2022-11-30 更新
QDTrack: Quasi-Dense Similarity Learning for Appearance-Only Multiple Object Tracking
Authors:Tobias Fischer, Jiangmiao Pang, Thomas E. Huang, Linlu Qiu, Haofeng Chen, Trevor Darrell, Fisher Yu
Similarity learning has been recognized as a crucial step for object tracking. However, existing multiple object tracking methods only use sparse ground truth matching as the training objective, while ignoring the majority of the informative regions in images. In this paper, we present Quasi-Dense Similarity Learning, which densely samples hundreds of object regions on a pair of images for contrastive learning. We combine this similarity learning with multiple existing object detectors to build Quasi-Dense Tracking (QDTrack), which does not require displacement regression or motion priors. We find that the resulting distinctive feature space admits a simple nearest neighbor search at inference time for object association. In addition, we show that our similarity learning scheme is not limited to video data, but can learn effective instance similarity even from static input, enabling a competitive tracking performance without training on videos or using tracking supervision. We conduct extensive experiments on a wide variety of popular MOT benchmarks. We find that, despite its simplicity, QDTrack rivals the performance of state-of-the-art tracking methods on all benchmarks and sets a new state-of-the-art on the large-scale BDD100K MOT benchmark, while introducing negligible computational overhead to the detector.
PDF
点此查看论文截图
AVisT: A Benchmark for Visual Object Tracking in Adverse Visibility
Authors:Mubashir Noman, Wafa Al Ghallabi, Daniya Najiha, Christoph Mayer, Akshay Dudhane, Martin Danelljan, Hisham Cholakkal, Salman Khan, Luc Van Gool, Fahad Shahbaz Khan
One of the key factors behind the recent success in visual tracking is the availability of dedicated benchmarks. While being greatly benefiting to the tracking research, existing benchmarks do not pose the same difficulty as before with recent trackers achieving higher performance mainly due to (i) the introduction of more sophisticated transformers-based methods and (ii) the lack of diverse scenarios with adverse visibility such as, severe weather conditions, camouflage and imaging effects. We introduce AVisT, a dedicated benchmark for visual tracking in diverse scenarios with adverse visibility. AVisT comprises 120 challenging sequences with 80k annotated frames, spanning 18 diverse scenarios broadly grouped into five attributes with 42 object categories. The key contribution of AVisT is diverse and challenging scenarios covering severe weather conditions such as, dense fog, heavy rain and sandstorm; obstruction effects including, fire, sun glare and splashing water; adverse imaging effects such as, low-light; target effects including, small targets and distractor objects along with camouflage. We further benchmark 17 popular and recent trackers on AVisT with detailed analysis of their tracking performance across attributes, demonstrating a big room for improvement in performance. We believe that AVisT can greatly benefit the tracking community by complementing the existing benchmarks, in developing new creative tracking solutions in order to continue pushing the boundaries of the state-of-the-art. Our dataset along with the complete tracking performance evaluation is available at: https://github.com/visionml/pytracking
PDF
点此查看论文截图
Analysis of Training Object Detection Models with Synthetic Data
Authors:Bram Vanherle, Steven Moonen, Frank Van Reeth, Nick Michiels
Recently, the use of synthetic training data has been on the rise as it offers correctly labelled datasets at a lower cost. The downside of this technique is that the so-called domain gap between the real target images and synthetic training data leads to a decrease in performance. In this paper, we attempt to provide a holistic overview of how to use synthetic data for object detection. We analyse aspects of generating the data as well as techniques used to train the models. We do so by devising a number of experiments, training models on the Dataset of Industrial Metal Objects (DIMO). This dataset contains both real and synthetic images. The synthetic part has different subsets that are either exact synthetic copies of the real data or are copies with certain aspects randomised. This allows us to analyse what types of variation are good for synthetic training data and which aspects should be modelled to closely match the target data. Furthermore, we investigate what types of training techniques are beneficial towards generalisation to real data, and how to use them. Additionally, we analyse how real images can be leveraged when training on synthetic images. All these experiments are validated on real data and benchmarked to models trained on real data. The results offer a number of interesting takeaways that can serve as basic guidelines for using synthetic data for object detection. Code to reproduce results is available at https://github.com/EDM-Research/DIMO_ObjectDetection.
