Determining positive/negative samples for object detection is known as label assignment. Here we present an anchor-free detector named AutoAssign. It requires little human knowledge and achieves appearance-aware through a fully differentiable weighting mechanism. During training, to both satisfy the prior distribution of data and adapt to category characteristics, we present Center Weighting to adjust the category-specific prior distributions. To adapt to object appearances, Confidence Weighting is proposed to adjust the specific assign strategy of each instance. The two weighting modules are then combined to generate positive and negative weights to adjust each location's confidence. Extensive experiments on the MS COCO show that our method steadily surpasses other best sampling strategies by large margins with various backbones. Moreover, our best model achieves 52.1% AP, outperforming all existing one-stage detectors. Besides, experiments on other datasets, e.g., PASCAL VOC, Objects365, and WiderFace, demonstrate the broad applicability of AutoAssign.
In this paper, we conduct a comprehensive study on the co-salient object detection (CoSOD) problem for images. CoSOD is an emerging and rapidly growing extension of salient object detection (SOD), which aims to detect the co-occurring salient objects in a group of images. However, existing CoSOD datasets often have a serious data bias, assuming that each group of images contains salient objects of similar visual appearances. This bias can lead to the ideal settings and effectiveness of models trained on existing datasets, being impaired in real-life situations, where similarities are usually semantic or conceptual. To tackle this issue, we first introduce a new benchmark, called CoSOD3k in the wild, which requires a large amount of semantic context, making it more challenging than existing CoSOD datasets. Our CoSOD3k consists of 3,316 high-quality, elaborately selected images divided into 160 groups with hierarchical annotations. The images span a wide range of categories, shapes, object sizes, and backgrounds. Second, we integrate the existing SOD techniques to build a unified, trainable CoSOD framework, which is long overdue in this field. Specifically, we propose a novel CoEG-Net that augments our prior model EGNet with a co-attention projection strategy to enable fast common information learning. CoEG-Net fully leverages previous large-scale SOD datasets and significantly improves the model scalability and stability. Third, we comprehensively summarize 40 cutting-edge algorithms, benchmarking 18 of them over three challenging CoSOD datasets (iCoSeg, CoSal2015, and our CoSOD3k), and reporting more detailed (i.e., group-level) performance analysis. Finally, we discuss the challenges and future works of CoSOD. We hope that our study will give a strong boost to growth in the CoSOD community. The benchmark toolbox and results are available on our project page at http://dpfan.net/CoSOD3K/.
Single shot detectors that are potentially faster and simpler than two-stage detectors tend to be more applicable to object detection in videos. Nevertheless, the extension of such object detectors from image to video is not trivial especially when appearance deterioration exists in videos, \emph{e.g.}, motion blur or occlusion. A valid question is how to explore temporal coherence across frames for boosting detection. In this paper, we propose to address the problem by enhancing per-frame features through aggregation of neighboring frames. Specifically, we present Single Shot Video Object Detector (SSVD) -- a new architecture that novelly integrates feature aggregation into a one-stage detector for object detection in videos. Technically, SSVD takes Feature Pyramid Network (FPN) as backbone network to produce multi-scale features. Unlike the existing feature aggregation methods, SSVD, on one hand, estimates the motion and aggregates the nearby features along the motion path, and on the other, hallucinates features by directly sampling features from the adjacent frames in a two-stream structure. Extensive experiments are conducted on ImageNet VID dataset, and competitive results are reported when comparing to state-of-the-art approaches. More remarkably, for $448 \times 448$ input, SSVD achieves 79.2% mAP on ImageNet VID, by processing one frame in 85 ms on an Nvidia Titan X Pascal GPU. The code is available at \url{https://github.com/ddjiajun/SSVD}.
In this paper, we address the problem of joint detection of objects like dog and its semantic parts like face, leg, etc. Our model is created on top of two Faster-RCNN models that share their features to perform a novel Attention-based feature fusion of related Object and Part features to get enhanced representations of both. These representations are used for final classification and bounding box regression separately for both models. Our experiments on the PASCAL-Part 2010 dataset show that joint detection can simultaneously improve both object detection and part detection in terms of mean Average Precision (mAP) at IoU=0.5.
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 another task, namely, "labels to photo" image generation by integrating the voting module of HoughNet to two different GAN models and showing that the accuracy is significantly improved in both cases. Code is available at https://github.com/nerminsamet/houghnet.
