The objective of this paper is a model that is able to discover, track and segment multiple moving objects in a video. We make four contributions: First, we introduce an object-centric segmentation model with a depth-ordered layer representation. This is implemented using a variant of the transformer architecture that ingests optical flow, where each query vector specifies an object and its layer for the entire video. The model can effectively discover multiple moving objects and handle mutual occlusions; Second, we introduce a scalable pipeline for generating multi-object synthetic training data via layer compositions, that is used to train the proposed model, significantly reducing the requirements for labour-intensive annotations, and supporting Sim2Real generalisation; Third, we conduct thorough ablation studies, showing that the model is able to learn object permanence and temporal shape consistency, and is able to predict amodal segmentation masks; Fourth, we evaluate our model, trained only on synthetic data, on standard video segmentation benchmarks, DAVIS, MoCA, SegTrack, FBMS-59, and achieve state-of-the-art performance among existing methods that do not rely on any manual annotations. With test-time adaptation, we observe further performance boosts.
In the booming video era, video segmentation attracts increasing research attention in the multimedia community. Semi-supervised video object segmentation (VOS) aims at segmenting objects in all target frames of a video, given annotated object masks of reference frames. Most existing methods build pixel-wise reference-target correlations and then perform pixel-wise tracking to obtain target masks. Due to neglecting object-level cues, pixel-level approaches make the tracking vulnerable to perturbations, and even indiscriminate among similar objects. Towards robust VOS, the key insight is to calibrate the representation and mask of each specific object to be expressive and discriminative. Accordingly, we propose a new deep network, which can adaptively construct object representations and calibrate object masks to achieve stronger robustness. First, we construct the object representations by applying an adaptive object proxy (AOP) aggregation method, where the proxies represent arbitrary-shaped segments at multi-levels for reference. Then, prototype masks are initially generated from the reference-target correlations based on AOP. Afterwards, such proto-masks are further calibrated through network modulation, conditioning on the object proxy representations. We consolidate this conditional mask calibration process in a progressive manner, where the object representations and proto-masks evolve to be discriminative iteratively. Extensive experiments are conducted on the standard VOS benchmarks, YouTube-VOS-18/19 and DAVIS-17. Our model achieves the state-of-the-art performance among existing published works, and also exhibits superior robustness against perturbations. Our project repo is at https://github.com/JerryX1110/Robust-Video-Object-Segmentation
Real-time video segmentation is a crucial task for many real-world applications such as autonomous driving and robot control. Since state-of-the-art semantic segmentation models are often too heavy for real-time applications despite their impressive performance, researchers have proposed lightweight architectures with speed-accuracy trade-offs, achieving real-time speed at the expense of reduced accuracy. In this paper, we propose a novel framework to speed up any architecture with skip-connections for real-time vision tasks by exploiting the temporal locality in videos. Specifically, at the arrival of each frame, we transform the features from the previous frame to reuse them at specific spatial bins. We then perform partial computation of the backbone network on the regions of the current frame that captures temporal differences between the current and previous frame. This is done by dynamically dropping out residual blocks using a gating mechanism which decides which blocks to drop based on inter-frame distortion. We validate our Spatial-Temporal Mask Generator (STMG) on video semantic segmentation benchmarks with multiple backbone networks, and show that our method largely speeds up inference with minimal loss of accuracy.
Video object segmentation (VOS) has made significant progress with the rise of deep learning. However, there still exist some thorny problems, for example, similar objects are easily confused and tiny objects are difficult to be found. To solve these problems and further improve the performance of VOS, we propose a simple yet effective solution for this task. In the solution, we first analyze the distribution of the Youtube-VOS dataset and supplement the dataset by introducing public static and video segmentation datasets. Then, we improve three network architectures with different characteristics and train several networks to learn the different characteristics of objects in videos. After that, we use a simple way to integrate all results to ensure that different models complement each other. Finally, subtle post-processing is carried out to ensure accurate video object segmentation with precise boundaries. Extensive experiments on Youtube-VOS dataset show that the proposed solution achieves the state-of-the-art performance with an 86.1% overall score on the YouTube-VOS 2022 test set, which is 5th place on the video object segmentation track of the Youtube-VOS Challenge 2022.
