Open-vocabulary scene understanding aims to localize and recognize unseen categories beyond the annotated label space. The recent breakthrough of 2D open-vocabulary perception is largely driven by Internet-scale paired image-text data with rich vocabulary concepts. However, this success cannot be directly transferred to 3D scenarios due to the inaccessibility of large-scale 3D-text pairs. To this end, we propose to distill knowledge encoded in pre-trained vision-language (VL) foundation models through captioning multi-view images from 3D, which allows explicitly associating 3D and semantic-rich captions. Further, to foster coarse-to-fine visual-semantic representation learning from captions, we design hierarchical 3D-caption pairs, leveraging geometric constraints between 3D scenes and multi-view images. Finally, by employing contrastive learning, the model learns language-aware embeddings that connect 3D and text for open-vocabulary tasks. Our method not only remarkably outperforms baseline methods by 25.8% $\sim$ 44.7% hIoU and 14.5% $\sim$ 50.4% hAP$_{50}$ in open-vocabulary semantic and instance segmentation, but also shows robust transferability on challenging zero-shot domain transfer tasks. See the project website at https://dingry.github.io/projects/PLA.
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.
Various research domains use machine learning approaches because they can solve complex tasks by learning from data. Deploying machine learning models, however, is not trivial and developers have to implement complete solutions which are often installed locally and include Graphical User Interfaces (GUIs). Distributing software to various users on-site has several problems. Therefore, we propose a concept to deploy software in the cloud. There are several frameworks available based on Representational State Transfer (REST) which can be used to implement cloud-based machine learning services. However, machine learning services for scientific users have special requirements that state-of-the-art REST frameworks do not cover completely. We contribute an EasyMLServe software framework to deploy machine learning services in the cloud using REST interfaces and generic local or web-based GUIs. Furthermore, we apply our framework on two real-world applications, \ie, energy time-series forecasting and cell instance segmentation. The EasyMLServe framework and the use cases are available on GitHub.
Considering the spectral properties of images, we propose a new self-attention mechanism with highly reduced computational complexity, up to a linear rate. To better preserve edges while promoting similarity within objects, we propose individualized processes over different frequency bands. In particular, we study a case where the process is merely over low-frequency components. By ablation study, we show that low frequency self-attention can achieve very close or better performance relative to full frequency even without retraining the network. Accordingly, we design and embed novel plug-and-play modules to the head of a CNN network that we refer to as FsaNet. The frequency self-attention 1) requires only a few low frequency coefficients as input, 2) can be mathematically equivalent to spatial domain self-attention with linear structures, 3) simplifies token mapping ($1\times1$ convolution) stage and token mixing stage simultaneously. We show that frequency self-attention requires $87.29\% \sim 90.04\%$ less memory, $96.13\% \sim 98.07\%$ less FLOPs, and $97.56\% \sim 98.18\%$ in run time than the regular self-attention. Compared to other ResNet101-based self-attention networks, \ourM achieves a new \sArt result ($83.0\%$ mIoU) on Cityscape test dataset and competitive results on ADE20k and VOCaug. \ourM can also enhance MASK R-CNN for instance segmentation on COCO. In addition, utilizing the proposed module, Segformer can be boosted on a series of models with different scales, and Segformer-B5 can be improved even without retraining. Code is accessible at \url{https://github.com/zfy-csu/FsaNet
Various state-of-the-art self-supervised visual representation learning approaches take advantage of data from multiple sensors by aligning the feature representations across views and/or modalities. In this work, we investigate how aligning representations affects the visual features obtained from cross-view and cross-modal contrastive learning on images and point clouds. On five real-world datasets and on five tasks, we train and evaluate 108 models based on four pretraining variations. We find that cross-modal representation alignment discards complementary visual information, such as color and texture, and instead emphasizes redundant depth cues. The depth cues obtained from pretraining improve downstream depth prediction performance. Also overall, cross-modal alignment leads to more robust encoders than pre-training by cross-view alignment, especially on depth prediction, instance segmentation, and object detection.
Scoliosis is a three-dimensional deformity of the spine, most often diagnosed in childhood. It affects 2-3% of the population, which is approximately seven million people in North America. Currently, the reference standard for assessing scoliosis is based on the manual assignment of Cobb angles at the site of the curvature center. This manual process is time consuming and unreliable as it is affected by inter- and intra-observer variance. To overcome these inaccuracies, machine learning (ML) methods can be used to automate the Cobb angle measurement process. This paper proposes to address the Cobb angle measurement task using YOLACT, an instance segmentation model. The proposed method first segments the vertebrae in an X-Ray image using YOLACT, then it tracks the important landmarks using the minimum bounding box approach. Lastly, the extracted landmarks are used to calculate the corresponding Cobb angles. The model achieved a Symmetric Mean Absolute Percentage Error (SMAPE) score of 10.76%, demonstrating the reliability of this process in both vertebra localization and Cobb angle measurement.
