Recent transformer-based offline video instance segmentation (VIS) approaches achieve encouraging results and significantly outperform online approaches. However, their reliance on the whole video and the immense computational complexity caused by full Spatio-temporal attention limit them in real-life applications such as processing lengthy videos. In this paper, we propose a single-stage transformer-based efficient online VIS framework named InstanceFormer, which is especially suitable for long and challenging videos. We propose three novel components to model short-term and long-term dependency and temporal coherence. First, we propagate the representation, location, and semantic information of prior instances to model short-term changes. Second, we propose a novel memory cross-attention in the decoder, which allows the network to look into earlier instances within a certain temporal window. Finally, we employ a temporal contrastive loss to impose coherence in the representation of an instance across all frames. Memory attention and temporal coherence are particularly beneficial to long-range dependency modeling, including challenging scenarios like occlusion. The proposed InstanceFormer outperforms previous online benchmark methods by a large margin across multiple datasets. Most importantly, InstanceFormer surpasses offline approaches for challenging and long datasets such as YouTube-VIS-2021 and OVIS. Code is available at https://github.com/rajatkoner08/InstanceFormer.
A big convergence of language, vision, and multimodal pretraining is emerging. In this work, we introduce a general-purpose multimodal foundation model BEiT-3, which achieves state-of-the-art transfer performance on both vision and vision-language tasks. Specifically, we advance the big convergence from three aspects: backbone architecture, pretraining task, and model scaling up. We introduce Multiway Transformers for general-purpose modeling, where the modular architecture enables both deep fusion and modality-specific encoding. Based on the shared backbone, we perform masked "language" modeling on images (Imglish), texts (English), and image-text pairs ("parallel sentences") in a unified manner. Experimental results show that BEiT-3 obtains state-of-the-art performance on object detection (COCO), semantic segmentation (ADE20K), image classification (ImageNet), visual reasoning (NLVR2), visual question answering (VQAv2), image captioning (COCO), and cross-modal retrieval (Flickr30K, COCO).
Long-tailed learning aims to tackle the crucial challenge that head classes dominate the training procedure under severe class imbalance in real-world scenarios. However, little attention has been given to how to quantify the dominance severity of head classes in the representation space. Motivated by this, we generalize the cosine-based classifiers to a von Mises-Fisher (vMF) mixture model, denoted as vMF classifier, which enables to quantitatively measure representation quality upon the hyper-sphere space via calculating distribution overlap coefficient. To our knowledge, this is the first work to measure representation quality of classifiers and features from the perspective of distribution overlap coefficient. On top of it, we formulate the inter-class discrepancy and class-feature consistency loss terms to alleviate the interference among the classifier weights and align features with classifier weights. Furthermore, a novel post-training calibration algorithm is devised to zero-costly boost the performance via inter-class overlap coefficients. Our method outperforms previous work with a large margin and achieves state-of-the-art performance on long-tailed image classification, semantic segmentation, and instance segmentation tasks (e.g., we achieve 55.0\% overall accuracy with ResNetXt-50 in ImageNet-LT). Our code is available at https://github.com/VipaiLab/vMF\_OP.
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.
In this paper, we tackle an emerging computer vision task, open-vocabulary universal image segmentation, that aims to perform semantic/instance/panoptic segmentation (background semantic labeling + foreground instance segmentation) for arbitrary categories of text-based descriptions in inference time. We first build a baseline method by directly adopting pre-trained CLIP models without finetuning or distillation. We then develop MaskCLIP, a Transformer-based approach with a MaskCLIP Visual Encoder, which is an encoder-only module that seamlessly integrates mask tokens with a pre-trained ViT CLIP model for semantic/instance segmentation and class prediction. MaskCLIP learns to efficiently and effectively utilize pre-trained partial/dense CLIP features within the MaskCLIP Visual Encoder that avoids the time-consuming student-teacher training process. MaskCLIP outperforms previous methods for semantic/instance/panoptic segmentation on ADE20K and PASCAL datasets. We show qualitative illustrations for MaskCLIP with online custom categories. Project website: https://maskclip.github.io.
We present a conceptually simple, flexible, and universal visual perception head for variant visual tasks, e.g., classification, object detection, instance segmentation and pose estimation, and different frameworks, such as one-stage or two-stage pipelines. Our approach effectively identifies an object in an image while simultaneously generating a high-quality bounding box or contour-based segmentation mask or set of keypoints. The method, called UniHead, views different visual perception tasks as the dispersible points learning via the transformer encoder architecture. Given a fixed spatial coordinate, UniHead adaptively scatters it to different spatial points and reasons about their relations by transformer encoder. It directly outputs the final set of predictions in the form of multiple points, allowing us to perform different visual tasks in different frameworks with the same head design. We show extensive evaluations on ImageNet classification and all three tracks of the COCO suite of challenges, including object detection, instance segmentation and pose estimation. Without bells and whistles, UniHead can unify these visual tasks via a single visual head design and achieve comparable performance compared to expert models developed for each task.We hope our simple and universal UniHead will serve as a solid baseline and help promote universal visual perception research. Code and models are available at https://github.com/Sense-X/UniHead.