Weakly supervised phrase grounding aims at learning region-phrase correspondences using only image-sentence pairs. A major challenge thus lies in the missing links between image regions and sentence phrases during training. To address this challenge, we leverage a generic object detector at training time, and propose a contrastive learning framework that accounts for both region-phrase and image-sentence matching. Our core innovation is the learning of a region-phrase score function, based on which an image-sentence score function is further constructed. Importantly, our region-phrase score function is learned by distilling from soft matching scores between the detected object names and candidate phrases within an image-sentence pair, while the image-sentence score function is supervised by ground-truth image-sentence pairs. The design of such score functions removes the need of object detection at test time, thereby significantly reducing the inference cost. Without bells and whistles, our approach achieves state-of-the-art results on visual phrase grounding, surpassing previous methods that require expensive object detectors at test time.
A recent approach for object detection and human pose estimation is to regress bounding boxes or human keypoints from a central point on the object or person. While this center-point regression is simple and efficient, we argue that the image features extracted at a central point contain limited information for predicting distant keypoints or bounding box boundaries, due to object deformation and scale/orientation variation. To facilitate inference, we propose to instead perform regression from a set of points placed at more advantageous positions. This point set is arranged to reflect a good initialization for the given task, such as modes in the training data for pose estimation, which lie closer to the ground truth than the central point and provide more informative features for regression. As the utility of a point set depends on how well its scale, aspect ratio and rotation matches the target, we adopt the anchor box technique of sampling these transformations to generate additional point-set candidates. We apply this proposed framework, called Point-Set Anchors, to object detection, instance segmentation, and human pose estimation. Our results show that this general-purpose approach can achieve performance competitive with state-of-the-art methods for each of these tasks. Code is available at \url{https://github.com/FangyunWei/PointSetAnchor}
Multi-level feature fusion is a fundamental topic in computer vision. It has been exploited to detect, segment and classify objects at various scales. When multi-level features meet multi-modal cues, the optimal feature aggregation and multi-modal learning strategy become a hot potato. In this paper, we leverage the inherent multi-modal and multi-level nature of RGB-D salient object detection to devise a novel cascaded refinement network. In particular, first, we propose to regroup the multi-level features into teacher and student features using a bifurcated backbone strategy (BBS). Second, we introduce a depth-enhanced module (DEM) to excavate informative depth cues from the channel and spatial views. Then, RGB and depth modalities are fused in a complementary way. Our architecture, named Bifurcated Backbone Strategy Network (BBS-Net), is simple, efficient, and backbone-independent. Extensive experiments show that BBS-Net significantly outperforms eighteen SOTA models on eight challenging datasets under five evaluation measures, demonstrating the superiority of our approach ($\sim 4 \%$ improvement in S-measure $vs.$ the top-ranked model: DMRA-iccv2019). In addition, we provide a comprehensive analysis on the generalization ability of different RGB-D datasets and provide a powerful training set for future research.
This paper studies the problem of learning semantic segmentation from image-level supervision only. Current popular solutions leverage object localization maps from classifiers as supervision signals, and struggle to make the localization maps capture more complete object content. Rather than previous efforts that primarily focus on intra-image information, we address the value of cross-image semantic relations for comprehensive object pattern mining. To achieve this, two neural co-attentions are incorporated into the classifier to complimentarily capture cross-image semantic similarities and differences. In particular, given a pair of training images, one co-attention enforces the classifier to recognize the common semantics from co-attentive objects, while the other one, called contrastive co-attention, drives the classifier to identify the unshared semantics from the rest, uncommon objects. This helps the classifier discover more object patterns and better ground semantics in image regions. In addition to boosting object pattern learning, the co-attention can leverage context from other related images to improve localization map inference, hence eventually benefiting semantic segmentation learning. More essentially, our algorithm provides a unified framework that handles well different WSSS settings, i.e., learning WSSS with (1) precise image-level supervision only, (2) extra simple single-label data, and (3) extra noisy web data. It sets new state-of-the-arts on all these settings, demonstrating well its efficacy and generalizability. Moreover, our approach ranked 1st place in the Weakly-Supervised Semantic Segmentation Track of CVPR2020 Learning from Imperfect Data Challenge.
For robots to operate robustly in the real world, they should be aware of their uncertainty. However, most methods for object pose estimation return a single point estimate of the object's pose. In this work, we propose two learned methods for estimating a distribution over an object's orientation. Our methods take into account both the inaccuracies in the pose estimation as well as the object symmetries. Our first method, which regresses from deep learned features to an isotropic Bingham distribution, gives the best performance for orientation distribution estimation for non-symmetric objects. Our second method learns to compare deep features and generates a non-parameteric histogram distribution. This method gives the best performance on objects with unknown symmetries, accurately modeling both symmetric and non-symmetric objects, without any requirement of symmetry annotation. We show that both of these methods can be used to augment an existing pose estimator. Our evaluation compares our methods to a large number of baseline approaches for uncertainty estimation across a variety of different types of objects.