A new open-source image processing pipeline for analyzing camera trap time-lapse recordings is described. This pipeline includes machine learning models to assist human-in-the-loop video segmentation and animal re-identification. We present some performance results and observations on the utility of this pipeline after using it in a year-long project studying the spatial ecology and social behavior of the gopher tortoise.
Transformers have become prevalent in computer vision due to their performance and flexibility in modelling complex operations. Of particular significance is the 'cross-attention' operation, which allows a vector representation (e.g. of an object in an image) to be learned by attending to an arbitrarily sized set of input features. Recently, "Masked Attention" was proposed in which a given object representation only attends to those image pixel features for which the segmentation mask of that object is active. This specialization of attention proved beneficial for various image and video segmentation tasks. In this paper, we propose another specialization of attention which enables attending over `soft-masks' (those with continuous mask probabilities instead of binary values), and is also differentiable through these mask probabilities, thus allowing the mask used for attention to be learned within the network without requiring direct loss supervision. This can be useful for several applications. Specifically, we employ our "Differentiable Soft-Masked Attention" for the task of Weakly-Supervised Video Object Segmentation (VOS), where we develop a transformer-based network for VOS which only requires a single annotated image frame for training, but can also benefit from cycle consistency training on a video with just one annotated frame. Although there is no loss for masks in unlabeled frames, the network is still able to segment objects in those frames due to our novel attention formulation. Code: https://github.com/Ali2500/HODOR/blob/main/hodor/modelling/encoder/soft_masked_attention.py
We present TubeFormer-DeepLab, the first attempt to tackle multiple core video segmentation tasks in a unified manner. Different video segmentation tasks (e.g., video semantic/instance/panoptic segmentation) are usually considered as distinct problems. State-of-the-art models adopted in the separate communities have diverged, and radically different approaches dominate in each task. By contrast, we make a crucial observation that video segmentation tasks could be generally formulated as the problem of assigning different predicted labels to video tubes (where a tube is obtained by linking segmentation masks along the time axis) and the labels may encode different values depending on the target task. The observation motivates us to develop TubeFormer-DeepLab, a simple and effective video mask transformer model that is widely applicable to multiple video segmentation tasks. TubeFormer-DeepLab directly predicts video tubes with task-specific labels (either pure semantic categories, or both semantic categories and instance identities), which not only significantly simplifies video segmentation models, but also advances state-of-the-art results on multiple video segmentation benchmarks
Motion, measured via optical flow, provides a powerful cue to discover and learn objects in images and videos. However, compared to using appearance, it has some blind spots, such as the fact that objects become invisible if they do not move. In this work, we propose an approach that combines the strengths of motion-based and appearance-based segmentation. We propose to supervise an image segmentation network with the pretext task of predicting regions that are likely to contain simple motion patterns, and thus likely to correspond to objects. As the model only uses a single image as input, we can apply it in two settings: unsupervised video segmentation, and unsupervised image segmentation. We achieve state-of-the-art results for videos, and demonstrate the viability of our approach on still images containing novel objects. Additionally we experiment with different motion models and optical flow backbones and find the method to be robust to these change. Project page and code available at https://www.robots.ox.ac.uk/~vgg/research/gwm.
3D convolutional networks is a good means to perform tasks such as video segmentation into coherent spatio-temporal chunks and classification of them with regard to a target taxonomy. In the chapter we are interested in the classification of continuous video takes with repeatable actions, such as strokes of table tennis. Filmed in a free marker less ecological environment, these videos represent a challenge from both segmentation and classification point of view. The 3D convnets are an efficient tool for solving these problems with window-based approaches.
