One major technique debt in video object segmentation is to label the object masks for training instances. As a result, we propose to prepare inexpensive, yet high quality pseudo ground truth corrected with motion cue for video object segmentation training. Our method conducts semantic segmentation using instance segmentation networks and, then, selects the segmented object of interest as the pseudo ground truth based on the motion information. Afterwards, the pseudo ground truth is exploited to finetune the pretrained objectness network to facilitate object segmentation in the remaining frames of the video. We show that the pseudo ground truth could effectively improve the segmentation performance. This straightforward unsupervised video object segmentation method is more efficient than existing methods. Experimental results on DAVIS and FBMS show that the proposed method outperforms state-of-the-art unsupervised segmentation methods on various benchmark datasets. And the category-agnostic pseudo ground truth has great potential to extend to multiple arbitrary object tracking.
Weakly-supervised instance segmentation, which could greatly save labor and time cost of pixel mask annotation, has attracted increasing attention in recent years. The commonly used pipeline firstly utilizes conventional image segmentation methods to automatically generate initial masks and then use them to train an off-the-shelf segmentation network in an iterative way. However, the initial generated masks usually contains a notable proportion of invalid masks which are mainly caused by small object instances. Directly using these initial masks to train segmentation model is harmful for the performance. To address this problem, we propose a hybrid network in this paper. In our architecture, there is a principle segmentation network which is used to handle the normal samples with valid generated masks. In addition, a complementary branch is added to handle the small and dim objects without valid masks. Experimental results indicate that our method can achieve significantly performance improvement both on the small object instances and large ones, and outperforms all state-of-the-art methods.
We introduce a novel 3D object proposal approach named Generative Shape Proposal Network (GSPN) for instance segmentation in point cloud data. Instead of treating object proposal as a direct bounding box regression problem, we take an analysis-by-synthesis strategy and generate proposals by reconstructing shapes from noisy observations in a scene. We incorporate GSPN into a novel 3D instance segmentation framework named Region-based PointNet (R-PointNet) which allows flexible proposal refinement and instance segmentation generation. We achieve state-of-the-art performance on several 3D instance segmentation tasks. The success of GSPN largely comes from its emphasis on geometric understandings during object proposal, which greatly reducing proposals with low objectness.
In interactive instance segmentation, users give feedback to iteratively refine segmentation masks. The user-provided clicks are transformed into guidance maps which provide the network with necessary cues on the whereabouts of the object of interest. Guidance maps used in current systems are purely distance-based and are either too localized or non-informative. We propose a novel transformation of user clicks to generate scale-aware guidance maps that leverage the hierarchical structural information present in an image. Using our guidance maps, even the most basic FCNs are able to outperform existing approaches that require state-of-the-art segmentation networks pre-trained on large scale segmentation datasets. We demonstrate the effectiveness of our proposed transformation strategy through comprehensive experimentation in which we significantly raise state-of-the-art on four standard interactive segmentation benchmarks.
We present PartNet: a consistent, large-scale dataset of 3D objects annotated with fine-grained, instance-level, and hierarchical 3D part information. Our dataset consists of 573,585 part instances over 26,671 3D models covering 24 object categories. This dataset enables and serves as a catalyst for many tasks such as shape analysis, dynamic 3D scene modeling and simulation, affordance analysis, and others. Using our dataset, we establish three benchmarking tasks for evaluating 3D part recognition: fine-grained semantic segmentation, hierarchical semantic segmentation, and instance segmentation. We benchmark four state-of-the-art 3D deep learning algorithms for fine-grained semantic segmentation and three baseline methods for hierarchical semantic segmentation. We also propose a novel method for part instance segmentation and demonstrate its superior performance over existing methods.
Dot-product attention has wide applications in computer vision and natural language processing. However, its memory and computational costs grow quadratically with the input size. Such growth prohibits its application on high-resolution inputs. To remedy this drawback, this paper proposes a novel efficient attention mechanism equivalent to dot-product attention but with substantially less memory and computational costs. Its resource efficiency allows more widespread and flexible integration of attention modules into a network, which leads to better accuracies. Empirical evaluations demonstrated the effectiveness of its advantages. Efficient attention modules brought significant performance boosts to object detectors and instance segmenters on MS-COCO 2017. Further, the resource efficiency democratizes attention to complex models, where high costs prohibit the use of dot-product attention. As an exemplar, a model with efficient attention achieved state-of-the-art accuracies for stereo depth estimation on the Scene Flow dataset. Code is available at https://github.com/cmsflash/efficient-attention.
