Natural language object retrieval is a highly useful yet challenging task for robots in human-centric environments. Previous work has primarily focused on commands specifying the desired object's type such as "scissors" and/or visual attributes such as "red," thus limiting the robot to only known object classes. We develop a model to retrieve objects based on descriptions of their usage. The model takes in a language command containing a verb, for example "Hand me something to cut," and RGB images of candidate objects and selects the object that best satisfies the task specified by the verb. Our model directly predicts an object's appearance from the object's use specified by a verb phrase. We do not need to explicitly specify an object's class label. Our approach allows us to predict high level concepts like an object's utility based on the language query. Based on contextual information present in the language commands, our model can generalize to unseen object classes and unknown nouns in the commands. Our model correctly selects objects out of sets of five candidates to fulfill natural language commands, and achieves an average accuracy of 62.3% on a held-out test set of unseen ImageNet object classes and 53.0% on unseen object classes and unknown nouns. Our model also achieves an average accuracy of 54.7% on unseen YCB object classes, which have a different image distribution from ImageNet objects. We demonstrate our model on a KUKA LBR iiwa robot arm, enabling the robot to retrieve objects based on natural language descriptions of their usage. We also present a new dataset of 655 verb-object pairs denoting object usage over 50 verbs and 216 object classes.
Object detection and data association are critical components in multi-object tracking (MOT) systems. Despite the fact that the two components are dependent on each other, prior works often design detection and data association modules separately which are trained with separate objectives. As a result, one cannot back-propagate the gradients and optimize the entire MOT system, which leads to sub-optimal performance. To address this issue, recent works simultaneously optimize detection and data association modules under a joint MOT framework, which has shown improved performance in both modules. In this work, we propose a new instance of joint MOT approach based on Graph Neural Networks (GNNs). The key idea is that GNNs can model relations between variable-sized objects in both the spatial and temporal domains, which is essential for learning discriminative features for detection and data association. Through extensive experiments on the MOT15/16/17/20 datasets, we demonstrate the effectiveness of our GNN-based joint MOT approach and show state-of-the-art performance for both detection and MOT tasks. Our code is available at: https://github.com/yongxinw/GSDT
Modern CNN-based object detectors focus on feature configuration during training but often ignore feature optimization during inference. In this paper, we propose a new feature optimization approach to enhance features and suppress background noise in both the training and inference stages. We introduce a generic Inference-aware Feature Filtering (IFF) module that can easily be combined with modern detectors, resulting in our iffDetector. Unlike conventional open-loop feature calculation approaches without feedback, the IFF module performs closed-loop optimization by leveraging high-level semantics to enhance the convolutional features. By applying Fourier transform analysis, we demonstrate that the IFF module acts as a negative feedback that theoretically guarantees the stability of feature learning. IFF can be fused with CNN-based object detectors in a plug-and-play manner with negligible computational cost overhead. Experiments on the PASCAL VOC and MS COCO datasets demonstrate that our iffDetector consistently outperforms state-of-the-art methods by significant margins\footnote{The test code and model are anonymously available in https://github.com/anonymous2020new/iffDetector }.
3D object detection has been widely studied due to its potential applicability to many promising areas such as robotics and augmented reality. Yet, the sparse nature of the 3D data poses unique challenges to this task. Most notably, the observable surface of the 3D point clouds is disjoint from the center of the instance to ground the bounding box prediction on. To this end, we propose Generative Sparse Detection Network (GSDN), a fully-convolutional single-shot sparse detection network that efficiently generates the support for object proposals. The key component of our model is a generative sparse tensor decoder, which uses a series of transposed convolutions and pruning layers to expand the support of sparse tensors while discarding unlikely object centers to maintain minimal runtime and memory footprint. GSDN can process unprecedentedly large-scale inputs with a single fully-convolutional feed-forward pass, thus does not require the heuristic post-processing stage that stitches results from sliding windows as other previous methods have. We validate our approach on three 3D indoor datasets including the large-scale 3D indoor reconstruction dataset where our method outperforms the state-of-the-art methods by a relative improvement of 7.14% while being 3.78 times faster than the best prior work.