PDF published in BMVC 2022, https://bmvc2022.mpi-inf.mpg.de/833/
点此查看论文截图
Bridging the Gap between Object and Image-level Representations for Open-Vocabulary Detection
Authors:Hanoona Rasheed, Muhammad Maaz, Muhammad Uzair Khattak, Salman Khan, Fahad Shahbaz Khan
Existing open-vocabulary object detectors typically enlarge their vocabulary sizes by leveraging different forms of weak supervision. This helps generalize to novel objects at inference. Two popular forms of weak-supervision used in open-vocabulary detection (OVD) include pretrained CLIP model and image-level supervision. We note that both these modes of supervision are not optimally aligned for the detection task: CLIP is trained with image-text pairs and lacks precise localization of objects while the image-level supervision has been used with heuristics that do not accurately specify local object regions. In this work, we propose to address this problem by performing object-centric alignment of the language embeddings from the CLIP model. Furthermore, we visually ground the objects with only image-level supervision using a pseudo-labeling process that provides high-quality object proposals and helps expand the vocabulary during training. We establish a bridge between the above two object-alignment strategies via a novel weight transfer function that aggregates their complimentary strengths. In essence, the proposed model seeks to minimize the gap between object and image-centric representations in the OVD setting. On the COCO benchmark, our proposed approach achieves 36.6 AP50 on novel classes, an absolute 8.2 gain over the previous best performance. For LVIS, we surpass the state-of-the-art ViLD model by 5.0 mask AP for rare categories and 3.4 overall. Code: https://github.com/hanoonaR/object-centric-ovd.
PDF Accepted at NeurIPS 2022
点此查看论文截图
HVC-Net: Unifying Homography, Visibility, and Confidence Learning for Planar Object Tracking
Authors:Haoxian Zhang, Yonggen Ling
Robust and accurate planar tracking over a whole video sequence is vitally important for many vision applications. The key to planar object tracking is to find object correspondences, modeled by homography, between the reference image and the tracked image. Existing methods tend to obtain wrong correspondences with changing appearance variations, camera-object relative motions and occlusions. To alleviate this problem, we present a unified convolutional neural network (CNN) model that jointly considers homography, visibility, and confidence. First, we introduce correlation blocks that explicitly account for the local appearance changes and camera-object relative motions as the base of our model. Second, we jointly learn the homography and visibility that links camera-object relative motions with occlusions. Third, we propose a confidence module that actively monitors the estimation quality from the pixel correlation distributions obtained in correlation blocks. All these modules are plugged into a Lucas-Kanade (LK) tracking pipeline to obtain both accurate and robust planar object tracking. Our approach outperforms the state-of-the-art methods on public POT and TMT datasets. Its superior performance is also verified on a real-world application, synthesizing high-quality in-video advertisements.
PDF Accepted to ECCV 2022
点此查看论文截图
Learning Equivariant Segmentation with Instance-Unique Querying
Authors:Wenguan Wang, James Liang, Dongfang Liu
Prevalent state-of-the-art instance segmentation methods fall into a query-based scheme, in which instance masks are derived by querying the image feature using a set of instance-aware embeddings. In this work, we devise a new training framework that boosts query-based models through discriminative query embedding learning. It explores two essential properties, namely dataset-level uniqueness and transformation equivariance, of the relation between queries and instances. First, our algorithm uses the queries to retrieve the corresponding instances from the whole training dataset, instead of only searching within individual scenes. As querying instances across scenes is more challenging, the segmenters are forced to learn more discriminative queries for effective instance separation. Second, our algorithm encourages both image (instance) representations and queries to be equivariant against geometric transformations, leading to more robust, instance-query matching. On top of four famous, query-based models ($i.e.,$ CondInst, SOLOv2, SOTR, and Mask2Former), our training algorithm provides significant performance gains ($e.g.,$ +1.6 - 3.2 AP) on COCO dataset. In addition, our algorithm promotes the performance of SOLOv2 by 2.7 AP, on LVISv1 dataset.
PDF Accepted to NeurIPS 2022; Code: https://github.com/JamesLiang819/Instance_Unique_Querying
点此查看论文截图
TransCenter: Transformers with Dense Representations for Multiple-Object Tracking
Authors:Yihong Xu, Yutong Ban, Guillaume Delorme, Chuang Gan, Daniela Rus, Xavier Alameda-Pineda
Transformers have proven superior performance for a wide variety of tasks since they were introduced. In recent years, they have drawn attention from the vision community in tasks such as image classification and object detection. Despite this wave, an accurate and efficient multiple-object tracking (MOT) method based on transformers is yet to be designed. We argue that the direct application of a transformer architecture with quadratic complexity and insufficient noise-initialized sparse queries - is not optimal for MOT. We propose TransCenter, a transformer-based MOT architecture with dense representations for accurately tracking all the objects while keeping a reasonable runtime. Methodologically, we propose the use of image-related dense detection queries and efficient sparse tracking queries produced by our carefully designed query learning networks (QLN). On one hand, the dense image-related detection queries allow us to infer targets’ locations globally and robustly through dense heatmap outputs. On the other hand, the set of sparse tracking queries efficiently interacts with image features in our TransCenter Decoder to associate object positions through time. As a result, TransCenter exhibits remarkable performance improvements and outperforms by a large margin the current state-of-the-art methods in two standard MOT benchmarks with two tracking settings (public/private). TransCenter is also proven efficient and accurate by an extensive ablation study and comparisons to more naive alternatives and concurrent works. For scientific interest, the code is made publicly available at https://github.com/yihongxu/transcenter.
