该报告提出以 PointRend 为基础并集成 5 个模型，解决 3D-FUTURE 中大目标的细粒度实例分割问题，在 3D AI Challenge 2020 验证与测试排行榜均获第一。
摘要：
本技术报告介绍了“FineGrainedSeg”团队在 3D AI Challenge 2020 实例分割赛道中的解决方案。为处理 3D-FUTURE 中极大的目标，我们采用 PointRend 作为基础框架；与 HTC 和 SOLOv2 相比，它能输出更细粒度的掩码。我们的最终提交方案是 5 个 PointRend 模型的集成，在验证集和测试集排行榜上均获得第一名。代码可在 https://github.com/zehuichen123/3DFuture_ins_seg 获取。
英文摘要：
This technical report introduces our solutions of Team 'FineGrainedSeg' for Instance Segmentation track in 3D AI Challenge 2020. In order to handle extremely large objects in 3D-FUTURE, we adopt PointRend as our basic framework, which outputs more fine-grained masks compared to HTC and SOLOv2. Our final submission is an ensemble of 5 PointRend models, which achieves the 1st place on both validation and test leaderboards. The code is available at https://github.com/zehuichen123/3DFuture_ins_seg.
We present a large-scale object detection system by team PFDet. Our system enables training with huge datasets using 512 GPUs, handles sparsely verified classes, and massive class imbalance. Using our method, we achieved 2nd place in the Google AI Open Images Object Detection Track 2018 on Kaggle.
TuSimple（图森未来）；Tongji University（同济大学）；Xidian University（西安电子科技大学）；Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）
In this technical report, we present our solutions of Waymo Open Dataset (WOD) Challenge 2020 - 2D Object Track. We adopt FPN as our basic framework. Cascade RCNN, stacked PAFPN Neck and Double-Head are used for performance improvements. In order to handle the small object detection problem in WOD, we use very large image scales for both training and testing. Using our methods, our team RW-TSDet achieved the 1st place in the 2D Object Detection Track.
We present an object detection framework based on PaddlePaddle. We put all the strategies together (multi-scale training, FPN, Cascade, Dcnv2, Non-local, libra loss) based on ResNet200-vd backbone. Our model score on public leaderboard comes to 0.6269 with single scale test. We proposed a new voting method called top-k voting-nms, based on the SoftNMS detection results. The voting method helps us merge all the models' results more easily and achieve 2nd place in the Google AI Open Images Object Detection Track 2019.
Hikvision Research Institute（海康威视研究院）；Zhejiang University（浙江大学）
OOD-CV challenge is an out-of-distribution generalization task. To solve this problem in object detection track, we propose a simple yet effective Generalize-then-Adapt (G&A) framework, which is composed of a two-stage domain generalization part and a one-stage domain adaptation part. The domain generalization part is implemented by a Supervised Model Pretraining stage using source data for model warm-up and a Weakly Semi-Supervised Model Pretraining stage using both source data with box-level label and auxiliary data (ImageNet-1K) with image-level label for performance boosting. The domain ad…
This report describes the winning solution to the Robust Vision Challenge (RVC) semantic segmentation track at ECCV 2022. Our method adopts the FAN-B-Hybrid model as the encoder and uses SegFormer as the segmentation framework. The model is trained on a composite dataset consisting of images from 9 datasets (ADE20K, Cityscapes, Mapillary Vistas, ScanNet, VIPER, WildDash 2, IDD, BDD, and COCO) with a simple dataset balancing strategy. All the original labels are projected to a 256-class unified label space, and the model is trained using a cross-entropy loss. Without significant hyperparameter …
Beijing University of Posts and Telecommunications（北京邮电大学）；Tomorrow Advancing Life（好未来）
This paper describes the approach we have taken in the challenge. We still adopted the two-stage scheme same as the last champion, that is, detection first and segmentation followed. We trained more powerful detector and segmentor separately. Besides, we also perform pseudo-label training on the test set, based on student-teacher framework and end-to-end transformer based object detection. The method ranks first on the 2nd Unidentified Video Objects (UVO) challenge, achieving AR@100 of 46.8, 64.7 and 32.2 in the limited data frame track, unlimited data frame track and video track respectively.
