress in the detection of mobile (i.e. movement-capable) objects in urban driving scenes in recent years. Supervised approaches typically require the annotation of large training sets; there has thus been great interest in leveraging weakly, semi- or self-supervised methods to avoid this, with much success. Whilst weakly and semi-supervised methods require some annotation, self-supervised methods have used cues such as motion to relieve the need for annotation altogether. However, a complete absence of annotation typically degrades their performance, and ambig…
Detection and Geographic Localization of Natural Objects in the Wild: A Case Study on Palms
Department of Mathematics, City University of Hong Kong（香港城市大学数学系）；Department of Computer Science, Xidian University（西安电子科技大学计算机学院）；Department of Biology, Wake Forest University（威克森林大学生物系）；School of Arts & Sciences, Colby-Sawyer College（科尔比-萨威学院艺术与科学学院）
DOMR: Establishing Cross-View Segmentation via Dense Object Matching
Hangzhou International Innovation Institute, Beihang University（北京航空航天大学杭州国际创新研究院）；Faculty of Science and Technology, University of Macau（澳门大学科学与技术学院）；College of Computer Science and Technology, Zhejiang University of Technology（浙江工业大学计算机科学与技术学院）；School of Artificial Intelligence, Beihang University（北京航空航天大学人工智能学院）
Zhejiang University（浙江大学）；Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）；Inception Institute of Artificial Intelligence（起源人工智能研究院）
Most of the existing single-stage and two-stage 3D object detectors are anchor-based methods, while the efficient but challenging anchor-free single-stage 3D object detection is not well investigated. Recent studies on 2D object detection show that the anchor-free methods also are of great potential. However, the unordered and sparse properties of point clouds prevent us from directly leveraging the advanced 2D methods on 3D point clouds. We overcome this by converting the voxel-based sparse 3D feature volumes into the sparse 2D feature maps. We propose an attentive module to fit the sparse fe…
A Large-Language-Model Assisted Automated Scale Bar Detection and Extraction Framework for Scanning Electron Microscopic Images
Shanghai Jiao Tong Global College（上海交通大学全球学院）；Shanghai Jiao Tong University（上海交通大学）；Global Institute of Future Technology（全球未来技术研究院）；AI Lab, Xiaomi Corporation（小米公司AI实验室）
