Existing weakly or semi-supervised semantic segmentation methods utilize image or box-level supervision to generate pseudo-labels for weakly labeled images. However, due to the lack of strong supervision, the generated pseudo-labels are often noisy near the object boundaries, which severely impacts the network's ability to learn strong representations. To address this problem, we present a novel framework that generates pseudo-labels for training images, which are then used to train a segmentation model. To generate pseudo-labels, we combine information from: (i) a class agnostic objectness network that learns to recognize object-like regions, and (ii) either image-level or bounding box annotations. We show the efficacy of our approach by demonstrating how the objectness network can naturally be leveraged to generate object-like regions for unseen categories. We then propose an end-to-end multi-task learning strategy, that jointly learns to segment semantics and objectness using the generated pseudo-labels. Extensive experiments demonstrate the high quality of our generated pseudo-labels and effectiveness of the proposed framework in a variety of domains. Our approach achieves better or competitive performance compared to existing weakly-supervised and semi-supervised methods.
We describe our two-stage instance segmentation framework we use to compete in the challenge. The first stage of our framework consists of an object detector, which generates object proposals in the format of bounding boxes. Then, the images and the detected bounding boxes are fed to the second stage, where a segmentation network is applied to segment the objects in the bounding boxes. We train all our networks in a class-agnostic way. Our approach achieves the first place in the UVO 2021 Image-based Open-World Segmentation Challenge.
Every hand-object interaction begins with contact. Despite predicting the contact state between hands and objects is useful in understanding hand-object interactions, prior methods on hand-object analysis have assumed that the interacting hands and objects are known, and were not studied in detail. In this study, we introduce a video-based method for predicting contact between a hand and an object. Specifically, given a video and a pair of hand and object tracks, we predict a binary contact state (contact or no-contact) for each frame. However, annotating a large number of hand-object tracks and contact labels is costly. To overcome the difficulty, we propose a semi-supervised framework consisting of (i) automatic collection of training data with motion-based pseudo-labels and (ii) guided progressive label correction (gPLC), which corrects noisy pseudo-labels with a small amount of trusted data. We validated our framework's effectiveness on a newly built benchmark dataset for hand-object contact prediction and showed superior performance against existing baseline methods. Code and data are available at https://github.com/takumayagi/hand_object_contact_prediction.
We propose a method for multi-object tracking and segmentation based on a novel memory-based mechanism to associate tracklets. The proposed tracker, MeNToS, addresses particularly the long-term data association problem, when objects are not observable for long time intervals. Indeed, the recently introduced HOTA metric (High Order Tracking Accuracy), which has a better alignment than the formerly established MOTA (Multiple Object Tracking Accuracy) with the human visual assessment of tracking, has shown that improvements are still needed for data association, despite the recent improvement in object detection. In MeNToS, after creating tracklets using instance segmentation and optical flow, the proposed method relies on a space-time memory network originally developed for one-shot video object segmentation to improve the association of sequence of detections (tracklets) with temporal gaps. We evaluate our tracker on KITTIMOTS and MOTSChallenge and we show the benefit of our data association strategy with the HOTA metric. Additional ablation studies demonstrate that our approach using a space-time memory network gives better and more robust long-term association than those based on a re-identification network. Our project page is at \url{www.mehdimiah.com/mentos+}.
Recently, learning frameworks have shown the capability of inferring the accurate shape, pose, and texture of an object from a single RGB image. However, current methods are trained on image collections of a single category in order to exploit specific priors, and they often make use of category-specific 3D templates. In this paper, we present an alternative approach that infers the textured mesh of objects combining a series of deformable 3D models and a set of instance-specific deformation, pose, and texture. Differently from previous works, our method is trained with images of multiple object categories using only foreground masks and rough camera poses as supervision. Without specific 3D templates, the framework learns category-level models which are deformed to recover the 3D shape of the depicted object. The instance-specific deformations are predicted independently for each vertex of the learned 3D mesh, enabling the dynamic subdivision of the mesh during the training process. Experiments show that the proposed framework can distinguish between different object categories and learn category-specific shape priors in an unsupervised manner. Predicted shapes are smooth and can leverage from multiple steps of subdivision during the training process, obtaining comparable or state-of-the-art results on two public datasets. Models and code are publicly released.