This paper presents Video K-Net, a simple, strong, and unified framework for fully end-to-end video panoptic segmentation. The method is built upon K-Net, a method that unifies image segmentation via a group of learnable kernels. We observe that these learnable kernels from K-Net, which encode object appearances and contexts, can naturally associate identical instances across video frames. Motivated by this observation, Video K-Net learns to simultaneously segment and track "things" and "stuff" in a video with simple kernel-based appearance modeling and cross-temporal kernel interaction. Despite the simplicity, it achieves state-of-the-art video panoptic segmentation results on Citscapes-VPS, KITTI-STEP, and VIPSeg without bells and whistles. In particular, on KITTI-STEP, the simple method can boost almost 12\% relative improvements over previous methods. On VIPSeg, Video K-Net boosts almost 15\% relative improvements and results in 39.8 % VPQ. We also validate its generalization on video semantic segmentation, where we boost various baselines by 2\% on the VSPW dataset. Moreover, we extend K-Net into clip-level video framework for video instance segmentation, where we obtain 40.5% mAP for ResNet50 backbone and 54.1% mAP for Swin-base on YouTube-2019 validation set. We hope this simple, yet effective method can serve as a new, flexible baseline in unified video segmentation design. Both code and models are released at https://github.com/lxtGH/Video-K-Net.
Text-based video segmentation aims to segment the target object in a video based on a describing sentence. Incorporating motion information from optical flow maps with appearance and linguistic modalities is crucial yet has been largely ignored by previous work. In this paper, we design a method to fuse and align appearance, motion, and linguistic features to achieve accurate segmentation. Specifically, we propose a multi-modal video transformer, which can fuse and aggregate multi-modal and temporal features between frames. Furthermore, we design a language-guided feature fusion module to progressively fuse appearance and motion features in each feature level with guidance from linguistic features. Finally, a multi-modal alignment loss is proposed to alleviate the semantic gap between features from different modalities. Extensive experiments on A2D Sentences and J-HMDB Sentences verify the performance and the generalization ability of our method compared to the state-of-the-art methods.
Human video instance segmentation plays an important role in computer understanding of human activities and is widely used in video processing, video surveillance, and human modeling in virtual reality. Most current VIS methods are based on Mask-RCNN framework, where the target appearance and motion information for data matching will increase computational cost and have an impact on segmentation real-time performance; on the other hand, the existing datasets for VIS focus less on all the people appearing in the video. In this paper, to solve the problems, we develop a new method for human video instance segmentation based on single-stage detector. To tracking the instance across the video, we have adopted data association strategy for matching the same instance in the video sequence, where we jointly learn target instance appearances and their affinities in a pair of video frames in an end-to-end fashion. We have also adopted the centroid sampling strategy for enhancing the embedding extraction ability of instance, which is to bias the instance position to the inside of each instance mask with heavy overlap condition. As a result, even there exists a sudden change in the character activity, the instance position will not move out of the mask, so that the problem that the same instance is represented by two different instances can be alleviated. Finally, we collect PVIS dataset by assembling several video instance segmentation datasets to fill the gap of the current lack of datasets dedicated to human video segmentation. Extensive simulations based on such dataset has been conduct. Simulation results verify the effectiveness and efficiency of the proposed work.
Referring video segmentation aims to segment the corresponding video object described by the language expression. To address this task, we first design a two-stream encoder to extract CNN-based visual features and transformer-based linguistic features hierarchically, and a vision-language mutual guidance (VLMG) module is inserted into the encoder multiple times to promote the hierarchical and progressive fusion of multi-modal features. Compared with the existing multi-modal fusion methods, this two-stream encoder takes into account the multi-granularity linguistic context, and realizes the deep interleaving between modalities with the help of VLGM. In order to promote the temporal alignment between frames, we further propose a language-guided multi-scale dynamic filtering (LMDF) module to strengthen the temporal coherence, which uses the language-guided spatial-temporal features to generate a set of position-specific dynamic filters to more flexibly and effectively update the feature of current frame. Extensive experiments on four datasets verify the effectiveness of the proposed model.