In this paper, we introduce a data-efficient instance segmentation method we used in the 2021 VIPriors Instance Segmentation Challenge. Our solution is a modified version of Swin Transformer, based on the mmdetection which is a powerful toolbox. To solve the problem of lack of data, we utilize data augmentation including random flip and multiscale training to train our model. During inference, multiscale fusion is used to boost the performance. We only use a single GPU during the whole training and testing stages. In the end, our team achieved the result of 0.366 for AP@0.50:0.95 on the test s…
2nd Place Solution for MeViS Track in CVPR 2024 PVUW Workshop: Motion Expression guided Video Segmentation
Institute of Automation, Chinese Academy of Sciences (CASIA)（中国科学院自动化研究所）；School of Artificial Intelligence, University of Chinese Academy of Sciences (UCAS)（中国科学院大学人工智能学院）；Beijing Academy of Artificial Intelligence (BAAI)（北京人工智能研究院）；University of Science and Technology Beijing (USTB)（北京科技大学）
School of Automation, Beijing Institute of Technology（北京理工大学自动化学院）
Oriented object detection in remote sensing images has made great progress in recent years. However, most of the current methods only focus on detecting targets, and cannot distinguish fine-grained objects well in complex scenes. In this technical report, we analyzed the key issues of fine-grained object recognition, and use an oriented feature alignment network (OFA-Net) to achieve high-performance fine-grained oriented object recognition in optical remote sensing images. OFA-Net achieves accurate object localization through a rotated bounding boxes refinement module. On this basis, the bound…
This report introduces the technical details of the team FuXi-Fresher for LVIS Challenge 2021. Our method focuses on the problem in following two aspects: the long-tail distribution and the segmentation quality of mask and boundary. Based on the advanced HTC instance segmentation algorithm, we connect transformer backbone(Swin-L) through composite connections inspired by CBNetv2 to enhance the baseline results. To alleviate the problem of long-tail distribution, we design a Distribution Balanced method which includes dataset balanced and loss function balaced modules. Further, we use a Mask an…
Static Segmentation by Tracking: A Label-Efficient Approach for Fine-Grained Specimen Image Segmentation
The Ohio State University（俄亥俄州立大学）；Princeton University（普林斯顿大学）；University of Maine（缅因大学）；University of Miami（迈阿密大学）；Virginia Tech（弗吉尼亚理工大学）；Duke University（杜克大学）；Rensselaer Polytechnic Institute（拉特格斯理工学院）
In this technical report, we describe our EfficientLPT architecture that won the panoptic tracking challenge in the 7th AI Driving Olympics at NeurIPS 2021. Our architecture builds upon the top-down EfficientLPS panoptic segmentation approach. EfficientLPT consists of a shared backbone with a modified EfficientNet-B5 model comprising the proximity convolution module as the encoder followed by the range-aware FPN to aggregate semantically rich range-aware multi-scale features. Subsequently, we employ two task-specific heads, the scale-invariant semantic head and hybrid task cascade with feedbac…
Ant Group（蚂蚁集团）；Northwestern Polytechnical University（西北工业大学）；Tongji University（同济大学）
The referring video object segmentation task (RVOS) aims to segment object instances in a given video referred by a language expression in all video frames. Due to the requirement of understanding cross-modal semantics within individual instances, this task is more challenging than the traditional semi-supervised video object segmentation where the ground truth object masks in the first frame are given. With the great achievement of Transformer in object detection and object segmentation, RVOS has been made remarkable progress where ReferFormer achieved the state-of-the-art performance. In thi…
DCFG: Diverse Cross-Channel Fine-Grained Feature Learning and Progressive Fusion Siamese Tracker for Thermal Infrared Target Tracking
College of Computer and Information Technology, China Three Gorges University（中国三峡大学计算机与信息学院）；Hubei Province Engineering Technology Research Center for Construction Quality Testing Equipment, China Three Gorges University（中国三峡大学湖北省建筑质量检测装备工程技术研究中心）；Wuhan College（武汉学院）
FGSGT: Saliency-Guided Siamese Network Tracker Based on Key Fine-Grained Feature Information for Thermal Infrared Target Tracking
College of Computer and Information Technology, China Three Gorges University（三峡大学计算机与信息学院）；Hubei Province Engineering Technology Research Center for Construction Quality Testing Equipment, China Three Gorges University（三峡大学湖北省建筑质量检测装备工程技术研究中心）；Nantong Institute of Technology（南通理工学院）；Wuhan College（武汉学院）
A video dataset that is designed to study fine-grained categorisation of pedestrians is introduced. Pedestrians were recorded "in-the-wild" from a moving vehicle. Annotations include bounding boxes, tracks, 14 keypoints with occlusion information and the fine-grained categories of age (5 classes), sex (2 classes), weight (3 classes) and clothing style (4 classes). There are a total of 27,454 bounding box and pose labels across 4222 tracks. This dataset is designed to train and test algorithms for fine-grained categorisation of people, it is also useful for benchmarking tracking, detection and …
This is our second-place solution for CVPR 2022 SoccerNet Tracking Challenge. Our method mainly includes two steps: online short-term tracking using our Cascaded Buffer-IoU (C-BIoU) Tracker, and, offline long-term tracking using appearance feature and hierarchical clustering. At each step, online tracking yielded HOTA scores near 90, and offline tracking further improved HOTA scores to around 93.2.
