Unsupervised domain adaptation (UDA) enables a learning machine to adapt from a labeled source domain to an unlabeled domain under the distribution shift. Thanks to the strong representation ability of deep neural networks, recent remarkable achievements in UDA resort to learning domain-invariant features. Intuitively, the hope is that a good feature representation, together with the hypothesis learned from the source domain, can generalize well to the target domain. However, the learning processes of domain-invariant features and source hypothesis inevitably involve domain-specific information that would degrade the generalizability of UDA models on the target domain. In this paper, motivated by the lottery ticket hypothesis that only partial parameters are essential for generalization, we find that only partial parameters are essential for learning domain-invariant information and generalizing well in UDA. Such parameters are termed transferable parameters. In contrast, the other parameters tend to fit domain-specific details and often fail to generalize, which we term as untransferable parameters. Driven by this insight, we propose Transferable Parameter Learning (TransPar) to reduce the side effect brought by domain-specific information in the learning process and thus enhance the memorization of domain-invariant information. Specifically, according to the distribution discrepancy degree, we divide all parameters into transferable and untransferable ones in each training iteration. We then perform separate updates rules for the two types of parameters. Extensive experiments on image classification and regression tasks (keypoint detection) show that TransPar outperforms prior arts by non-trivial margins. Moreover, experiments demonstrate that TransPar can be integrated into the most popular deep UDA networks and be easily extended to handle any data distribution shift scenarios.
Unsupervised learning is just at a tipping point where it could really take off. Among these approaches, contrastive learning has seen tremendous progress and led to state-of-the-art performance. In this paper, we construct a novel probabilistic graphical model that effectively incorporates the low rank promoting prior into the framework of contrastive learning, referred to as LORAC. In contrast to the existing conventional self-supervised approaches that only considers independent learning, our hypothesis explicitly requires that all the samples belonging to the same instance class lie on the same subspace with small dimension. This heuristic poses particular joint learning constraints to reduce the degree of freedom of the problem during the search of the optimal network parameterization. Most importantly, we argue that the low rank prior employed here is not unique, and many different priors can be invoked in a similar probabilistic way, corresponding to different hypotheses about underlying truth behind the contrastive features. Empirical evidences show that the proposed algorithm clearly surpasses the state-of-the-art approaches on multiple benchmarks, including image classification, object detection, instance segmentation and keypoint detection.
The combination of a small unmanned ground vehicle (UGV) and a large unmanned carrier vehicle allows more flexibility in real applications such as rescue in dangerous scenarios. The autonomous recovery system, which is used to guide the small UGV back to the carrier vehicle, is an essential component to achieve a seamless combination of the two vehicles. This paper proposes a novel autonomous recovery framework with a low-cost monocular vision system to provide accurate positioning and attitude estimation of the UGV during navigation. First, we introduce a light-weight convolutional neural network called UGV-KPNet to detect the keypoints of the small UGV from the images captured by a monocular camera. UGV-KPNet is computationally efficient with a small number of parameters and provides pixel-level accurate keypoints detection results in real-time. Then, six degrees of freedom pose is estimated using the detected keypoints to obtain positioning and attitude information of the UGV. Besides, we are the first to create a large-scale real-world keypoints dataset of the UGV. The experimental results demonstrate that the proposed system achieves state-of-the-art performance in terms of both accuracy and speed on UGV keypoint detection, and can further boost the 6-DoF pose estimation for the UGV.
By considering the spatial correspondence, dense self-supervised representation learning has achieved superior performance on various dense prediction tasks. However, the pixel-level correspondence tends to be noisy because of many similar misleading pixels, e.g., backgrounds. To address this issue, in this paper, we propose to explore \textbf{set} \textbf{sim}ilarity (SetSim) for dense self-supervised representation learning. We generalize pixel-wise similarity learning to set-wise one to improve the robustness because sets contain more semantic and structure information. Specifically, by resorting to attentional features of views, we establish corresponding sets, thus filtering out noisy backgrounds that may cause incorrect correspondences. Meanwhile, these attentional features can keep the coherence of the same image across different views to alleviate semantic inconsistency. We further search the cross-view nearest neighbours of sets and employ the structured neighbourhood information to enhance the robustness. Empirical evaluations demonstrate that SetSim is superior to state-of-the-art methods on object detection, keypoint detection, instance segmentation, and semantic segmentation.