PDF 17 pages, 10 figures, updated results and add comparisons
点此查看论文截图
From Forks to Forceps: A New Framework for Instance Segmentation of Surgical Instruments
Authors:Britty Baby, Daksh Thapar, Mustafa Chasmai, Tamajit Banerjee, Kunal Dargan, Ashish Suri, Subhashis Banerjee, Chetan Arora
Minimally invasive surgeries and related applications demand surgical tool classification and segmentation at the instance level. Surgical tools are similar in appearance and are long, thin, and handled at an angle. The fine-tuning of state-of-the-art (SOTA) instance segmentation models trained on natural images for instrument segmentation has difficulty discriminating instrument classes. Our research demonstrates that while the bounding box and segmentation mask are often accurate, the classification head mis-classifies the class label of the surgical instrument. We present a new neural network framework that adds a classification module as a new stage to existing instance segmentation models. This module specializes in improving the classification of instrument masks generated by the existing model. The module comprises multi-scale mask attention, which attends to the instrument region and masks the distracting background features. We propose training our classifier module using metric learning with arc loss to handle low inter-class variance of surgical instruments. We conduct exhaustive experiments on the benchmark datasets EndoVis2017 and EndoVis2018. We demonstrate that our method outperforms all (more than 18) SOTA methods compared with, and improves the SOTA performance by at least 12 points (20%) on the EndoVis2017 benchmark challenge and generalizes effectively across the datasets.
PDF WACV 2023
点此查看论文截图
MGTUNet: An new UNet for colon nuclei instance segmentation and quantification
Authors:Liangrui Pan, Lian Wang, Mingting Liu, Zhujun Xu, Liwen Xu, Shaoliang Peng
Colorectal cancer (CRC) is among the top three malignant tumor types in terms of morbidity and mortality. Histopathological images are the gold standard for diagnosing colon cancer. Cellular nuclei instance segmentation and classification, and nuclear component regression tasks can aid in the analysis of the tumor microenvironment in colon tissue. Traditional methods are still unable to handle both types of tasks end-to-end at the same time, and have poor prediction accuracy and high application costs. This paper proposes a new UNet model for handling nuclei based on the UNet framework, called MGTUNet, which uses Mish, Group normalization and transposed convolution layer to improve the segmentation model, and a ranger optimizer to adjust the SmoothL1Loss values. Secondly, it uses different channels to segment and classify different types of nucleus, ultimately completing the nuclei instance segmentation and classification task, and the nuclei component regression task simultaneously. Finally, we did extensive comparison experiments using eight segmentation models. By comparing the three evaluation metrics and the parameter sizes of the models, MGTUNet obtained 0.6254 on PQ, 0.6359 on mPQ, and 0.8695 on R2. Thus, the experiments demonstrated that MGTUNet is now a state-of-the-art method for quantifying histopathological images of colon cancer.
PDF Accepted in BIBM2022(regular paper)
点此查看论文截图
A Flexible-Frame-Rate Vision-Aided Inertial Object Tracking System for Mobile Devices
Authors:Yo-Chung Lau, Kuan-Wei Tseng, I-Ju Hsieh, Hsiao-Ching Tseng, Yi-Ping Hung
Real-time object pose estimation and tracking is challenging but essential for emerging augmented reality (AR) applications. In general, state-of-the-art methods address this problem using deep neural networks which indeed yield satisfactory results. Nevertheless, the high computational cost of these methods makes them unsuitable for mobile devices where real-world applications usually take place. In addition, head-mounted displays such as AR glasses require at least 90~FPS to avoid motion sickness, which further complicates the problem. We propose a flexible-frame-rate object pose estimation and tracking system for mobile devices. It is a monocular visual-inertial-based system with a client-server architecture. Inertial measurement unit (IMU) pose propagation is performed on the client side for high speed tracking, and RGB image-based 3D pose estimation is performed on the server side to obtain accurate poses, after which the pose is sent to the client side for visual-inertial fusion, where we propose a bias self-correction mechanism to reduce drift. We also propose a pose inspection algorithm to detect tracking failures and incorrect pose estimation. Connected by high-speed networking, our system supports flexible frame rates up to 120 FPS and guarantees high precision and real-time tracking on low-end devices. Both simulations and real world experiments show that our method achieves accurate and robust object tracking.