We propose an end-to-end learning approach for panoptic segmentation, a novel task unifying instance (things) and semantic (stuff) segmentation. Our model, TASCNet, uses feature maps from a shared backbone network to predict in a single feed-forward pass both things and stuff segmentations. We explicitly constrain these two output distributions through a global things and stuff binary mask to enforce cross-task consistency. Our proposed unified network is competitive with the state of the art on several benchmarks for panoptic segmentation as well as on the individual semantic and instance segmentation tasks.
Pixel-accurate tracking of objects is a key element in many computer vision applications, often solved by iterated individual object tracking or instance segmentation followed by object matching. Here we introduce cross-classification clustering (3C), a technique that simultaneously tracks complex, interrelated objects in an image stack. The key idea in cross-classification is to efficiently turn a clustering problem into a classification problem by running a logarithmic number of independent classifications per image, letting the cross-labeling of these classifications uniquely classify each pixel to the object labels. We apply the 3C mechanism to achieve state-of-the-art accuracy in connectomics -- the nanoscale mapping of neural tissue from electron microscopy volumes. Our reconstruction system increases scalability by an order of magnitude over existing single-object tracking methods (such as flood-filling networks). This scalability is important for the deployment of connectomics pipelines, since currently the best performing techniques require computing infrastructures that are beyond the reach of most laboratories. Our algorithm may offer benefits in other domains that require pixel-accurate tracking of multiple objects, such as segmentation of videos and medical imagery.
In this paper, we propose a novel scene text detection method named TextMountain. The key idea of TextMountain is making full use of border-center information. Different from previous works that treat center-border as a binary classification problem, we predict text center-border probability (TCBP) and text center-direction (TCD). The TCBP is just like a mountain whose top is text center and foot is text border. The mountaintop can separate text instances which cannot be easily achieved using semantic segmentation map and its rising direction can plan a road to top for each pixel on mountain foot at the group stage. The TCD helps TCBP learning better. Our label rules will not lead to the ambiguous problem with the transformation of angle, so the proposed method is robust to multi-oriented text and can also handle well with curved text. In inference stage, each pixel at the mountain foot needs to search the path to the mountaintop and this process can be efficiently completed in parallel, yielding the efficiency of our method compared with others. The experiments on MLT, ICDAR2015, RCTW-17 and SCUT-CTW1500 databases demonstrate that the proposed method achieves better or comparable performance in terms of both accuracy and efficiency. It is worth mentioning our method achieves an F-measure of 76.85% on MLT which outperforms the previous methods by a large margin. Code will be made available.
Contextual information is vital in visual understanding problems, such as semantic segmentation and object detection. We propose a Criss-Cross Network (CCNet) for obtaining full-image contextual information in a very effective and efficient way. Concretely, for each pixel, a novel criss-cross attention module harvests the contextual information of all the pixels on its criss-cross path. By taking a further recurrent operation, each pixel can finally capture the full-image dependencies. Besides, a category consistent loss is proposed to enforce the criss-cross attention module to produce more discriminative features. Overall, CCNet is with the following merits: 1) GPU memory friendly. Compared with the non-local block, the proposed recurrent criss-cross attention module requires 11x less GPU memory usage. 2) High computational efficiency. The recurrent criss-cross attention significantly reduces FLOPs by about 85% of the non-local block. 3) The state-of-the-art performance. We conduct extensive experiments on semantic segmentation benchmarks including Cityscapes, ADE20K, human parsing benchmark LIP, instance segmentation benchmark COCO, video segmentation benchmark CamVid. In particular, our CCNet achieves the mIoU scores of 81.9%, 45.76% and 55.47% on the Cityscapes test set, the ADE20K validation set and the LIP validation set respectively, which are the new state-of-the-art results. The source codes are available at \url{https://github.com/speedinghzl/CCNet}.