Three-dimensional objects are commonly represented as 3D boxes in a point-cloud. This representation mimics the well-studied image-based 2D bounding-box detection but comes with additional challenges. Objects in a 3D world do not follow any particular orientation, and box-based detectors have difficulties enumerating all orientations or fitting an axis-aligned bounding box to rotated objects. In this paper, we instead propose to represent, detect, and track 3D objects as points. Our framework, CenterPoint, first detects centers of objects using a keypoint detector and regresses to other attributes, including 3D size, 3D orientation, and velocity. In a second stage, it refines these estimates using additional point features on the object. In CenterPoint, 3D object tracking simplifies to greedy closest-point matching. The resulting detection and tracking algorithm is simple, efficient, and effective. CenterPoint achieved state-of-the-art performance on the nuScenes benchmark for both 3D detection and tracking, with 65.5 NDS and 63.8 AMOTA for a single model. On the Waymo Open Dataset, CenterPoint outperforms all previous single model method by a large margin and ranks first among all Lidar-only submissions. The code and pretrained models are available at https://github.com/tianweiy/CenterPoint.
Solving long-tail large vocabulary object detection with deep learning based models is a challenging and demanding task, which is however under-explored.In this work, we provide the first systematic analysis on the underperformance of state-of-the-art models in front of long-tail distribution. We find existing detection methods are unable to model few-shot classes when the dataset is extremely skewed, which can result in classifier imbalance in terms of parameter magnitude. Directly adapting long-tail classification models to detection frameworks can not solve this problem due to the intrinsic difference between detection and classification.In this work, we propose a novel balanced group softmax (BAGS) module for balancing the classifiers within the detection frameworks through group-wise training. It implicitly modulates the training process for the head and tail classes and ensures they are both sufficiently trained, without requiring any extra sampling for the instances from the tail classes.Extensive experiments on the very recent long-tail large vocabulary object recognition benchmark LVIS show that our proposed BAGS significantly improves the performance of detectors with various backbones and frameworks on both object detection and instance segmentation. It beats all state-of-the-art methods transferred from long-tail image classification and establishes new state-of-the-art.Code is available at https://github.com/FishYuLi/BalancedGroupSoftmax.
We address the problem of language-based temporal localization of moments in untrimmed videos. Compared to temporal localization with fixed categories, this problem is more challenging as the language-based queries have no predefined activity classes and may also contain complex descriptions. Current state-of-the-art model MAC addresses it by mining activity concepts from both video and language modalities. This method encodes the semantic activity concepts from the verb/object pair in a language query and leverages visual activity concepts from video activity classification prediction scores. We propose "Multi-faceted VideoMoment Localizer" (MML), an extension of MAC model by the introduction of visual object evidence via object segmentation masks and video understanding features via video captioning. Furthermore, we improve language modelling in sentence embedding. We experimented on Charades-STA dataset and identified that MML outperforms MAC baseline by 4.93% and 1.70% on R@1 and R@5metrics respectively. Our code and pre-trained model are publicly available at https://github.com/madhawav/MML.
Anchor-based Siamese trackers have achieved remarkable advancements in accuracy, yet the further improvement is restricted by the lagged tracking robustness. We find the underlying reason is that the regression network in anchor-based methods is only trained on the positive anchor boxes (i.e., $IoU \geq0.6$). This mechanism makes it difficult to refine the anchors whose overlap with the target objects are small. In this paper, we propose a novel object-aware anchor-free network to address this issue. First, instead of refining the reference anchor boxes, we directly predict the position and scale of target objects in an anchor-free fashion. Since each pixel in groundtruth boxes is well trained, the tracker is capable of rectifying inexact predictions of target objects during inference. Second, we introduce a feature alignment module to learn an object-aware feature from predicted bounding boxes. The object-aware feature can further contribute to the classification of target objects and background. Moreover, we present a novel tracking framework based on the anchor-free model. The experiments show that our anchor-free tracker achieves state-of-the-art performance on five benchmarks, including VOT-2018, VOT-2019, OTB-100, GOT-10k and LaSOT. The source code is available at https://github.com/researchmm/TracKit.