Accurate 7DoF prediction of vehicles at an intersection is an important task for assessing potential conflicts between road users. In principle, this could be achieved by a single camera system that is capable of detecting the pose of each vehicle but this would require a large, accurately labelled dataset from which to train the detector. Although large vehicle pose datasets exist (ostensibly developed for autonomous vehicles), we find training on these datasets inadequate. These datasets contain images from a ground level viewpoint, whereas an ideal view for intersection observation would be elevated higher above the road surface. We develop an alternative approach using a weakly supervised method of fine tuning 3D object detectors for traffic observation cameras; showing in the process that large existing autonomous vehicle datasets can be leveraged for pre-training. To fine-tune the monocular 3D object detector, our method utilises multiple 2D detections from overlapping, wide-baseline views and a loss that encodes the subjacent geometric consistency. Our method achieves vehicle 7DoF pose prediction accuracy on our dataset comparable to the top performing monocular 3D object detectors on autonomous vehicle datasets. We present our training methodology, multi-view reprojection loss, and dataset.
Limited by the performance factor, it is arduous to recognize target object and locate it in Augmented Reality (AR) scenes on low-end mobile devices, especially which using monocular cameras. In this paper, we proposed an algorithm which can quickly locate the target object through image object detection in the circumstances of having very sparse feature points. We introduce YOLOv3-Tiny to our algorithm as the object detection module to filter the possible points and using Principal Component Analysis (PCA) to determine the location. We conduct the experiment in a manually designed scene by holding a smartphone and the results represent high positioning speed and accuracy of our method.
Instance segmentation is a challenging task aiming at classifying and segmenting all object instances of specific classes. While two-stage box-based methods achieve top performances in the image domain, they cannot easily extend their superiority into the video domain. This is because they usually deal with features or images cropped from the detected bounding boxes without alignment, failing to capture pixel-level temporal consistency. We embrace the observation that bottom-up methods dealing with box-free features could offer accurate spacial correlations across frames, which can be fully utilized for object and pixel level tracking. We first propose our bottom-up framework equipped with a temporal context fusion module to better encode inter-frame correlations. Intra-frame cues for semantic segmentation and object localization are simultaneously extracted and reconstructed by corresponding decoders after a shared backbone. For efficient and robust tracking among instances, we introduce an instance-level correspondence across adjacent frames, which is represented by a center-to-center flow, termed as instance flow, to assemble messy dense temporal correspondences. Experiments demonstrate that the proposed method outperforms the state-of-the-art online methods (taking image-level input) on the challenging Youtube-VIS dataset.
Supervised training of object detectors requires well-annotated large-scale datasets, whose production is costly. Therefore, some efforts have been made to obtain annotations in economical ways, such as cloud sourcing. However, datasets obtained by these methods tend to contain noisy annotations such as inaccurate bounding boxes and incorrect class labels. In this study, we propose a new problem setting of training object detectors on datasets with entangled noises of annotations of class labels and bounding boxes. Our proposed method efficiently decouples the entangled noises, corrects the noisy annotations, and subsequently trains the detector using the corrected annotations. We verified the effectiveness of our proposed method and compared it with the baseline on noisy datasets with different noise levels. The experimental results show that our proposed method significantly outperforms the baseline.
Geometric organization of objects into semantically meaningful arrangements pervades the built world. As such, assistive robots operating in warehouses, offices, and homes would greatly benefit from the ability to recognize and rearrange objects into these semantically meaningful structures. To be useful, these robots must contend with previously unseen objects and receive instructions without significant programming. While previous works have examined recognizing pairwise semantic relations and sequential manipulation to change these simple relations none have shown the ability to arrange objects into complex structures such as circles or table settings. To address this problem we propose a novel transformer-based neural network, StructFormer, which takes as input a partial-view point cloud of the current object arrangement and a structured language command encoding the desired object configuration. We show through rigorous experiments that StructFormer enables a physical robot to rearrange novel objects into semantically meaningful structures with multi-object relational constraints inferred from the language command.
Reconstructing the 3D geometry of an object from an image is a major challenge in computer vision. Recently introduced differentiable renderers can be leveraged to learn the 3D geometry of objects from 2D images, but those approaches require additional supervision to enable the renderer to produce an output that can be compared to the input image. This can be scene information or constraints such as object silhouettes, uniform backgrounds, material, texture, and lighting. In this paper, we propose an approach that enables a differentiable rendering-based learning of 3D objects from images with backgrounds without the need for silhouette supervision. Instead of trying to render an image close to the input, we propose an adversarial style-transfer and domain adaptation pipeline that allows to translate the input image domain to the rendered image domain. This allows us to directly compare between a translated image and the differentiable rendering of a 3D object reconstruction in order to train the 3D object reconstruction network. We show that the approach learns 3D geometry from images with backgrounds and provides a better performance than constrained methods for single-view 3D object reconstruction on this task.