An object's geocentric pose, defined as the height above ground and orientation with respect to gravity, is a powerful representation of real-world structure for object detection, segmentation, and localization tasks using RGBD images. For close-range vision tasks, height and orientation have been derived directly from stereo-computed depth and more recently from monocular depth predicted by deep networks. For long-range vision tasks such as Earth observation, depth cannot be reliably estimated with monocular images. Inspired by recent work in monocular height above ground prediction and optical flow prediction from static images, we develop an encoding of geocentric pose to address this challenge and train a deep network to compute the representation densely, supervised by publicly available airborne lidar. We exploit these attributes to rectify oblique images and remove observed object parallax to dramatically improve the accuracy of localization and to enable accurate alignment of multiple images taken from very different oblique viewpoints. We demonstrate the value of our approach by extending two large-scale public datasets for semantic segmentation in oblique satellite images. All of our data and code are publicly available.
We present RELATE, a model that learns to generate physically plausible scenes and videos of multiple interacting objects. Similar to other generative approaches, RELATE is trained end-to-end on raw, unlabeled data. RELATE combines an object-centric GAN formulation with a model that explicitly accounts for correlations between individual objects. This allows the model to generate realistic scenes and videos from a physically-interpretable parameterization. Furthermore, we show that modeling the object correlation is necessary to learn to disentangle object positions and identity. We find that RELATE is also amenable to physically realistic scene editing and that it significantly outperforms prior art in object-centric scene generation in both synthetic (CLEVR, ShapeStacks) and real-world data (cars). In addition, in contrast to state-of-the-art methods in object-centric generative modeling, RELATE also extends naturally to dynamic scenes and generates videos of high visual fidelity. Source code, datasets and more results are available at http://geometry.cs.ucl.ac.uk/projects/2020/relate/.
Various methods of measuring unit selectivity have been developed with the aim of better understanding how neural networks work. But the different measures provide divergent estimates of selectivity, and this has led to different conclusions regarding the conditions in which selective object representations are learned and the functional relevance of these representations. In an attempt to better characterize object selectivity, we undertake a comparison of various selectivity measures on a large set of units in AlexNet, including localist selectivity, precision, class-conditional mean activity selectivity (CCMAS), network dissection,the human interpretation of activation maximization (AM) images, and standard signal-detection measures. We find that the different measures provide different estimates of object selectivity, with precision and CCMAS measures providing misleadingly high estimates. Indeed, the most selective units had a poor hit-rate or a high false-alarm rate (or both) in object classification, making them poor object detectors. We fail to find any units that are even remotely as selective as the 'grandmother cell' units reported in recurrent neural networks. In order to generalize these results, we compared selectivity measures on units in VGG-16 and GoogLeNet trained on the ImageNet or Places-365 datasets that have been described as 'object detectors'. Again, we find poor hit-rates and high false-alarm rates for object classification. We conclude that signal-detection measures provide a better assessment of single-unit selectivity compared to common alternative approaches, and that deep convolutional networks of image classification do not learn object detectors in their hidden layers.
This work studies the problem of object goal navigation which involves navigating to an instance of the given object category in unseen environments. End-to-end learning-based navigation methods struggle at this task as they are ineffective at exploration and long-term planning. We propose a modular system called, `Goal-Oriented Semantic Exploration' which builds an episodic semantic map and uses it to explore the environment efficiently based on the goal object category. Empirical results in visually realistic simulation environments show that the proposed model outperforms a wide range of baselines including end-to-end learning-based methods as well as modular map-based methods and led to the winning entry of the CVPR-2020 Habitat ObjectNav Challenge. Ablation analysis indicates that the proposed model learns semantic priors of the relative arrangement of objects in a scene, and uses them to explore efficiently. Domain-agnostic module design allow us to transfer our model to a mobile robot platform and achieve similar performance for object goal navigation in the real-world.
The availability of a large labeled dataset is a key requirement for applying deep learning methods to solve various computer vision tasks. In the context of understanding human activities, existing public datasets, while large in size, are often limited to a single RGB camera and provide only per-frame or per-clip action annotations. To enable richer analysis and understanding of human activities, we introduce IKEA ASM -- a three million frame, multi-view, furniture assembly video dataset that includes depth, atomic actions, object segmentation, and human pose. Additionally, we benchmark prominent methods for video action recognition, object segmentation and human pose estimation tasks on this challenging dataset. The dataset enables the development of holistic methods, which integrate multi-modal and multi-view data to better perform on these tasks.