PDF
点此查看论文截图
Single-Stage Open-world Instance Segmentation with Cross-task Consistency Regularization
Authors:Xizhe Xue, Dongdong Yu, Lingqiao Liu, Yu Liu, Satoshi Tsutsui, Ying Li, Zehuan Yuan, Ping Song, Mike Zheng Shou
Open-World Instance Segmentation (OWIS) is an emerging research topic that aims to segment class-agnostic object instances from images. The mainstream approaches use a two-stage segmentation framework, which first locates the candidate object bounding boxes and then performs instance segmentation. In this work, we instead promote a single-stage framework for OWIS. We argue that the end-to-end training process in the single-stage framework can be more convenient for directly regularizing the localization of class-agnostic object pixels. Based on the single-stage instance segmentation framework, we propose a regularization model to predict foreground pixels and use its relation to instance segmentation to construct a cross-task consistency loss. We show that such a consistency loss could alleviate the problem of incomplete instance annotation — a common problem in the existing OWIS datasets. We also show that the proposed loss lends itself to an effective solution to semi-supervised OWIS that could be considered an extreme case that all object annotations are absent for some images. Our extensive experiments demonstrate that the proposed method achieves impressive results in both fully-supervised and semi-supervised settings. Compared to SOTA methods, the proposed method significantly improves the $AP_{100}$ score by 4.75\% in UVO$\rightarrow$UVO setting and 4.05\% in COCO$\rightarrow$UVO setting. In the case of semi-supervised learning, our model learned with only 30\% labeled data, even outperforms its fully-supervised counterpart with 50\% labeled data. The code will be released soon.
PDF
点此查看论文截图
Learning with Free Object Segments for Long-Tailed Instance Segmentation
Authors:Cheng Zhang, Tai-Yu Pan, Tianle Chen, Jike Zhong, Wenjin Fu, Wei-Lun Chao
One fundamental challenge in building an instance segmentation model for a large number of classes in complex scenes is the lack of training examples, especially for rare objects. In this paper, we explore the possibility to increase the training examples without laborious data collection and annotation. We find that an abundance of instance segments can potentially be obtained freely from object-centric images, according to two insights: (i) an object-centric image usually contains one salient object in a simple background; (ii) objects from the same class often share similar appearances or similar contrasts to the background. Motivated by these insights, we propose a simple and scalable framework FreeSeg for extracting and leveraging these “free” object foreground segments to facilitate model training in long-tailed instance segmentation. Concretely, we investigate the similarity among object-centric images of the same class to propose candidate segments of foreground instances, followed by a novel ranking of segment quality. The resulting high-quality object segments can then be used to augment the existing long-tailed datasets, e.g., by copying and pasting the segments onto the original training images. Extensive experiments show that FreeSeg yields substantial improvements on top of strong baselines and achieves state-of-the-art accuracy for segmenting rare object categories.
PDF Accepted to ECCV 2022
点此查看论文截图
Rectifying Open-set Object Detection: A Taxonomy, Practical Applications, and Proper Evaluation
Authors:Yusuke Hosoya, Masanori Suganuma, Takayuki Okatani
Open-set object detection (OSOD) has recently gained attention. It is to detect unknown objects while correctly detecting known objects. In this paper, we first point out that the recent studies’ formalization of OSOD, which generalizes open-set recognition (OSR) and thus considers an unlimited variety of unknown objects, has a fundamental issue. This issue emerges from the difference between image classification and object detection, making it hard to evaluate OSOD methods’ performance properly. We then introduce a novel scenario of OSOD, which considers known and unknown classes within a specified super-class of object classes. This new scenario has practical applications and is free from the above issue, enabling proper evaluation of OSOD performance and probably making the problem more manageable. Finally, we experimentally evaluate existing OSOD methods with the new scenario using multiple datasets, showing that the current state-of-the-art OSOD methods attain limited performance similar to a simple baseline method. The paper also presents a taxonomy of OSOD that clarifies different problem formalizations. We hope our study helps the community reconsider OSOD problems and progress in the right direction.