Wide Area Motion Imagery (WAMI) yields high-resolution images with a large number of extremely small objects. Target objects have large spatial displacements throughout consecutive frames. This nature of WAMI images makes object tracking and detection challenging. In this paper, we present our deep neural network-based combined object detection and tracking model, namely, Heat Map Network (HM-Net). HM-Net is significantly faster than state-of-the-art frame differencing and background subtraction-based methods, without compromising detection and tracking performances. HM-Net follows the object center-based joint detection and tracking paradigm. Simple heat map-based predictions support an unlimited number of simultaneous detections. The proposed method uses two consecutive frames and the object detection heat map obtained from the previous frame as input, which helps HM-Net monitor spatio-temporal changes between frames and keeps track of previously predicted objects. Although reuse of prior object detection heat map acts as a vital feedback-based memory element, it can lead to an unintended surge of false-positive detections. To increase the robustness of the method against false positives and to eliminate low confidence detections, HM-Net employs novel feedback filters and advanced data augmentations. HM-Net outperforms state-of-the-art WAMI moving object detection and tracking methods on the WPAFB dataset with its 96.2% F1 and 94.4% mAP detection scores while achieving a 61.8% mAP tracking score on the same dataset. This performance corresponds to an improvement of 2.1% for F1, 6.1% for mAP scores on detection, and 9.5% for mAP score on tracking over the state-of-the-art.
We present SSOD, the first end-to-end analysis-by synthesis framework with controllable GANs for the task of self-supervised object detection. We use collections of real world images without bounding box annotations to learn to synthesize and detect objects. We leverage controllable GANs to synthesize images with pre-defined object properties and use them to train object detectors. We propose a tight end-to-end coupling of the synthesis and detection networks to optimally train our system. Finally, we also propose a method to optimally adapt SSOD to an intended target data without requiring labels for it. For the task of car detection, on the challenging KITTI and Cityscapes datasets, we show that SSOD outperforms the prior state-of-the-art purely image-based self-supervised object detection method Wetectron. Even without requiring any 3D CAD assets, it also surpasses the state-of-the-art rendering based method Meta-Sim2. Our work advances the field of self-supervised object detection by introducing a successful new paradigm of using controllable GAN-based image synthesis for it and by significantly improving the baseline accuracy of the task. We open-source our code at https://github.com/NVlabs/SSOD.
In realistic applications of object search, robots will need to locate target objects in complex environments while coping with unreliable sensors, especially for small or hard-to-detect objects. In such settings, correlational information can be valuable for planning efficiently. Previous approaches that consider correlational information typically resort to ad-hoc, greedy search strategies. We introduce the Correlational Object Search POMDP (COS-POMDP), which models correlations while preserving optimal solutions with a reduced state space. We propose a hierarchical planning algorithm to scale up COS-POMDPs for practical domains. Our evaluation, conducted with the AI2-THOR household simulator and the YOLOv5 object detector, shows that our method finds objects more successfully and efficiently compared to baselines,particularly for hard-to-detect objects such as srub brush and remote control.
Counting objects is a fundamental but challenging problem. In this paper, we propose diffusion-based, geometry-free, and learning-free methodologies to count the number of objects in images. The main idea is to represent each object by a unique index value regardless of its intensity or size, and to simply count the number of index values. First, we place different vectors, refer to as seed vectors, uniformly throughout the mask image. The mask image has boundary information of the objects to be counted. Secondly, the seeds are diffused using an edge-weighted harmonic variational optimization model within each object. We propose an efficient algorithm based on an operator splitting approach and alternating direction minimization method, and theoretical analysis of this algorithm is given. An optimal solution of the model is obtained when the distributed seeds are completely diffused such that there is a unique intensity within each object, which we refer to as an index. For computational efficiency, we stop the diffusion process before a full convergence, and propose to cluster these diffused index values. We refer to this approach as Counting Objects by Diffused Index (CODI). We explore scalar and multi-dimensional seed vectors. For Scalar seeds, we use Gaussian fitting in histogram to count, while for vector seeds, we exploit a high-dimensional clustering method for the final step of counting via clustering. The proposed method is flexible even if the boundary of the object is not clear nor fully enclosed. We present counting results in various applications such as biological cells, agriculture, concert crowd, and transportation. Some comparisons with existing methods are presented.