We propose Video-TransUNet, a deep architecture for instance segmentation in medical CT videos constructed by integrating temporal feature blending into the TransUNet deep learning framework. In particular, our approach amalgamates strong frame representation via a ResNet CNN backbone, multi-frame feature blending via a Temporal Context Module (TCM), non-local attention via a Vision Transformer, and reconstructive capabilities for multiple targets via a UNet-based convolutional-deconvolutional architecture with multiple heads. We show that this new network design can significantly outperform other state-of-the-art systems when tested on the segmentation of bolus and pharynx/larynx in Videofluoroscopic Swallowing Study (VFSS) CT sequences. On our VFSS2022 dataset it achieves a dice coefficient of 0.8796 and an average surface distance of 1.0379 pixels. Note that tracking the pharyngeal bolus accurately is a particularly important application in clinical practice since it constitutes the primary method for diagnostics of swallowing impairment. Our findings suggest that the proposed model can indeed enhance the TransUNet architecture via exploiting temporal information and improving segmentation performance by a significant margin. We publish key source code, network weights, and ground truth annotations for simplified performance reproduction.
With the recent development of Deep Learning applied to Computer Vision, sport video understanding has gained a lot of attention, providing much richer information for both sport consumers and leagues. This paper introduces DeepSportradar-v1, a suite of computer vision tasks, datasets and benchmarks for automated sport understanding. The main purpose of this framework is to close the gap between academic research and real world settings. To this end, the datasets provide high-resolution raw images, camera parameters and high quality annotations. DeepSportradar currently supports four challenging tasks related to basketball: ball 3D localization, camera calibration, player instance segmentation and player re-identification. For each of the four tasks, a detailed description of the dataset, objective, performance metrics, and the proposed baseline method are provided. To encourage further research on advanced methods for sport understanding, a competition is organized as part of the MMSports workshop from the ACM Multimedia 2022 conference, where participants have to develop state-of-the-art methods to solve the above tasks. The four datasets, development kits and baselines are publicly available.
Segmentation from point cloud data is essential in many applications such as remote sensing, mobile robots, or autonomous cars. However, the point clouds captured by the 3D range sensor are commonly sparse and unstructured, challenging efficient segmentation. In this paper, we present a fast solution to point cloud instance segmentation with small computational demands. To this end, we propose a novel fast Euclidean clustering (FEC) algorithm which applies a pointwise scheme over the clusterwise scheme used in existing works. Our approach is conceptually simple, easy to implement (40 lines in C++), and achieves two orders of magnitudes faster against the classical segmentation methods while producing high-quality results.
Recognizing 3D part instances from a 3D point cloud is crucial for 3D structure and scene understanding. Several learning-based approaches use semantic segmentation and instance center prediction as training tasks and fail to further exploit the inherent relationship between shape semantics and part instances. In this paper, we present a new method for 3D part instance segmentation. Our method exploits semantic segmentation to fuse nonlocal instance features, such as center prediction, and further enhances the fusion scheme in a multi- and cross-level way. We also propose a semantic region center prediction task to train and leverage the prediction results to improve the clustering of instance points. Our method outperforms existing methods with a large-margin improvement in the PartNet benchmark. We also demonstrate that our feature fusion scheme can be applied to other existing methods to improve their performance in indoor scene instance segmentation tasks.
Segmenting highly-overlapping image objects is challenging, because there is typically no distinction between real object contours and occlusion boundaries on images. Unlike previous instance segmentation methods, we model image formation as a composition of two overlapping layers, and propose Bilayer Convolutional Network (BCNet), where the top layer detects occluding objects (occluders) and the bottom layer infers partially occluded instances (occludees). The explicit modeling of occlusion relationship with bilayer structure naturally decouples the boundaries of both the occluding and occluded instances, and considers the interaction between them during mask regression. We investigate the efficacy of bilayer structure using two popular convolutional network designs, namely, Fully Convolutional Network (FCN) and Graph Convolutional Network (GCN). Further, we formulate bilayer decoupling using the vision transformer (ViT), by representing instances in the image as separate learnable occluder and occludee queries. Large and consistent improvements using one/two-stage and query-based object detectors with various backbones and network layer choices validate the generalization ability of bilayer decoupling, as shown by extensive experiments on image instance segmentation benchmarks (COCO, KINS, COCOA) and video instance segmentation benchmarks (YTVIS, OVIS, BDD100K MOTS), especially for heavy occlusion cases. Code and data are available at https://github.com/lkeab/BCNet.