Visual relationship detection is fundamental for holistic image understanding. However, localizing and classifying (subject, predicate, object) triplets constitutes a hard learning objective due to the combinatorial explosion of possible relationships, their long-tail distribution in natural images, and an expensive annotation process. This paper introduces a novel weakly-supervised method for visual relationship detection that relies only on image-level predicate annotations. A graph neural network is trained to classify the predicates in an image from the graph representation of all objects, implicitly encoding an inductive bias for pairwise relationships. We then frame relationship detection as the explanation of such a predicate classifier, i.e. we reconstruct a complete relationship by recovering the subject and the object of a predicted predicate. Using this novel technique and minimal labels, we present comparable results to recent fully-supervised and weakly-supervised methods on three diverse and challenging datasets: HICO-DET for human-object interaction, Visual Relationship Detection for generic object-to-object relationships, and UnRel for unusual relationships.
In this work, we present HyperFlow - a novel generative model that leverages hypernetworks to create continuous 3D object representations in a form of lightweight surfaces (meshes), directly out of point clouds. Efficient object representations are essential for many computer vision applications, including robotic manipulation and autonomous driving. However, creating those representations is often cumbersome, because it requires processing unordered sets of point clouds. Therefore, it is either computationally expensive, due to additional optimization constraints such as permutation invariance, or leads to quantization losses introduced by binning point clouds into discrete voxels. Inspired by mesh-based representations of objects used in computer graphics, we postulate a fundamentally different approach and represent 3D objects as a family of surfaces. To that end, we devise a generative model that uses a hypernetwork to return the weights of a Continuous Normalizing Flows (CNF) target network. The goal of this target network is to map points from a probability distribution into a 3D mesh. To avoid numerical instability of the CNF on compact support distributions, we propose a new Spherical Log-Normal function which models density of 3D points around object surfaces mimicking noise introduced by 3D capturing devices. As a result, we obtain continuous mesh-based object representations that yield better qualitative results than competing approaches, while reducing training time by over an order of magnitude.
Deploying deep learning models on embedded systems has been challenging due to limited computing resources. The majority of existing work focuses on accelerating image classification, while other fundamental vision problems, such as object detection, have not been adequately addressed. Compared with image classification, detection problems are more sensitive to the spatial variance of objects, and therefore, require specialized convolutions to aggregate spatial information. To address this need, recent work introduces dynamic deformable convolution to augment regular convolutions. However, this will lead to inefficient memory accesses of inputs with existing hardware. In this work, we harness the flexibility of FPGAs to develop a novel object detection pipeline with deformable convolutions. We show the speed-accuracy tradeoffs for a set of algorithm modifications including irregular-access versus limited-range and fixed-shape. We then Co-Design a Network CoDeNet with the modified deformable convolution and quantize it to 4-bit weights and 8-bit activations. With our high-efficiency implementation, our solution reaches 26.9 frames per second with a tiny model size of 0.76 MB while achieving 61.7 AP50 on the standard object detection dataset, Pascal VOC. With our higher accuracy implementation, our model gets to 67.1 AP50 on Pascal VOC with only 2.9 MB of parameters-20.9x smaller but 10% more accurate than Tiny-YOLO.
Accurately predicting the 3D shape of any arbitrary object in any pose from a single image is a key goal of computer vision research. This is challenging as it requires a model to learn a representation that can infer both the visible and occluded portions of any object using a limited training set. A training set that covers all possible object shapes is inherently infeasible. Such learning-based approaches are inherently vulnerable to overfitting, and successfully implementing them is a function of both the architecture design and the training approach. We present an extensive investigation of factors specific to architecture design, training, experiment design, and evaluation that influence reconstruction performance and measurement. We show that our proposed SDFNet achieves state-of-the-art performance on seen and unseen shapes relative to existing methods GenRe and OccNet. We provide the first large-scale evaluation of single image shape reconstruction to unseen objects. The source code, data and trained models can be found on https://github.com/rehg-lab/3DShapeGen.