We tackle the problem of one-shot instance segmentation: Given an example image of a novel, previously unknown object category, find and segment all objects of this category within a complex scene. To address this challenging new task, we propose Siamese Mask R-CNN. It extends Mask R-CNN by a Siamese backbone encoding both reference image and scene, allowing it to target detection and segmentation towards the reference category. We demonstrate empirical results on MS Coco highlighting challenges of the one-shot setting: while transferring knowledge about instance segmentation to novel object categories works very well, targeting the detection network towards the reference category appears to be more difficult. Our work provides a first strong baseline for one-shot instance segmentation and will hopefully inspire further research into more powerful and flexible scene analysis algorithms. Code is available at: https://github.com/bethgelab/siamese-mask-rcnn
We present an instance segmentation scheme based on pixel affinity information, which is the relationship of two pixels belonging to a same instance. In our scheme, we use two neural networks with similar structure. One is to predict pixel level semantic score and the other is designed to derive pixel affinities. Regarding pixels as the vertexes and affinities as edges, we then propose a simple yet effective graph merge algorithm to cluster pixels into instances. Experimental results show that our scheme can generate fine-grained instance mask. With Cityscapes training data, the proposed scheme achieves 27.3 AP on test set.
The superior performance of Deformable Convolutional Networks arises from its ability to adapt to the geometric variations of objects. Through an examination of its adaptive behavior, we observe that while the spatial support for its neural features conforms more closely than regular ConvNets to object structure, this support may nevertheless extend well beyond the region of interest, causing features to be influenced by irrelevant image content. To address this problem, we present a reformulation of Deformable ConvNets that improves its ability to focus on pertinent image regions, through increased modeling power and stronger training. The modeling power is enhanced through a more comprehensive integration of deformable convolution within the network, and by introducing a modulation mechanism that expands the scope of deformation modeling. To effectively harness this enriched modeling capability, we guide network training via a proposed feature mimicking scheme that helps the network to learn features that reflect the object focus and classification power of R-CNN features. With the proposed contributions, this new version of Deformable ConvNets yields significant performance gains over the original model and produces leading results on the COCO benchmark for object detection and instance segmentation.
Auxiliary information can be exploited in machine learning models using the paradigm of evidence based conditional inference. Multi-modal techniques in Deep Neural Networks (DNNs) can be seen as perturbing the latent feature representation for incorporating evidence from the auxiliary modality. However, they require training a specialized network which can map sparse evidence to a high dimensional latent space vector. Designing such a network, as well as collecting jointly labeled data for training is a non-trivial task. In this paper, we present a novel multi-task learning (MTL) based framework to perform evidence based conditional inference in DNNs which can overcome both these shortcomings. Our framework incorporates evidence as the output of secondary task(s), while modeling the original problem as the primary task of interest. During inference, we employ a novel Bayesian formulation to change the joint latent feature representation so as to maximize the probability of the observed evidence. Since our approach models evidence as prediction from a DNN, this can often be achieved using standard pre-trained backbones for popular tasks, eliminating the need for training altogether. Even when training is required, our MTL architecture ensures the same can be done without any need for jointly labeled data. Exploiting evidence using our framework, we show an improvement of 3.9% over the state-of-the-art, for predicting semantic segmentation given the image tags, and 2.8% for predicting instance segmentation given image captions.
We present a generic and flexible module that encodes region proposals by both their intrinsic features and the extrinsic correlations to the others. The proposed non-local region of interest (NL-RoI) can be seamlessly adapted into different generalized R-CNN architectures to better address various perception tasks. Observe that existing techniques from R-CNN treat RoIs independently and perform the prediction solely based on image features within each region proposal. However, the pairwise relationships between proposals could further provide useful information for detection and segmentation. NL-RoI is thus formulated to enrich each RoI representation with the information from all other RoIs, and yield a simple, low-cost, yet effective module for region-based convolutional networks. Our experimental results show that NL-RoI can improve the performance of Faster/Mask R-CNN for object detection and instance segmentation.