Learning descriptive 3D features is crucial for understanding 3D scenes with diverse objects and complex structures. However, it is usually unknown whether important geometric attributes and scene context obtain enough emphasis in an end-to-end trained 3D scene understanding network. To guide 3D feature learning toward important geometric attributes and scene context, we explore the help of textual scene descriptions. Given some free-form descriptions paired with 3D scenes, we extract the knowledge regarding the object relationships and object attributes. We then inject the knowledge to 3D feature learning through three classification-based auxiliary tasks. This language-assisted training can be combined with modern object detection and instance segmentation methods to promote 3D semantic scene understanding, especially in a label-deficient regime. Moreover, the 3D feature learned with language assistance is better aligned with the language features, which can benefit various 3D-language multimodal tasks. Experiments on several benchmarks of 3D-only and 3D-language tasks demonstrate the effectiveness of our language-assisted 3D feature learning. Code is available at https://github.com/Asterisci/Language-Assisted-3D.
In this paper, we consider the instance segmentation task on a long-tailed dataset, which contains label noise, i.e., some of the annotations are incorrect. There are two main reasons making this case realistic. First, datasets collected from real world usually obey a long-tailed distribution. Second, for instance segmentation datasets, as there are many instances in one image and some of them are tiny, it is easier to introduce noise into the annotations. Specifically, we propose a new dataset, which is a large vocabulary long-tailed dataset containing label noise for instance segmentation. Furthermore, we evaluate previous proposed instance segmentation algorithms on this dataset. The results indicate that the noise in the training dataset will hamper the model in learning rare categories and decrease the overall performance, and inspire us to explore more effective approaches to address this practical challenge. The code and dataset are available in https://github.com/GuanlinLee/Noisy-LVIS.
Modeling spatial relationship in the data remains critical across many different tasks, such as image classification, semantic segmentation and protein structure understanding. Previous works often use a unified solution like relative positional encoding. However, there exists different kinds of spatial relations, including short-range, medium-range and long-range relations, and modeling them separately can better capture the focus of different tasks on the multi-range relations (e.g., short-range relations can be important in instance segmentation, while long-range relations should be upweighted for semantic segmentation). In this work, we introduce the EurNet for Efficient multi-range relational modeling. EurNet constructs the multi-relational graph, where each type of edge corresponds to short-, medium- or long-range spatial interactions. In the constructed graph, EurNet adopts a novel modeling layer, called gated relational message passing (GRMP), to propagate multi-relational information across the data. GRMP captures multiple relations within the data with little extra computational cost. We study EurNets in two important domains for image and protein structure modeling. Extensive experiments on ImageNet classification, COCO object detection and ADE20K semantic segmentation verify the gains of EurNet over the previous SoTA FocalNet. On the EC and GO protein function prediction benchmarks, EurNet consistently surpasses the previous SoTA GearNet. Our results demonstrate the strength of EurNets on modeling spatial multi-relational data from various domains. The implementations of EurNet for image modeling are available at https://github.com/hirl-team/EurNet-Image . The implementations for other applied domains/tasks will be released soon.
In this paper, we provide the observation that too few queries assigned as positive samples in DETR with one-to-one set matching leads to sparse supervision on the encoder's output which considerably hurt the discriminative feature learning of the encoder and vice visa for attention learning in the decoder. To alleviate this, we present a novel collaborative hybrid assignments training scheme, namely $\mathcal{C}$o-DETR, to learn more efficient and effective DETR-based detectors from versatile label assignment manners. This new training scheme can easily enhance the encoder's learning ability in end-to-end detectors by training the multiple parallel auxiliary heads supervised by one-to-many label assignments such as ATSS and Faster RCNN. In addition, we conduct extra customized positive queries by extracting the positive coordinates from these auxiliary heads to improve the training efficiency of positive samples in the decoder. In inference, these auxiliary heads are discarded and thus our method introduces no additional parameters and computational cost to the original detector while requiring no hand-crafted non-maximum suppression (NMS). We conduct extensive experiments to evaluate the effectiveness of the proposed approach on DETR variants, including DAB-DETR, Deformable-DETR, and DINO-Deformable-DETR. The state-of-the-art DINO-Deformable-DETR with Swin-L can be improved from 58.5% to 59.5% AP on COCO val. Surprisingly, incorporated with ViT-L backbone, we achieve 66.0% AP on COCO test-dev and 67.9% AP on LVIS val, outperforming previous methods by clear margins with much fewer model sizes. Codes are available at \url{https://github.com/Sense-X/Co-DETR}.