Sampling, grouping, and aggregation are three important components in the multi-scale analysis of point clouds. In this paper, we present a novel data-driven sampler learning strategy for point-wise analysis tasks. Unlike the widely used sampling technique, Farthest Point Sampling (FPS), we propose to learn sampling and downstream applications jointly. Our key insight is that uniform sampling methods like FPS are not always optimal for different tasks: sampling more points around boundary areas can make the point-wise classification easier for segmentation. Towards this end, we propose a novel sampler learning strategy that learns sampling point displacement supervised by task-related ground truth information and can be trained jointly with the underlying tasks. We further demonstrate our methods in various point-wise analysis tasks, including semantic part segmentation, point cloud completion, and keypoint detection. Our experiments show that jointly learning of the sampler and task brings better performance than using FPS in various point-based networks.
We propose a simple yet reliable bottom-up approach with a good trade-off between accuracy and efficiency for the problem of multi-person pose estimation. Given an image, we employ an Hourglass Network to infer all the keypoints from different persons indiscriminately as well as the guiding offsets connecting the adjacent keypoints belonging to the same persons. Then, we greedily group the candidate keypoints into multiple human poses (if any), utilizing the predicted guiding offsets. And we refer to this process as greedy offset-guided keypoint grouping (GOG). Moreover, we revisit the encoding-decoding method for the multi-person keypoint coordinates and reveal some important facts affecting accuracy. Experiments have demonstrated the obvious performance improvements brought by the introduced components. Our approach is comparable to the state of the art on the challenging COCO dataset under fair conditions. The source code and our pre-trained model are publicly available online.
The results obtained from state of the art human pose estimation (HPE) models degrade rapidly when evaluating people of a low resolution, but can super resolution (SR) be used to help mitigate this effect? By using various SR approaches we enhanced two low resolution datasets and evaluated the change in performance of both an object and keypoint detector as well as end-to-end HPE results. We remark the following observations. First we find that for people who were originally depicted at a low resolution (segmentation area in pixels), their keypoint detection performance would improve once SR was applied. Second, the keypoint detection performance gained is dependent on that persons pixel count in the original image prior to any application of SR; keypoint detection performance was improved when SR was applied to people with a small initial segmentation area, but degrades as this becomes larger. To address this we introduced a novel Mask-RCNN approach, utilising a segmentation area threshold to decide when to use SR during the keypoint detection step. This approach achieved the best results on our low resolution datasets for each HPE performance metrics.
Pixel-wise regression is probably the most common problem in fine-grained computer vision tasks, such as estimating keypoint heatmaps and segmentation masks. These regression problems are very challenging particularly because they require, at low computation overheads, modeling long-range dependencies on high-resolution inputs/outputs to estimate the highly nonlinear pixel-wise semantics. While attention mechanisms in Deep Convolutional Neural Networks(DCNNs) has become popular for boosting long-range dependencies, element-specific attention, such as Nonlocal blocks, is highly complex and noise-sensitive to learn, and most of simplified attention hybrids try to reach the best compromise among multiple types of tasks. In this paper, we present the Polarized Self-Attention(PSA) block that incorporates two critical designs towards high-quality pixel-wise regression: (1) Polarized filtering: keeping high internal resolution in both channel and spatial attention computation while completely collapsing input tensors along their counterpart dimensions. (2) Enhancement: composing non-linearity that directly fits the output distribution of typical fine-grained regression, such as the 2D Gaussian distribution (keypoint heatmaps), or the 2D Binormial distribution (binary segmentation masks). PSA appears to have exhausted the representation capacity within its channel-only and spatial-only branches, such that there is only marginal metric differences between its sequential and parallel layouts. Experimental results show that PSA boosts standard baselines by $2-4$ points, and boosts state-of-the-arts by $1-2$ points on 2D pose estimation and semantic segmentation benchmarks.