While training on samples drawn from independent and identical distribution has been a de facto paradigm for optimizing image classification networks, humans learn new concepts in an easy-to-hard manner and on the selected examples progressively. Driven by this fact, we investigate the training paradigms where the samples are not drawn from independent and identical distribution. We propose a data sampling strategy, named Drop-and-Refresh (DaR), motivated by the learning behaviors of humans that selectively drop easy samples and refresh them only periodically. We show in our experiments that the proposed DaR strategy can maintain (and in many cases improve) the predictive accuracy even when the training cost is reduced by 15% on various datasets (CIFAR 10, CIFAR 100 and ImageNet) and with different backbone architectures (ResNets, DenseNets and MobileNets). Furthermore and perhaps more importantly, we find the ImageNet pre-trained models using our DaR sampling strategy achieves better transferability for the downstream tasks including object detection (+0.3 AP), instance segmentation (+0.3 AP), scene parsing (+0.5 mIoU) and human pose estimation (+0.6 AP). Our investigation encourages people to rethink the connections between the sampling strategy for training and the transferability of its learned features for pre-training ImageNet models.
Scene text detection methods based on deep learning have achieved remarkable results over the past years. However, due to the high diversity and complexity of natural scenes, previous state-of-the-art text detection methods may still produce a considerable amount of false positives, when applied to images captured in real-world environments. To tackle this issue, mainly inspired by Mask R-CNN, we propose in this paper an effective model for scene text detection, which is based on Feature Pyramid Network (FPN) and instance segmentation. We propose a supervised pyramid context network (SPCNET) to precisely locate text regions while suppressing false positives. Benefited from the guidance of semantic information and sharing FPN, SPCNET obtains significantly enhanced performance while introducing marginal extra computation. Experiments on standard datasets demonstrate that our SPCNET clearly outperforms start-of-the-art methods. Specifically, it achieves an F-measure of 92.1% on ICDAR2013, 87.2% on ICDAR2015, 74.1% on ICDAR2017 MLT and 82.9% on Total-Text.
We report competitive results on object detection and instance segmentation on the COCO dataset using standard models trained from random initialization. The results are no worse than their ImageNet pre-training counterparts even when using the hyper-parameters of the baseline system (Mask R-CNN) that were optimized for fine-tuning pre-trained models, with the sole exception of increasing the number of training iterations so the randomly initialized models may converge. Training from random initialization is surprisingly robust; our results hold even when: (i) using only 10% of the training data, (ii) for deeper and wider models, and (iii) for multiple tasks and metrics. Experiments show that ImageNet pre-training speeds up convergence early in training, but does not necessarily provide regularization or improve final target task accuracy. To push the envelope we demonstrate 50.9 AP on COCO object detection without using any external data---a result on par with the top COCO 2017 competition results that used ImageNet pre-training. These observations challenge the conventional wisdom of ImageNet pre-training for dependent tasks and we expect these discoveries will encourage people to rethink the current de facto paradigm of `pre-training and fine-tuning' in computer vision.
More than one billion people live in slums around the world. In some developing countries, slum residents make up for more than half of the population and lack reliable sanitation services, clean water, electricity, other basic services. Thus, slum rehabilitation and improvement is an important global challenge, and a significant amount of effort and resources have been put into this endeavor. These initiatives rely heavily on slum mapping and monitoring, and it is essential to have robust and efficient methods for mapping and monitoring existing slum settlements. In this work, we introduce an approach to segment and map individual slums from satellite imagery, leveraging regional convolutional neural networks for instance segmentation using transfer learning. In addition, we also introduce a method to perform change detection and monitor slum change over time. We show that our approach effectively learns slum shape and appearance, and demonstrates strong quantitative results, resulting in a maximum AP of 80.0.
We address the issue of domain gap when making use of synthetic data to train a scene-specific object detector and pose estimator. While previous works have shown that the constraints of learning a scene-specific model can be leveraged to create geometrically and photometrically consistent synthetic data, care must be taken to design synthetic content which is as close as possible to the real-world data distribution. In this work, we propose to solve domain gap through the use of appearance randomization to generate a wide range of synthetic objects to span the space of realistic images for training. An ablation study of our results is presented to delineate the individual contribution of different components in the randomization process. We evaluate our method on VIRAT, UA-DETRAC, EPFL-Car datasets, where we demonstrate that using scene specific domain randomized synthetic data is better than fine-tuning off-the-shelf models on limited real data.