Modeling temporal information for both detection and tracking in a unified framework has been proved a promising solution to video instance segmentation (VIS). However, how to effectively incorporate the temporal information into an online model remains an open problem. In this work, we propose a new online VIS paradigm named Instance As Identity (IAI), which models temporal information for both detection and tracking in an efficient way. In detail, IAI employs a novel identification module to predict identification number for tracking instances explicitly. For passing temporal information cross frame, IAI utilizes an association module which combines current features and past embeddings. Notably, IAI can be integrated with different image models. We conduct extensive experiments on three VIS benchmarks. IAI outperforms all the online competitors on YouTube-VIS-2019 (ResNet-101 43.7 mAP) and YouTube-VIS-2021 (ResNet-50 38.0 mAP). Surprisingly, on the more challenging OVIS, IAI achieves SOTA performance (20.6 mAP). Code is available at https://github.com/zfonemore/IAI
Defects increase the cost and duration of construction projects as they require significant inspection and documentation efforts. Automating defect detection could significantly reduce these efforts. This work focuses on detecting honeycombs, a substantial defect in concrete structures that may affect structural integrity. We compared honeycomb images scraped from the web with images obtained from real construction inspections. We found that web images do not capture the complete variance found in real-case scenarios and that there is still a lack of data in this domain. Our dataset is therefore freely available for further research. A Mask R-CNN and EfficientNet-B0 were trained for honeycomb detection. The Mask R-CNN model allows detecting honeycombs based on instance segmentation, whereas the EfficientNet-B0 model allows a patch-based classification. Our experiments demonstrate that both approaches are suitable for solving and automating honeycomb detection. In the future, this solution can be incorporated into defect documentation systems.
We propose MinVIS, a minimal video instance segmentation (VIS) framework that achieves state-of-the-art VIS performance with neither video-based architectures nor training procedures. By only training a query-based image instance segmentation model, MinVIS outperforms the previous best result on the challenging Occluded VIS dataset by over 10% AP. Since MinVIS treats frames in training videos as independent images, we can drastically sub-sample the annotated frames in training videos without any modifications. With only 1% of labeled frames, MinVIS outperforms or is comparable to fully-supervised state-of-the-art approaches on YouTube-VIS 2019/2021. Our key observation is that queries trained to be discriminative between intra-frame object instances are temporally consistent and can be used to track instances without any manually designed heuristics. MinVIS thus has the following inference pipeline: we first apply the trained query-based image instance segmentation to video frames independently. The segmented instances are then tracked by bipartite matching of the corresponding queries. This inference is done in an online fashion and does not need to process the whole video at once. MinVIS thus has the practical advantages of reducing both the labeling costs and the memory requirements, while not sacrificing the VIS performance. Code is available at: https://github.com/NVlabs/MinVIS
Long-tailed datasets are very frequently encountered in real-world use cases where few classes or categories (known as majority or head classes) have higher number of data samples compared to the other classes (known as minority or tail classes). Training deep neural networks on such datasets gives results biased towards the head classes. So far, researchers have come up with multiple weighted loss and data re-sampling techniques in efforts to reduce the bias. However, most of such techniques assume that the tail classes are always the most difficult classes to learn and therefore need more weightage or attention. Here, we argue that the assumption might not always hold true. Therefore, we propose a novel approach to dynamically measure the instantaneous difficulty of each class during the training phase of the model. Further, we use the difficulty measures of each class to design a novel weighted loss technique called `class-wise difficulty based weighted (CDB-W) loss' and a novel data sampling technique called `class-wise difficulty based sampling (CDB-S)'. To verify the wide-scale usability of our CDB methods, we conducted extensive experiments on multiple tasks such as image classification, object detection, instance segmentation and video-action classification. Results verified that CDB-W loss and CDB-S could achieve state-of-the-art results on many class-imbalanced datasets such as ImageNet-LT, LVIS and EGTEA, that resemble real-world use cases.