Implicit Neural Representations (INRs) are powerful to parameterize continuous signals in computer vision. However, almost all INRs methods are limited to low-level tasks, e.g., image/video compression, super-resolution, and image generation. The questions on how to explore INRs to high-level tasks and deep networks are still under-explored. Existing INRs methods suffer from two problems: 1) narrow theoretical definitions of INRs are inapplicable to high-level tasks; 2) lack of representation capabilities to deep networks. Motivated by the above facts, we reformulate the definitions of INRs from a novel perspective and propose an innovative Implicit Neural Representation Network (INRN), which is the first study of INRs to tackle both low-level and high-level tasks. Specifically, we present three key designs for basic blocks in INRN along with two different stacking ways and corresponding loss functions. Extensive experiments with analysis on both low-level tasks (image fitting) and high-level vision tasks (image classification, object detection, instance segmentation) demonstrate the effectiveness of the proposed method.
Automatic security inspection relying on computer vision technology is a challenging task in real-world scenarios due to many factors, such as intra-class variance, class imbalance, and occlusion. Most previous methods rarely touch the cases where the prohibited items are deliberately hidden in messy objects because of the scarcity of large-scale datasets, hindering their applications. To address this issue and facilitate related research, we present a large-scale dataset, named PIDray, which covers various cases in real-world scenarios for prohibited item detection, especially for deliberately hidden items. In specific, PIDray collects 124,486 X-ray images for $12$ categories of prohibited items, and each image is manually annotated with careful inspection, which makes it, to our best knowledge, to largest prohibited items detection dataset to date. Meanwhile, we propose a general divide-and-conquer pipeline to develop baseline algorithms on PIDray. Specifically, we adopt the tree-like structure to suppress the influence of the long-tailed issue in the PIDray dataset, where the first course-grained node is tasked with the binary classification to alleviate the influence of head category, while the subsequent fine-grained node is dedicated to the specific tasks of the tail categories. Based on this simple yet effective scheme, we offer strong task-specific baselines across object detection, instance segmentation, and multi-label classification tasks and verify the generalization ability on common datasets (e.g., COCO and PASCAL VOC). Extensive experiments on PIDray demonstrate that the proposed method performs favorably against current state-of-the-art methods, especially for deliberately hidden items. Our benchmark and codes will be released at https://github.com/lutao2021/PIDray.
Instance segmentation is applied widely in image editing, image analysis and autonomous driving, etc. However, insufficient data is a common problem in practical applications. The Visual Inductive Priors(VIPriors) Instance Segmentation Challenge has focused on this problem. VIPriors for Data-Efficient Computer Vision Challenges ask competitors to train models from scratch in a data-deficient setting, but there are some visual inductive priors that can be used. In order to address the VIPriors instance segmentation problem, we designed a Task-Specific Data Augmentation(TS-DA) strategy and Inference Processing(TS-IP) strategy. The main purpose of task-specific data augmentation strategy is to tackle the data-deficient problem. And in order to make the most of visual inductive priors, we designed a task-specific inference processing strategy. We demonstrate the applicability of proposed method on VIPriors Instance Segmentation Challenge. The segmentation model applied is Hybrid Task Cascade based detector on the Swin-Base based CBNetV2 backbone. Experimental results demonstrate that proposed method can achieve a competitive result on the test set of 2022 VIPriors Instance Segmentation Challenge, with 0.531 [email omitted]:0.95.
Segmenting unseen objects from images is a critical perception skill that a robot needs to acquire. In robot manipulation, it can facilitate a robot to grasp and manipulate unseen objects. Mean shift clustering is a widely used method for image segmentation tasks. However, the traditional mean shift clustering algorithm is not differentiable, making it difficult to integrate it into an end-to-end neural network training framework. In this work, we propose the Mean Shift Mask Transformer (MSMFormer), a new transformer architecture that simulates the von Mises-Fisher (vMF) mean shift clustering algorithm, allowing for the joint training and inference of both the feature extractor and the clustering. Its central component is a hypersphere attention mechanism, which updates object queries on a hypersphere. To illustrate the effectiveness of our method, we apply MSMFormer to unseen object instance segmentation. Our experiments show that MSMFormer achieves competitive performance compared to state-of-the-art methods for unseen object instance segmentation. The project page, appendix, video, and code are available at https://irvlutd.github.io/MSMFormer
This paper introduces the first public large-scale, long-span dataset with sea turtle photographs captured in the wild -- \href{https://www.kaggle.com/datasets/wildlifedatasets/seaturtleid2022}{SeaTurtleID2022}. The dataset contains 8729 photographs of 438 unique individuals collected within 13 years, making it the longest-spanned dataset for animal re-identification. All photographs include various annotations, e.g., identity, encounter timestamp, and body parts segmentation masks. Instead of standard "random" splits, the dataset allows for two realistic and ecologically motivated splits: (i) a \textit{time-aware closed-set} with training, validation, and test data from different days/years, and (ii) a \textit{time-aware open-set} with new unknown individuals in test and validation sets. We show that time-aware splits are essential for benchmarking re-identification methods, as random splits lead to performance overestimation. Furthermore, a baseline instance segmentation and re-identification performance over various body parts is provided. Finally, an end-to-end system for sea turtle re-identification is proposed and evaluated. The proposed system based on Hybrid Task Cascade for head instance segmentation and ArcFace-trained feature-extractor achieved an accuracy of 86.8\%.