Perceiving the world in terms of objects and tracking them through time is a crucial prerequisite for reasoning and scene understanding. Recently, several methods have been proposed for unsupervised learning of object-centric representations. However, since these models were evaluated on different downstream tasks, it remains unclear how they compare in terms of basic perceptual abilities such as detection, figure-ground segmentation and tracking of objects. To close this gap, we design a benchmark with four data sets of varying complexity and seven additional test sets featuring challenging tracking scenarios relevant for natural videos. Using this benchmark, we compare the perceptual abilities of four object-centric approaches: ViMON, a video-extension of MONet, based on recurrent spatial attention, OP3, which exploits clustering via spatial mixture models, as well as TBA and SCALOR, which use explicit factorization via spatial transformers. Our results suggest that the architectures with unconstrained latent representations learn more powerful representations in terms of object detection, segmentation and tracking than the spatial transformer based architectures. We also observe that none of the methods are able to gracefully handle the most challenging tracking scenarios despite their synthetic nature, suggesting that our benchmark may provide fruitful guidance towards learning more robust object-centric video representations.
3D Multi-object tracking (MOT) is crucial to autonomous systems. Recent work uses a standard tracking-by-detection pipeline, where feature extraction is first performed independently for each object in order to compute an affinity matrix. Then the affinity matrix is passed to the Hungarian algorithm for data association. A key process of this standard pipeline is to learn discriminative features for different objects in order to reduce confusion during data association. In this work, we propose two techniques to improve the discriminative feature learning for MOT: (1) instead of obtaining features for each object independently, we propose a novel feature interaction mechanism by introducing the Graph Neural Network. As a result, the feature of one object is informed of the features of other objects so that the object feature can lean towards the object with similar feature (i.e., object probably with a same ID) and deviate from objects with dissimilar features (i.e., object probably with different IDs), leading to a more discriminative feature for each object; (2) instead of obtaining the feature from either 2D or 3D space in prior work, we propose a novel joint feature extractor to learn appearance and motion features from 2D and 3D space simultaneously. As features from different modalities often have complementary information, the joint feature can be more discriminate than feature from each individual modality. To ensure that the joint feature extractor does not heavily rely on one modality, we also propose an ensemble training paradigm. Through extensive evaluation, our proposed method achieves state-of-the-art performance on KITTI and nuScenes 3D MOT benchmarks. Our code will be made available at https://github.com/xinshuoweng/GNN3DMOT
Similarity learning has been recognized as a crucial step for object tracking. However, existing multiple object tracking methods only use sparse ground truth matching as the training objective, while ignoring the majority of the informative regions on the images. In this paper, we present Quasi-Dense Similarity Learning, which densely samples hundreds of region proposals on a pair of images for contrastive learning. We can directly combine this similarity learning with existing detection methods to build Quasi-Dense Tracking (QDTrack) without turning to displacement regression or motion priors. We also find that the resulting distinctive feature space admits a simple nearest neighbor search at the inference time. Despite its simplicity, QDTrack outperforms all existing methods on MOT, BDD100K, Waymo, and TAO tracking benchmarks. It achieves 68.7 MOTA at 20.3 FPS on MOT17 without using external training data. Compared to methods with similar detectors, it boosts almost 10 points of MOTA and significantly decreases the number of ID switches on BDD100K and Waymo datasets. Our code and trained models are available at http://vis.xyz/pub/qdtrack.
Region sampling or weighting is significantly important to the success of modern region-based object detectors. Unlike some previous works, which only focus on "hard" samples when optimizing the objective function, we argue that sample weighting should be data-dependent and task-dependent. The importance of a sample for the objective function optimization is determined by its uncertainties to both object classification and bounding box regression tasks. To this end, we devise a general loss function to cover most region-based object detectors with various sampling strategies, and then based on it we propose a unified sample weighting network to predict a sample's task weights. Our framework is simple yet effective. It leverages the samples' uncertainty distributions on classification loss, regression loss, IoU, and probability score, to predict sample weights. Our approach has several advantages: (i). It jointly learns sample weights for both classification and regression tasks, which differentiates it from most previous work. (ii). It is a data-driven process, so it avoids some manual parameter tuning. (iii). It can be effortlessly plugged into most object detectors and achieves noticeable performance improvements without affecting their inference time. Our approach has been thoroughly evaluated with recent object detection frameworks and it can consistently boost the detection accuracy. Code has been made available at \url{https://github.com/caiqi/sample-weighting-network}.