We share our recent findings in an attempt to train a universal segmentation network for various cell types and imaging modalities. Our method was built on the generalized U-Net architecture, which allows the evaluation of each component individually. We modified the traditional binary training targets to include three classes for direct instance segmentation. Detailed experiments were performed regarding training schemes, training settings, network backbones, and individual modules on the segmentation performance. Our proposed training scheme draws minibatches in turn from each dataset, and the gradients are accumulated before an optimization step. We found that the key to training a universal network is all-time supervision on all datasets, and it is necessary to sample each dataset in an unbiased way. Our experiments also suggest that there might exist common features to define cell boundaries across cell types and imaging modalities, which could allow application of trained models to totally unseen datasets. A few training tricks can further boost the segmentation performance, including uneven class weights in the cross-entropy loss function, well-designed learning rate scheduler, larger image crops for contextual information, and additional loss terms for unbalanced classes. We also found that segmentation performance can benefit from group normalization layer and Atrous Spatial Pyramid Pooling module, thanks to their more reliable statistics estimation and improved semantic understanding, respectively. We participated in the 6th Cell Tracking Challenge (CTC) held at IEEE International Symposium on Biomedical Imaging (ISBI) 2021 using one of the developed variants. Our method was evaluated as the best runner up during the initial submission for the primary track, and also secured the 3rd place in an additional round of competition in preparation for the summary publication.
Humans have the ability of recognizing visual semantics in an unlimited granularity, but existing visual recognition algorithms cannot achieve this goal. In this paper, we establish a new paradigm named visual recognition by request (ViRReq) to bridge the gap. The key lies in decomposing visual recognition into atomic tasks named requests and leveraging a knowledge base, a hierarchical and text-based dictionary, to assist task definition. ViRReq allows for (i) learning complicated whole-part hierarchies from highly incomplete annotations and (ii) inserting new concepts with minimal efforts. We also establish a solid baseline by integrating language-driven recognition into recent semantic and instance segmentation methods, and demonstrate its flexible recognition ability on CPP and ADE20K, two datasets with hierarchical whole-part annotations.
Synthesizing natural interactions between virtual humans and their 3D environments is critical for numerous applications, such as computer games and AR/VR experiences. Our goal is to synthesize humans interacting with a given 3D scene controlled by high-level semantic specifications as pairs of action categories and object instances, e.g., "sit on the chair". The key challenge of incorporating interaction semantics into the generation framework is to learn a joint representation that effectively captures heterogeneous information, including human body articulation, 3D object geometry, and the intent of the interaction. To address this challenge, we design a novel transformer-based generative model, in which the articulated 3D human body surface points and 3D objects are jointly encoded in a unified latent space, and the semantics of the interaction between the human and objects are embedded via positional encoding. Furthermore, inspired by the compositional nature of interactions that humans can simultaneously interact with multiple objects, we define interaction semantics as the composition of varying numbers of atomic action-object pairs. Our proposed generative model can naturally incorporate varying numbers of atomic interactions, which enables synthesizing compositional human-scene interactions without requiring composite interaction data. We extend the PROX dataset with interaction semantic labels and scene instance segmentation to evaluate our method and demonstrate that our method can generate realistic human-scene interactions with semantic control. Our perceptual study shows that our synthesized virtual humans can naturally interact with 3D scenes, considerably outperforming existing methods. We name our method COINS, for COmpositional INteraction Synthesis with Semantic Control. Code and data are available at https://github.com/zkf1997/COINS.
The requirement of expensive annotations is a major burden for training a well-performed instance segmentation model. In this paper, we present an economic active learning setting, named active pointly-supervised instance segmentation (APIS), which starts with box-level annotations and iteratively samples a point within the box and asks if it falls on the object. The key of APIS is to find the most desirable points to maximize the segmentation accuracy with limited annotation budgets. We formulate this setting and propose several uncertainty-based sampling strategies. The model developed with these strategies yields consistent performance gain on the challenging MS-COCO dataset, compared against other learning strategies. The results suggest that APIS, integrating the advantages of active learning and point-based supervision, is an effective learning paradigm for label-efficient instance segmentation.
Instance segmentation on point clouds is crucially important for 3D scene understanding. Most SOTAs adopt distance clustering, which is typically effective but does not perform well in segmenting adjacent objects with the same semantic label (especially when they share neighboring points). Due to the uneven distribution of offset points, these existing methods can hardly cluster all instance points. To this end, we design a novel divide-and-conquer strategy named PBNet that binarizes each point and clusters them separately to segment instances. Our binary clustering divides offset instance points into two categories: high and low density points (HPs vs. LPs). Adjacent objects can be clearly separated by removing LPs, and then be completed and refined by assigning LPs via a neighbor voting method. To suppress potential over-segmentation, we propose to construct local scenes with the weight mask for each instance. As a plug-in, the proposed binary clustering can replace traditional distance clustering and lead to consistent performance gains on many mainstream baselines. A series of experiments on ScanNetV2 and S3DIS datasets indicate the superiority of our model. In particular, PBNet ranks first on the ScanNetV2 official benchmark challenge, achieving the highest mAP. Code will be available publicly at https://github.com/weiguangzhao/PBNet.