Robot manipulation of unknown objects in unstructured environments is a challenging problem due to the variety of shapes, materials, arrangements and lighting conditions. Even with large-scale real-world data collection, robust perception and manipulation of transparent and reflective objects across various lighting conditions remain challenging. To address these challenges we propose an approach to performing sim-to-real transfer of robotic perception. The underlying model, SimNet, is trained as a single multi-headed neural network using simulated stereo data as input and simulated object segmentation masks, 3D oriented bounding boxes (OBBs), object keypoints, and disparity as output. A key component of SimNet is the incorporation of a learned stereo sub-network that predicts disparity. SimNet is evaluated on 2D car detection, unknown object detection, and deformable object keypoint detection and significantly outperforms a baseline that uses a structured light RGB-D sensor. By inferring grasp positions using the OBB and keypoint predictions, SimNet can be used to perform end-to-end manipulation of unknown objects in both easy and hard scenarios using our fleet of Toyota HSR robots in four home environments. In unknown object grasping experiments, the predictions from the baseline RGB-D network and SimNet enable successful grasps of most of the easy objects. However, the RGB-D baseline only grasps 35% of the hard (e.g., transparent) objects, while SimNet grasps 95%, suggesting that SimNet can enable robust manipulation of unknown objects, including transparent objects, in unknown environments.
Rehabilitation is important to improve quality of life for mobility-impaired patients. Smart walkers are a commonly used solution that should embed automatic and objective tools for data-driven human-in-the-loop control and monitoring. However, present solutions focus on extracting few specific metrics from dedicated sensors with no unified full-body approach. We investigate a general, real-time, full-body pose estimation framework based on two RGB+D camera streams with non-overlapping views mounted on a smart walker equipment used in rehabilitation. Human keypoint estimation is performed using a two-stage neural network framework. The 2D-Stage implements a detection module that locates body keypoints in the 2D image frames. The 3D-Stage implements a regression module that lifts and relates the detected keypoints in both cameras to the 3D space relative to the walker. Model predictions are low-pass filtered to improve temporal consistency. A custom acquisition method was used to obtain a dataset, with 14 healthy subjects, used for training and evaluating the proposed framework offline, which was then deployed on the real walker equipment. An overall keypoint detection error of 3.73 pixels for the 2D-Stage and 44.05mm for the 3D-Stage were reported, with an inference time of 26.6ms when deployed on the constrained hardware of the walker. We present a novel approach to patient monitoring and data-driven human-in-the-loop control in the context of smart walkers. It is able to extract a complete and compact body representation in real-time and from inexpensive sensors, serving as a common base for downstream metrics extraction solutions, and Human-Robot interaction applications. Despite promising results, more data should be collected on users with impairments, to assess its performance as a rehabilitation tool in real-world scenarios.
Contemporary grasp detection approaches employ deep learning to achieve robustness to sensor and object model uncertainty. The two dominant approaches design either grasp-quality scoring or anchor-based grasp recognition networks. This paper presents a different approach to grasp detection by treating it as keypoint detection in image-space. The deep network detects each grasp candidate as a pair of keypoints, convertible to the grasp representationg = {x, y, w, {\theta}} T , rather than a triplet or quartet of corner points. Decreasing the detection difficulty by grouping keypoints into pairs boosts performance. To promote capturing dependencies between keypoints, a non-local module is incorporated into the network design. A final filtering strategy based on discrete and continuous orientation prediction removes false correspondences and further improves grasp detection performance. GKNet, the approach presented here, achieves a good balance between accuracy and speed on the Cornell and the abridged Jacquard datasets (96.9% and 98.39% at 41.67 and 23.26 fps). Follow-up experiments on a manipulator evaluate GKNet using 4 types of grasping experiments reflecting different nuisance sources: static grasping, dynamic grasping, grasping at varied camera angles, and bin picking. GKNet outperforms reference baselines in static and dynamic grasping experiments while showing robustness to varied camera viewpoints and moderate clutter. The results confirm the hypothesis that grasp keypoints are an effective output representation for deep grasp networks that provide robustness to expected nuisance factors.