This technical report describes our 2nd-place solution for the ECCV 2022 YouTube-VIS Long Video Challenge. We adopt the previously proposed online video instance segmentation method IDOL for this challenge. In addition, we use pseudo labels to further help contrastive learning, so as to obtain more temporally consistent instance embedding to improve tracking performance between frames. The proposed method obtains 40.2 AP on the YouTube-VIS 2022 long video dataset and was ranked second place in this challenge. We hope our simple and effective method could benefit further research.
Traffic flow analysis is revolutionising traffic management. Qualifying traffic flow data, traffic control bureaus could provide drivers with real-time alerts, advising the fastest routes and therefore optimising transportation logistics and reducing congestion. The existing traffic flow datasets have two major limitations. They feature a limited number of classes, usually limited to one type of vehicle, and the scarcity of unlabelled data. In this paper, we introduce a new benchmark traffic flow image dataset called TrafficCAM. Our dataset distinguishes itself by two major highlights. Firstly, TrafficCAM provides both pixel-level and instance-level semantic labelling along with a large range of types of vehicles and pedestrians. It is composed of a large and diverse set of video sequences recorded in streets from eight Indian cities with stationary cameras. Secondly, TrafficCAM aims to establish a new benchmark for developing fully-supervised tasks, and importantly, semi-supervised learning techniques. It is the first dataset that provides a vast amount of unlabelled data, helping to better capture traffic flow qualification under a low cost annotation requirement. More precisely, our dataset has 4,402 image frames with semantic and instance annotations along with 59,944 unlabelled image frames. We validate our new dataset through a large and comprehensive range of experiments on several state-of-the-art approaches under four different settings: fully-supervised semantic and instance segmentation, and semi-supervised semantic and instance segmentation tasks. Our benchmark dataset will be released.
Previous top-performing methods for 3D instance segmentation often maintain inter-task dependencies and the tendency towards a lack of robustness. Besides, inevitable variations of different datasets make these methods become particularly sensitive to hyper-parameter values and manifest poor generalization capability. In this paper, we address the aforementioned challenges by proposing a novel query-based method, termed as 3D-QueryIS, which is detector-free, semantic segmentation-free, and cluster-free. Specifically, we propose to generate representative points in an implicit manner, and use them together with the initial queries to generate the informative instance queries. Then, the class and binary instance mask predictions can be produced by simply applying MLP layers on top of the instance queries and the extracted point cloud embeddings. Thus, our 3D-QueryIS is free from the accumulated errors caused by the inter-task dependencies. Extensive experiments on multiple benchmark datasets demonstrate the effectiveness and efficiency of our proposed 3D-QueryIS method.
Recently, transformer-based methods have achieved impressive results on Video Instance Segmentation (VIS). However, most of these top-performing methods run in an offline manner by processing the entire video clip at once to predict instance mask volumes. This makes them incapable of handling the long videos that appear in challenging new video instance segmentation datasets like UVO and OVIS. We propose a fully online transformer-based video instance segmentation model that performs comparably to top offline methods on the YouTube-VIS 2019 benchmark and considerably outperforms them on UVO and OVIS. This method, called Robust Online Video Segmentation (ROVIS), augments the Mask2Former image instance segmentation model with track queries, a lightweight mechanism for carrying track information from frame to frame, originally introduced by the TrackFormer method for multi-object tracking. We show that, when combined with a strong enough image segmentation architecture, track queries can exhibit impressive accuracy while not being constrained to short videos.
Self-supervised pre-training, based on the pretext task of instance discrimination, has fueled the recent advance in label-efficient object detection. However, existing studies focus on pre-training only a feature extractor network to learn transferable representations for downstream detection tasks. This leads to the necessity of training multiple detection-specific modules from scratch in the fine-tuning phase. We argue that the region proposal network (RPN), a common detection-specific module, can additionally be pre-trained towards reducing the localization error of multi-stage detectors. In this work, we propose a simple pretext task that provides an effective pre-training for the RPN, towards efficiently improving downstream object detection performance. We evaluate the efficacy of our approach on benchmark object detection tasks and additional downstream tasks, including instance segmentation and few-shot detection. In comparison with multi-stage detectors without RPN pre-training, our approach is able to consistently improve downstream task performance, with largest gains found in label-scarce settings.