Humans can predict the functionality of an object even without any surroundings, since their knowledge and experience would allow them to "hallucinate" the interaction or usage scenarios involving the object. We develop predictive and generative deep convolutional neural networks to replicate this feat. Specifically, our work focuses on functionalities of man-made 3D objects characterized by human-object or object-object interactions. Our networks are trained on a database of scene contexts, called interaction contexts, each consisting of a central object and one or more surrounding objects, that represent object functionalities. Given a 3D object in isolation, our functional similarity network (fSIM-NET), a variation of the triplet network, is trained to predict the functionality of the object by inferring functionality-revealing interaction contexts. fSIM-NET is complemented by a generative network (iGEN-NET) and a segmentation network (iSEG-NET). iGEN-NET takes a single voxelized 3D object with a functionality label and synthesizes a voxelized surround, i.e., the interaction context which visually demonstrates the corresponding functionality. iSEG-NET further separates the interacting objects into different groups according to their interaction types.
Monocular multi-object detection and localization in 3D space has been proven to be a challenging task. The MoNet3D algorithm is a novel and effective framework that can predict the 3D position of each object in a monocular image and draw a 3D bounding box for each object. The MoNet3D method incorporates prior knowledge of the spatial geometric correlation of neighbouring objects into the deep neural network training process to improve the accuracy of 3D object localization. Experiments on the KITTI dataset show that the accuracy for predicting the depth and horizontal coordinates of objects in 3D space can reach 96.25\% and 94.74\%, respectively. Moreover, the method can realize the real-time image processing at 27.85 FPS, showing promising potential for embedded advanced driving-assistance system applications. Our code is publicly available at https://github.com/CQUlearningsystemgroup/YicongPeng.
With the trend of adversarial attacks, researchers attempt to fool trained object detectors in 2D scenes. Among many of them, an intriguing new form of attack with potential real-world usage is to append adversarial patches (e.g. logos) to images. Nevertheless, much less have we known about adversarial attacks from 3D rendering views, which is essential for the attack to be persistently strong in the physical world. This paper presents a new 3D adversarial logo attack: we construct an arbitrary shape logo from a 2D texture image and map this image into a 3D adversarial logo via a texture mapping called logo transformation. The resulting 3D adversarial logo is then viewed as an adversarial texture enabling easy manipulation of its shape and position. This greatly extends the versatility of adversarial training for computer graphics synthesized imagery. Contrary to the traditional adversarial patch, this new form of attack is mapped into the 3D object world and back-propagates to the 2D image domain through differentiable rendering. In addition, and unlike existing adversarial patches, our new 3D adversarial logo is shown to fool state-of-the-art deep object detectors robustly under model rotations, leading to one step further for realistic attacks in the physical world. Our codes are available at https://github.com/TAMU-VITA/3D_Adversarial_Logo.
Learning object-centric representations of complex scenes is a promising step towards enabling efficient abstract reasoning from low-level perceptual features. Yet, most deep learning approaches learn distributed representations that do not capture the compositional properties of natural scenes. In this paper, we present the Slot Attention module, an architectural component that interfaces with perceptual representations such as the output of a convolutional neural network and produces a set of task-dependent abstract representations which we call slots. These slots are exchangeable and can bind to any object in the input by specializing through a competitive procedure over multiple rounds of attention. We empirically demonstrate that Slot Attention can extract object-centric representations that enable generalization to unseen compositions when trained on unsupervised object discovery and supervised property prediction tasks.
We present an extension to the disjoint paths problem in which additional \emph{lifted} edges are introduced to provide path connectivity priors. We call the resulting optimization problem the lifted disjoint paths problem. We show that this problem is NP-hard by reduction from integer multicommodity flow and 3-SAT. To enable practical global optimization, we propose several classes of linear inequalities that produce a high-quality LP-relaxation. Additionally, we propose efficient cutting plane algorithms for separating the proposed linear inequalities. The lifted disjoint path problem is a natural model for multiple object tracking and allows an elegant mathematical formulation for long range temporal interactions. Lifted edges help to prevent id switches and to re-identify persons. Our lifted disjoint paths tracker achieves nearly optimal assignments with respect to input detections. As a consequence, it leads on all three main benchmarks of the MOT challenge, improving significantly over state-of-the-art.