In this paper, we present a new bottom-up one-stage method for whole-body pose estimation, which we call "hierarchical point regression," or HPRNet for short. In standard body pose estimation, the locations of $\sim 17$ major joints on the human body are estimated. Differently, in whole-body pose estimation, the locations of fine-grained keypoints (68 on face, 21 on each hand and 3 on each foot) are estimated as well, which creates a scale variance problem that needs to be addressed. To handle the scale variance among different body parts, we build a hierarchical point representation of body parts and jointly regress them. The relative locations of fine-grained keypoints in each part (e.g. face) are regressed in reference to the center of that part, whose location itself is estimated relative to the person center. In addition, unlike the existing two-stage methods, our method predicts whole-body pose in a constant time independent of the number of people in an image. On the COCO WholeBody dataset, HPRNet significantly outperforms all previous bottom-up methods on the keypoint detection of all whole-body parts (i.e. body, foot, face and hand); it also achieves state-of-the-art results on face (75.4 AP) and hand (50.4 AP) keypoint detection. Code and models are available at \url{https://github.com/nerminsamet/HPRNet}.
Vision transformer (ViT) has recently shown its strong capability in achieving comparable results to convolutional neural networks (CNNs) on image classification. However, vanilla ViT simply inherits the same architecture from the natural language processing directly, which is often not optimized for vision applications. Motivated by this, in this paper, we propose a new architecture that adopts the pyramid structure and employ a novel regional-to-local attention rather than global self-attention in vision transformers. More specifically, our model first generates regional tokens and local tokens from an image with different patch sizes, where each regional token is associated with a set of local tokens based on the spatial location. The regional-to-local attention includes two steps: first, the regional self-attention extract global information among all regional tokens and then the local self-attention exchanges the information among one regional token and the associated local tokens via self-attention. Therefore, even though local self-attention confines the scope in a local region but it can still receive global information. Extensive experiments on four vision tasks, including image classification, object and keypoint detection, semantics segmentation and action recognition, show that our approach outperforms or is on par with state-of-the-art ViT variants including many concurrent works. Our source codes and models are available at https://github.com/ibm/regionvit.
Existing multi-camera solutions for automatic scorekeeping in steel-tip darts are very expensive and thus inaccessible to most players. Motivated to develop a more accessible low-cost solution, we present a new approach to keypoint detection and apply it to predict dart scores from a single image taken from any camera angle. This problem involves detecting multiple keypoints that may be of the same class and positioned in close proximity to one another. The widely adopted framework for regressing keypoints using heatmaps is not well-suited for this task. To address this issue, we instead propose to model keypoints as objects. We develop a deep convolutional neural network around this idea and use it to predict dart locations and dartboard calibration points within an overall pipeline for automatic dart scoring, which we call DeepDarts. Additionally, we propose several task-specific data augmentation strategies to improve the generalization of our method. As a proof of concept, two datasets comprising 16k images originating from two different dartboard setups were manually collected and annotated to evaluate the system. In the primary dataset containing 15k images captured from a face-on view of the dartboard using a smartphone, DeepDarts predicted the total score correctly in 94.7% of the test images. In a second more challenging dataset containing limited training data (830 images) and various camera angles, we utilize transfer learning and extensive data augmentation to achieve a test accuracy of 84.0%. Because DeepDarts relies only on single images, it has the potential to be deployed on edge devices, giving anyone with a smartphone access to an automatic dart scoring system for steel-tip darts. The code and datasets are available.
Despite the attention marker-less pose estimation has attracted in recent years, marker-based approaches still provide unbeatable accuracy under controlled environmental conditions. Thus, they are used in many fields such as robotics or biomedical applications but are primarily implemented through classical approaches, which require lots of heuristics and parameter tuning for reliable performance under different environments. In this work, we propose MarkerPose, a robust, real-time pose estimation system based on a planar target of three circles and a stereo vision system. MarkerPose is meant for high-accuracy pose estimation applications. Our method consists of two deep neural networks for marker point detection. A SuperPoint-like network for pixel-level accuracy keypoint localization and classification, and we introduce EllipSegNet, a lightweight ellipse segmentation network for sub-pixel-level accuracy keypoint detection. The marker's pose is estimated through stereo triangulation. The target point detection is robust to low lighting and motion blur conditions. We compared MarkerPose with a detection method based on classical computer vision techniques using a robotic arm for validation. The results show our method provides better accuracy than the classical technique. Finally, we demonstrate the suitability of MarkerPose in a 3D freehand ultrasound system, which is an application where highly accurate pose estimation is required. Code is available in Python and C++ at https://github.com/jhacsonmeza/MarkerPose.