PDF 17 pages, 7 figures
点此查看论文截图
Mask3D for 3D Semantic Instance Segmentation
Authors:Jonas Schult, Francis Engelmann, Alexander Hermans, Or Litany, Siyu Tang, Bastian Leibe
Modern 3D semantic instance segmentation approaches predominantly rely on specialized voting mechanisms followed by carefully designed geometric clustering techniques. Building on the successes of recent Transformer-based methods for object detection and image segmentation, we propose the first Transformer-based approach for 3D semantic instance segmentation. We show that we can leverage generic Transformer building blocks to directly predict instance masks from 3D point clouds. In our model called Mask3D each object instance is represented as an instance query. Using Transformer decoders, the instance queries are learned by iteratively attending to point cloud features at multiple scales. Combined with point features, the instance queries directly yield all instance masks in parallel. Mask3D has several advantages over current state-of-the-art approaches, since it neither relies on (1) voting schemes which require hand-selected geometric properties (such as centers) nor (2) geometric grouping mechanisms requiring manually-tuned hyper-parameters (e.g. radii) and (3) enables a loss that directly optimizes instance masks. Mask3D sets a new state-of-the-art on ScanNet test (+6.2 mAP), S3DIS 6-fold (+10.1 mAP), STPLS3D (+11.2 mAP) and ScanNet200 test (+12.4 mAP).
PDF
点此查看论文截图
Instance Segmentation of Dense and Overlapping Objects via Layering
Authors:Long Chen, Yuli Wu, Dorit Merhof
Instance segmentation aims to delineate each individual object of interest in an image. State-of-the-art approaches achieve this goal by either partitioning semantic segmentations or refining coarse representations of detected objects. In this work, we propose a novel approach to solve the problem via object layering, i.e. by distributing crowded, even overlapping objects into different layers. By grouping spatially separated objects in the same layer, instances can be effortlessly isolated by extracting connected components in each layer. In comparison to previous methods, our approach is not affected by complex object shapes or object overlaps. With minimal post-processing, our method yields very competitive results on a diverse line of datasets: C. elegans (BBBC), Overlapping Cervical Cells (OCC) and cultured neuroblastoma cells (CCDB). The source code is publicly available.
PDF
点此查看论文截图
Hierarchical Instance Mixing across Domains in Aerial Segmentation
Authors:Edoardo Arnaudo, Antonio Tavera, Fabrizio Dominici, Carlo Masone, Barbara Caputo
We investigate the task of unsupervised domain adaptation in aerial semantic segmentation and discover that the current state-of-the-art algorithms designed for autonomous driving based on domain mixing do not translate well to the aerial setting. This is due to two factors: (i) a large disparity in the extension of the semantic categories, which causes a domain imbalance in the mixed image, and (ii) a weaker structural consistency in aerial scenes than in driving scenes since the same scene might be viewed from different perspectives and there is no well-defined and repeatable structure of the semantic elements in the images. Our solution to these problems is composed of: (i) a new mixing strategy for aerial segmentation across domains called Hierarchical Instance Mixing (HIMix), which extracts a set of connected components from each semantic mask and mixes them according to a semantic hierarchy and, (ii) a twin-head architecture in which two separate segmentation heads are fed with variations of the same images in a contrastive fashion to produce finer segmentation maps. We conduct extensive experiments on the LoveDA benchmark, where our solution outperforms the current state-of-the-art.
PDF
点此查看论文截图
VITA: Video Instance Segmentation via Object Token Association
Authors:Miran Heo, Sukjun Hwang, Seoung Wug Oh, Joon-Young Lee, Seon Joo Kim
We introduce a novel paradigm for offline Video Instance Segmentation (VIS), based on the hypothesis that explicit object-oriented information can be a strong clue for understanding the context of the entire sequence. To this end, we propose VITA, a simple structure built on top of an off-the-shelf Transformer-based image instance segmentation model. Specifically, we use an image object detector as a means of distilling object-specific contexts into object tokens. VITA accomplishes video-level understanding by associating frame-level object tokens without using spatio-temporal backbone features. By effectively building relationships between objects using the condensed information, VITA achieves the state-of-the-art on VIS benchmarks with a ResNet-50 backbone: 49.8 AP, 45.7 AP on YouTube-VIS 2019 & 2021, and 19.6 AP on OVIS. Moreover, thanks to its object token-based structure that is disjoint from the backbone features, VITA shows several practical advantages that previous offline VIS methods have not explored - handling long and high-resolution videos with a common GPU, and freezing a frame-level detector trained on image domain. Code is available at https://github.com/sukjunhwang/VITA.
PDF
点此查看论文截图