In the field of autonomous driving, self-training is widely applied to mitigate distribution shifts in LiDAR-based 3D object detectors. This eliminates the need for expensive, high-quality labels whenever the environment changes (e.g., geographic location, sensor setup, weather condition). State-of-the-art self-training approaches, however, mostly ignore the temporal nature of autonomous driving data. To address this issue, we propose a flow-aware self-training method that enables unsupervised domain adaptation for 3D object detectors on continuous LiDAR point clouds. In order to get reliable pseudo-labels, we leverage scene flow to propagate detections through time. In particular, we introduce a flow-based multi-target tracker, that exploits flow consistency to filter and refine resulting tracks. The emerged precise pseudo-labels then serve as a basis for model re-training. Starting with a pre-trained KITTI model, we conduct experiments on the challenging Waymo Open Dataset to demonstrate the effectiveness of our approach. Without any prior target domain knowledge, our results show a significant improvement over the state-of-the-art.
Weakly supervised object detection (WSOD) is a challenging task that requires simultaneously learn object classifiers and estimate object locations under the supervision of image category labels. A major line of WSOD methods roots in multiple instance learning which regards images as bags of instances and selects positive instances from each bag to learn the detector. However, a grand challenge emerges when the detector inclines to converge to discriminative parts of objects rather than the whole objects. In this paper, under the hypothesis that optimal solutions are included in local minima, we propose a discovery-and-selection approach fused with multiple instance learning (DS-MIL), which finds rich local minima and select optimal solution from multiple local minima. To implement DS-MIL, an attention module is proposed so that more context information can be captured by feature maps and more valuable proposals can be collected during training. With proposal candidates, a selection module is proposed to select informative instances for object detector. Experimental results on commonly used benchmarks show that our proposed DS-MIL approach can consistently improve the baselines, reporting state-of-the-art performance.
Object-oriented SLAM is a popular technology in autonomous driving and robotics. In this paper, we propose a stereo visual SLAM with a robust quadric landmark representation method. The system consists of four components, including deep learning detection, object-oriented data association, dual quadric landmark initialization and object-based pose optimization. State-of-the-art quadric-based SLAM algorithms always face observation related problems and are sensitive to observation noise, which limits their application in outdoor scenes. To solve this problem, we propose a quadric initialization method based on the decoupling of the quadric parameters method, which improves the robustness to observation noise. The sufficient object data association algorithm and object-oriented optimization with multiple cues enables a highly accurate object pose estimation that is robust to local observations. Experimental results show that the proposed system is more robust to observation noise and significantly outperforms current state-of-the-art methods in outdoor environments. In addition, the proposed system demonstrates real-time performance.
We introduce MeronymNet, a novel hierarchical approach for controllable, part-based generation of multi-category objects using a single unified model. We adopt a guided coarse-to-fine strategy involving semantically conditioned generation of bounding box layouts, pixel-level part layouts and ultimately, the object depictions themselves. We use Graph Convolutional Networks, Deep Recurrent Networks along with custom-designed Conditional Variational Autoencoders to enable flexible, diverse and category-aware generation of 2-D objects in a controlled manner. The performance scores for generated objects reflect MeronymNet's superior performance compared to multiple strong baselines and ablative variants. We also showcase MeronymNet's suitability for controllable object generation and interactive object editing at various levels of structural and semantic granularity.
Reasoning is an essential part of human intelligence and thus has been a long-standing goal in artificial intelligence research. With the recent success of deep learning, incorporating reasoning with deep learning systems, i.e., neuro-symbolic AI has become a major field of interest. We propose the Neuro-Symbolic Forward Reasoner (NSFR), a new approach for reasoning tasks taking advantage of differentiable forward-chaining using first-order logic. The key idea is to combine differentiable forward-chaining reasoning with object-centric (deep) learning. Differentiable forward-chaining reasoning computes logical entailments smoothly, i.e., it deduces new facts from given facts and rules in a differentiable manner. The object-centric learning approach factorizes raw inputs into representations in terms of objects. Thus, it allows us to provide a consistent framework to perform the forward-chaining inference from raw inputs. NSFR factorizes the raw inputs into the object-centric representations, converts them into probabilistic ground atoms, and finally performs differentiable forward-chaining inference using weighted rules for inference. Our comprehensive experimental evaluations on object-centric reasoning data sets, 2D Kandinsky patterns and 3D CLEVR-Hans, and a variety of tasks show the effectiveness and advantage of our approach.