In this paper, we present a regression-based pose recognition method using cascade Transformers. One way to categorize the existing approaches in this domain is to separate them into 1). heatmap-based and 2). regression-based. In general, heatmap-based methods achieve higher accuracy but are subject to various heuristic designs (not end-to-end mostly), whereas regression-based approaches attain relatively lower accuracy but they have less intermediate non-differentiable steps. Here we utilize the encoder-decoder structure in Transformers to perform regression-based person and keypoint detection that is general-purpose and requires less heuristic design compared with the existing approaches. We demonstrate the keypoint hypothesis (query) refinement process across different self-attention layers to reveal the recursive self-attention mechanism in Transformers. In the experiments, we report competitive results for pose recognition when compared with the competing regression-based methods.
This paper presents HoughNet, a one-stage, anchor-free, voting-based, bottom-up object detection method. Inspired by the Generalized Hough Transform, HoughNet determines the presence of an object at a certain location by the sum of the votes cast on that location. Votes are collected from both near and long-distance locations based on a log-polar vote field. Thanks to this voting mechanism, HoughNet is able to integrate both near and long-range, class-conditional evidence for visual recognition, thereby generalizing and enhancing current object detection methodology, which typically relies on only local evidence. On the COCO dataset, HoughNet's best model achieves $46.4$ $AP$ (and $65.1$ $AP_{50}$), performing on par with the state-of-the-art in bottom-up object detection and outperforming most major one-stage and two-stage methods. We further validate the effectiveness of our proposal in other visual detection tasks, namely, video object detection, instance segmentation, 3D object detection and keypoint detection for human pose estimation, and an additional "labels to photo" image generation task, where the integration of our voting module consistently improves performance in all cases. Code is available at https://github.com/nerminsamet/houghnet.
We introduce DexYCB, a new dataset for capturing hand grasping of objects. We first compare DexYCB with a related one through cross-dataset evaluation. We then present a thorough benchmark of state-of-the-art approaches on three relevant tasks: 2D object and keypoint detection, 6D object pose estimation, and 3D hand pose estimation. Finally, we evaluate a new robotics-relevant task: generating safe robot grasps in human-to-robot object handover. Dataset and code are available at https://dex-ycb.github.io.
Vision-based reinforcement learning (RL) is successful, but how to generalize it to unknown test environments remains challenging. Existing methods focus on training an RL policy that is universal to changing visual domains, whereas we focus on extracting visual foreground that is universal, feeding clean invariant vision to the RL policy learner. Our method is completely unsupervised, without manual annotations or access to environment internals. Given videos of actions in a training environment, we learn how to extract foregrounds with unsupervised keypoint detection, followed by unsupervised visual attention to automatically generate a foreground mask per video frame. We can then introduce artificial distractors and train a model to reconstruct the clean foreground mask from noisy observations. Only this learned model is needed during test to provide distraction-free visual input to the RL policy learner. Our Visual Attention and Invariance (VAI) method significantly outperforms the state-of-the-art on visual domain generalization, gaining 15 to 49% (61 to 229%) more cumulative rewards per episode on DeepMind Control (our DrawerWorld Manipulation) benchmarks. Our results demonstrate that it is not only possible to learn domain-invariant vision without any supervision, but freeing RL from visual distractions also makes the policy more focused and thus far better.
Bottom-up approaches for image-based multi-person pose estimation consist of two stages: (1) keypoint detection and (2) grouping of the detected keypoints to form person instances. Current grouping approaches rely on learned embedding from only visual features that completely ignore the spatial configuration of human poses. In this work, we formulate the grouping task as a graph partitioning problem, where we learn the affinity matrix with a Graph Neural Network (GNN). More specifically, we design a Geometry-aware Association GNN that utilizes spatial information of the keypoints and learns local affinity from the global context. The learned geometry-based affinity is further fused with appearance-based affinity to achieve robust keypoint association. Spectral clustering is used to partition the graph for the formation of the pose instances. Experimental results on two benchmark datasets show that our proposed method outperforms existing appearance-only grouping frameworks, which shows the effectiveness of utilizing spatial context for robust grouping. Source code is available at: https://github.com/jiahaoLjh/PoseGrouping.