In this paper, we focus on unsupervised learning for Video Object Segmentation (VOS) which learns visual correspondence (i.e., the similarity between pixel-level features) from unlabeled videos. Previous methods are mainly based on the contrastive learning paradigm, which optimize either in image level or pixel level. Image-level optimization (e.g., the spatially pooled feature of ResNet) learns robust high-level semantics but is sub-optimal since the pixel-level features are optimized implicitly. By contrast, pixel-level optimization is more explicit, however, it is sensitive to the visual quality of training data and is not robust to object deformation. To complementarily perform these two levels of optimization in a unified framework, we propose the In-aNd-Out (INO) generative learning from a purely generative perspective with the help of naturally designed class tokens and patch tokens in Vision Transformer (ViT). Specifically, for image-level optimization, we force the out-view imagination from local to global views on class tokens, which helps capture high-level semantics, and we name it as out-generative learning. As to pixel-level optimization, we perform in-view masked image modeling on patch tokens, which recovers the corrupted parts of an image via inferring its fine-grained structure, and we term it as in-generative learning. To discover the temporal information better, we additionally force the inter-frame consistency from both feature and affinity matrix levels. Extensive experiments on DAVIS-2017 val and YouTube-VOS 2018 val show that our INO outperforms previous state-of-the-art methods by significant margins. Code is available: https://github.com/pansanity666/INO_VOS
A common problem with segmentation of medical images using neural networks is the difficulty to obtain a significant number of pixel-level annotated data for training. To address this issue, we proposed a semi-supervised segmentation network based on contrastive learning. In contrast to the previous state-of-the-art, we introduce Min-Max Similarity (MMS), a contrastive learning form of dual-view training by employing classifiers and projectors to build all-negative, and positive and negative feature pairs, respectively, to formulate the learning as solving a MMS problem. The all-negative pairs are used to supervise the networks learning from different views and to capture general features, and the consistency of unlabeled predictions is measured by pixel-wise contrastive loss between positive and negative pairs. To quantitatively and qualitatively evaluate our proposed method, we test it on four public endoscopy surgical tool segmentation datasets and one cochlear implant surgery dataset, which we manually annotated. Results indicate that our proposed method consistently outperforms state-of-the-art semi-supervised and fully supervised segmentation algorithms. And our semi-supervised segmentation algorithm can successfully recognize unknown surgical tools and provide good predictions. Also, our MMS approach could achieve inference speeds of about 40 frames per second (fps) and is suitable to deal with the real-time video segmentation.
Deep learning has shown impressive performance in semantic segmentation, but it is still unaffordable for resource-constrained mobile devices. While offloading computation tasks is promising, the high traffic demands overwhelm the limited bandwidth. Existing compression algorithms are not fit for semantic segmentation, as the lack of obvious and concentrated regions of interest (RoIs) forces the adoption of uniform compression strategies, leading to low compression ratios or accuracy. This paper introduces STAC, a DNN-driven compression scheme tailored for edge-assisted semantic video segmentation. STAC is the first to exploit DNN's gradients as spatial sensitivity metrics for spatial adaptive compression and achieves superior compression ratio and accuracy. Yet, it is challenging to adapt this content-customized compression to videos. Practical issues include varying spatial sensitivity and huge bandwidth consumption for compression strategy feedback and offloading. We tackle these issues through a spatiotemporal adaptive scheme, which (1) takes partial strategy generation operations offline to reduce communication load, and (2) propagates compression strategies and segmentation results across frames through dense optical flow, and adaptively offloads keyframes to accommodate video content. We implement STAC on a commodity mobile device. Experiments show that STAC can save up to 20.95% of bandwidth without losing accuracy, compared to the state-of-the-art algorithm.