Huazhong Univerisity of Science and Technology（华中科技大学）
Discriminative representation is essential to keep a unique identifier for each target in Multiple object tracking (MOT). Some recent MOT methods extract features of the bounding box region or the center point as identity embeddings. However, when targets are occluded, these coarse-grained global representations become unreliable. To this end, we propose exploring diverse fine-grained representation, which describes appearance comprehensively from global and local perspectives. This fine-grained representation requires high feature resolution and precise semantic information. To effectively al…
Towards an Effective Action-Region Tracking Framework for Fine-grained Video Action Recognition
DUT-RU International School of Information Science & Engineering, Dalian University of Technology, China（大连理工大学国际信息科学与工程学院，大连理工大学，中国）；Beihang University, China（北京航空航天大学，中国）；The University of Sydney, Australia（悉尼大学，澳大利亚）
This technical report presents the online and real-time 2D and 3D multi-object tracking (MOT) algorithms that reached the 1st places on both Waymo Open Dataset 2D tracking and 3D tracking challenges. An efficient and pragmatic online tracking-by-detection framework named HorizonMOT is proposed for camera-based 2D tracking in the image space and LiDAR-based 3D tracking in the 3D world space. Within the tracking-by-detection paradigm, our trackers leverage our high-performing detectors used in the 2D/3D detection challenges and achieved 45.13% 2D MOTA/L2 and 63.45% 3D MOTA/L2 in the 2D/3D tracki…
We present our 1st place solution to the Group Dance Multiple People Tracking Challenge. Based on MOTR: End-to-End Multiple-Object Tracking with Transformer, we explore: 1) detect queries as anchors, 2) tracking as query denoising, 3) joint training on pseudo video clips generated from CrowdHuman dataset, and 4) using the YOLOX detection proposals for the anchor initialization of detect queries. Our method achieves 73.4% HOTA on the DanceTrack test set, surpassing the second-place solution by +6.8% HOTA.
This paper presents the 2nd place solution to the Facebook AI Image Similarity Challenge : Matching Track on DrivenData. The solution is based on self-supervised learning, and Vision Transformer(ViT). The main breaktrough comes from concatenating query and reference image to form as one image and asking ViT to directly predict from the image if query image used reference image. The solution scored 0.8291 Micro-average Precision on the private leaderboard.
This is our 2nd-place solution for the ECCV 2022 Multiple People Tracking in Group Dance Challenge. Our method mainly includes two steps: online short-term tracking using our Cascaded Buffer-IoU (C-BIoU) Tracker, and, offline long-term tracking using appearance feature and hierarchical clustering. Our C-BIoU tracker adds buffers to expand the matching space of detections and tracks, which mitigates the effect of irregular motions in two aspects: one is to directly match identical but non-overlapping detections and tracks in adjacent frames, and the other is to compensate for the motion estimat…
Establishing visual correspondence across images is a challenging and essential task. Recently, an influx of self-supervised methods have been proposed to better learn representations for visual correspondence. However, we find that these methods often fail to leverage semantic information and over-rely on the matching of low-level features. In contrast, human vision is capable of distinguishing between distinct objects as a pretext to tracking. Inspired by this paradigm, we propose to learn semantic-aware fine-grained correspondence. Firstly, we demonstrate that semantic correspondence is imp…
Huazhong University of Science and Technology（华中科技大学）；Peking University（北京大学）；Wangxuan Institute of Computer Technology（王选计算机研究所）
Temporal sentence grounding (TSG) aims to localize the temporal segment which is semantically aligned with a natural language query in an untrimmed video.Most existing methods extract frame-grained features or object-grained features by 3D ConvNet or detection network under a conventional TSG framework, failing to capture the subtle differences between frames or to model the spatio-temporal behavior of core persons/objects. In this paper, we introduce a new perspective to address the TSG task by tracking pivotal objects and activities to learn more fine-grained spatio-temporal behaviors. Speci…
Development of a Realistic Crowd Simulation Environment for Fine-grained Validation of People Tracking Methods
Silesian University of Technology（西里西亚工业大学）；Institute of Information Science and Technologies, National Research Council（国家研究委员会信息科学与技术研究所）；QSystems.pro sp. z o.o.（QSystems.pro有限责任公司）；Blees sp. z o.o.（Blees有限责任公司）；Silesian University（西里西亚大学）