Augmented reality devices require multiple sensors to perform various tasks such as localization and tracking. Currently, popular cameras are mostly frame-based (e.g. RGB and Depth) which impose a high data bandwidth and power usage. With the necessity for low power and more responsive augmented reality systems, using solely frame-based sensors imposes limits to the various algorithms that needs high frequency data from the environement. As such, event-based sensors have become increasingly popular due to their low power, bandwidth and latency, as well as their very high frequency data acquisition capabilities. In this paper, we propose, for the first time, to use an event-based camera to increase the speed of 3D object tracking in 6 degrees of freedom. This application requires handling very high object speed to convey compelling AR experiences. To this end, we propose a new system which combines a recent RGB-D sensor (Kinect Azure) with an event camera (DAVIS346). We develop a deep learning approach, which combines an existing RGB-D network along with a novel event-based network in a cascade fashion, and demonstrate that our approach significantly improves the robustness of a state-of-the-art frame-based 6-DOF object tracker using our RGB-D-E pipeline.
The recent rise of unsupervised and self-supervised learning has dramatically reduced the dependency on labeled data, providing effective image representations for transfer to downstream vision tasks. Furthermore, recent works employed these representations in a fully unsupervised setup for image classification, reducing the need for human labels on the fine-tuning stage as well. This work demonstrates that large-scale unsupervised models can also perform a more challenging object segmentation task, requiring neither pixel-level nor image-level labeling. Namely, we show that recent unsupervised GANs allow to differentiate between foreground/background pixels, providing high-quality saliency masks. By extensive comparison on standard benchmarks, we outperform existing unsupervised alternatives for object segmentation, achieving new state-of-the-art.
Recently, remarkable progress has been made in weakly supervised object localization (WSOL) to promote object localization maps. The common practice of evaluating these maps applies an indirect and coarse way, i.e., obtaining tight bounding boxes which can cover high-activation regions and calculating intersection-over-union (IoU) scores between the predicted and ground-truth boxes. This measurement can evaluate the ability of localization maps to some extent, but we argue that the maps should be measured directly and delicately, i.e., comparing the maps with the ground-truth object masks pixel-wisely. To fulfill the direct evaluation, we annotate pixel-level object masks on the ILSVRC validation set. We propose to use IoU-Threshold curves for evaluating the real quality of localization maps. Beyond the amended evaluation metric and annotated object masks, this work also introduces a novel self-enhancement method to harvest accurate object localization maps and object boundaries with only category labels as supervision. We propose a two-stage approach to generate the localization maps by simply comparing the similarity of point-wise features between the high-activation and the rest pixels. Based on the predicted localization maps, we explore to estimate object boundaries on a very large dataset. A hard-negative suppression loss is proposed for obtaining fine boundaries. We conduct extensive experiments on the ILSVRC and CUB benchmarks. In particular, the proposed Self-Enhancement Maps achieve the state-of-the-art localization accuracy of 54.88% on ILSVRC. The code and the annotated masks are released at https://github.com/xiaomengyc/SEM.
Multi-object tracking is a fundamental vision problem that has been studied for a long time. As deep learning brings excellent performances to object detection algorithms, Tracking by Detection (TBD) has become the mainstream tracking framework. Despite the success of TBD, this two-step method is too complicated to train in an end-to-end manner and induces many challenges as well, such as insufficient exploration of video spatial-temporal information, vulnerability when facing object occlusion, and excessive reliance on detection results. To address these challenges, we propose a concise end-to-end model TubeTK which only needs one step training by introducing the ``bounding-tube" to indicate temporal-spatial locations of objects in a short video clip. TubeTK provides a novel direction of multi-object tracking, and we demonstrate its potential to solve the above challenges without bells and whistles. We analyze the performance of TubeTK on several MOT benchmarks and provide empirical evidence to show that TubeTK has the ability to overcome occlusions to some extent without any ancillary technologies like Re-ID. Compared with other methods that adopt private detection results, our one-stage end-to-end model achieves state-of-the-art performances even if it adopts no ready-made detection results. We hope that the proposed TubeTK model can serve as a simple but strong alternative for video-based MOT task. The code and models are available at https://github.com/BoPang1996/TubeTK.