We explore the task of language-guided video segmentation (LVS). Previous algorithms mostly adopt 3D CNNs to learn video representation, struggling to capture long-term context and easily suffering from visual-linguistic misalignment. In light of this, we present Locater (local-global context aware Transformer), which augments the Transformer architecture with a finite memory so as to query the entire video with the language expression in an efficient manner. The memory is designed to involve two components -- one for persistently preserving global video content, and one for dynamically gathering local temporal context and segmentation history. Based on the memorized local-global context and the particular content of each frame, Locater holistically and flexibly comprehends the expression as an adaptive query vector for each frame. The vector is used to query the corresponding frame for mask generation. The memory also allows Locater to process videos with linear time complexity and constant size memory, while Transformer-style self-attention computation scales quadratically with sequence length. To thoroughly examine the visual grounding capability of LVS models, we contribute a new LVS dataset, A2D-S+, which is built upon A2D-S dataset but poses increased challenges in disambiguating among similar objects. Experiments on three LVS datasets and our A2D-S+ show that Locater outperforms previous state-of-the-arts. Further, we won the 1st place in the Referring Video Object Segmentation Track of the 3rd Large-scale Video Object Segmentation Challenge, where Locater served as the foundation for the winning solution. Our code and dataset are available at: https://github.com/leonnnop/Locater
The promise of self-supervised learning (SSL) is to leverage large amounts of unlabeled data to solve complex tasks. While there has been excellent progress with simple, image-level learning, recent methods have shown the advantage of including knowledge of image structure. However, by introducing hand-crafted image segmentations to define regions of interest, or specialized augmentation strategies, these methods sacrifice the simplicity and generality that makes SSL so powerful. Instead, we propose a self-supervised learning paradigm that discovers this image structure by itself. Our method, Odin, couples object discovery and representation networks to discover meaningful image segmentations without any supervision. The resulting learning paradigm is simpler, less brittle, and more general, and achieves state-of-the-art transfer learning results for object detection and instance segmentation on COCO, and semantic segmentation on PASCAL and Cityscapes, while strongly surpassing supervised pre-training for video segmentation on DAVIS.
The segmentation task has traditionally been formulated as a complete-label pixel classification task to predict a class for each pixel from a fixed number of predefined semantic categories shared by all images or videos. Yet, following this formulation, standard architectures will inevitably encounter various challenges under more realistic settings where the scope of categories scales up (e.g., beyond the level of 1k). On the other hand, in a typical image or video, only a few categories, i.e., a small subset of the complete label are present. Motivated by this intuition, in this paper, we propose to decompose segmentation into two sub-problems: (i) image-level or video-level multi-label classification and (ii) pixel-level rank-adaptive selected-label classification. Given an input image or video, our framework first conducts multi-label classification over the complete label, then sorts the complete label and selects a small subset according to their class confidence scores. We then use a rank-adaptive pixel classifier to perform the pixel-wise classification over only the selected labels, which uses a set of rank-oriented learnable temperature parameters to adjust the pixel classifications scores. Our approach is conceptually general and can be used to improve various existing segmentation frameworks by simply using a lightweight multi-label classification head and rank-adaptive pixel classifier. We demonstrate the effectiveness of our framework with competitive experimental results across four tasks, including image semantic segmentation, image panoptic segmentation, video instance segmentation, and video semantic segmentation. Especially, with our RankSeg, Mask2Former gains +0.8%/+0.7%/+0.7% on ADE20K panoptic segmentation/YouTubeVIS 2019 video instance segmentation/VSPW video semantic segmentation benchmarks respectively.
Most existing real-time deep models trained with each frame independently may produce inconsistent results across the temporal axis when tested on a video sequence. A few methods take the correlations in the video sequence into account,e.g., by propagating the results to the neighboring frames using optical flow or extracting frame representations using multi-frame information, which may lead to inaccurate results or unbalanced latency. In this work, we focus on improving the temporal consistency without introducing computation overhead in inference. To this end, we perform inference at each frame. Temporal consistency is achieved by learning from video frames with extra constraints during the training phase. introduced for inference. We propose several techniques to learn from the video sequence, including a temporal consistency loss and online/offline knowledge distillation methods. On the task of semantic video segmentation, weighing among accuracy, temporal smoothness, and efficiency, our proposed method outperforms keyframe-based methods and a few baseline methods that are trained with each frame independently, on datasets including Cityscapes, Camvid, and 300VW-Mask. We further apply our training method to video instance segmentation on YouTubeVISand develop an application of portrait matting in video sequences, by segmenting temporally consistent instance-level trimaps across frames. Experiments show superior qualitative and quantitative results. Code is available at: https://git.io/vidseg.