本文基于 Unity 3D 开发人群仿真扩展 CrowdSim2，通过增强环境、天气、交通和智能体运动真实性生成数据集，并利用 IOU-Tracker、Deep-Sort 与 Deep-TAMA 验证其用于人员跟踪算法评估的可用性。
We extend the classical tracking-by-detection paradigm to this tracking-any-object task. Solid detection results are first extracted from TAO dataset. Some state-of-the-art techniques like \textbf{BA}lanced-\textbf{G}roup \textbf{S}oftmax (\textbf{BAGS}\cite{li2020overcoming}) and DetectoRS\cite{qiao2020detectors} are integrated during detection. Then we learned appearance features to represent any object by training feature learning networks. We ensemble several models for improving detection and feature representation. Simple linking strategies with most similar appearance features and track…
APRIL-GAN: A Zero-/Few-Shot Anomaly Classification and Segmentation Method for CVPR 2023 VAND Workshop Challenge Tracks 1&2: 1st Place on Zero-shot AD and 4th Place on Few-shot AD
Adapting SAM 2 for Visual Object Tracking: 1st Place Solution for MMVPR Challenge Multi-Modal Tracking
University of Washington（华盛顿大学）；Electronics and Telecommunications Research Institute（电子电信研究所）；National Center for High-performance Computing（高性能计算国家中心）
In this technical report, we present our solution to localize a spatio-temporal person in an untrimmed video based on a sentence. We achieve the second vIOU(0.30025) in the HC-STVG track of the 3rd Person in Context(PIC) Challenge. Our solution contains three parts: 1) human attributes information is extracted from the sentence, it is helpful to filter out tube proposals in the testing phase and supervise our classifier to learn appearance information in the training phase. 2) we detect humans with YoloV5 and track humans based on the DeepSort framework but replace the original ReID network wi…
ICME 2026 Grand Challenge on Cross-Scenario Defect Detection and Fine-Grained Severity Grading for High-Precision Manufacturing
East China Normal University（华东师范大学）；Shanghai Jiao Tong University（上海交通大学）；Tsinghua Shenzhen International Graduate School（清华大学深圳国际研究生院）；Université de Nantes（南特大学）
Harbin Institute of Technology（哈尔滨工业大学）；Peng Cheng Laboratory（鹏城实验室）；Shenzhen Institute of Information Technology（深圳信息职业技术学院）
Existing deep Thermal InfraRed (TIR) trackers usually use the feature models of RGB trackers for representation. However, these feature models learned on RGB images are neither effective in representing TIR objects nor taking fine-grained TIR information into consideration. To this end, we develop a multi-task framework to learn the TIR-specific discriminative features and fine-grained correlation features for TIR tracking. Specifically, we first use an auxiliary classification network to guide the generation of TIR-specific discriminative features for distinguishing the TIR objects belonging …
We present a domain adaptation (DA) system that can be used in multi-source and semi-supervised settings. Using the proposed method we achieved 2nd place on multi-source track and 3rd place on semi-supervised track of the VisDA 2019 challenge (http://ai.bu.edu/visda-2019/). The source code of the method is available at https://github.com/filaPro/visda2019.
How Texts Help? A Fine-grained Evaluation to Reveal the Role of Language in Vision-Language Tracking
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；School of Computer Science and Technology, University of Chinese Academy of Sciences（中国科学院大学计算机科学与技术学院）；CAS Center for Excellence in Brain Science and Intelligence Technology（中国科学院脑科学与智能技术卓越创新中心）；School of Physical and Mathematical Sciences, Nanyang Technological University（南洋理工大学物理与数学科学学院）
We present our solutions to the Google Landmark Challenges 2021, for both the retrieval and the recognition tracks. Both solutions are ensembles of transformers and ConvNet models based on Sub-center ArcFace with dynamic margins. Since the two tracks share the same training data, we used the same pipeline and training approach, but with different model selections for the ensemble and different post-processing. The key improvement over last year is newer state-of-the-art vision architectures, especially transformers which significantly outperform ConvNets for the retrieval task. We finished thi…
University of Oulu（奥卢大学）；Delft University of Technology（代尔夫特理工大学）
To address the problem of training on small datasets for action recognition tasks, most prior works are either based on a large number of training samples or require pre-trained models transferred from other large datasets to tackle overfitting problems. However, it limits the research within organizations that have strong computational abilities. In this work, we try to propose a data-efficient framework that can train the model from scratch on small datasets while achieving promising results. Specifically, by introducing a 3D central difference convolution operation, we proposed a novel C3D …
