Underexposure regions are vital to construct a complete perception of the surroundings for safe autonomous driving. The availability of thermal cameras has provided an essential alternate to explore regions where other optical sensors lack in capturing interpretable signals. A thermal camera captures an image using the heat difference emitted by objects in the infrared spectrum, and object detection in thermal images becomes effective for autonomous driving in challenging conditions. Although object detection in the visible spectrum domain imaging has matured, thermal object detection lacks effectiveness. A significant challenge is scarcity of labeled data for the thermal domain which is desiderata for SOTA artificial intelligence techniques. This work proposes a domain adaptation framework which employs a style transfer technique for transfer learning from visible spectrum images to thermal images. The framework uses a generative adversarial network (GAN) to transfer the low-level features from the visible spectrum domain to the thermal domain through style consistency. The efficacy of the proposed method of object detection in thermal images is evident from the improved results when used styled images from publicly available thermal image datasets (FLIR ADAS and KAIST Multi-Spectral).
Salient object detection (SOD) is a crucial and preliminary task for many computer vision applications, which have made progress with deep CNNs. Most of the existing methods mainly rely on the RGB information to distinguish the salient objects, which faces difficulties in some complex scenarios. To solve this, many recent RGBD-based networks are proposed by adopting the depth map as an independent input and fuse the features with RGB information. Taking the advantages of RGB and RGBD methods, we propose a novel depth-aware salient object detection framework, which has following superior designs: 1) It only takes the depth information as training data while only relies on RGB information in the testing phase. 2) It comprehensively optimizes SOD features with multi-level depth-aware regularizations. 3) The depth information also serves as error-weighted map to correct the segmentation process. With these insightful designs combined, we make the first attempt in realizing an unified depth-aware framework with only RGB information as input for inference, which not only surpasses the state-of-the-art performances on five public RGB SOD benchmarks, but also surpasses the RGBD-based methods on five benchmarks by a large margin, while adopting less information and implementation light-weighted. The code and model will be publicly available.
We tackle the problem of joint perception and motion forecasting in the context of self-driving vehicles. Towards this goal we propose PnPNet, an end-to-end model that takes as input sequential sensor data, and outputs at each time step object tracks and their future trajectories. The key component is a novel tracking module that generates object tracks online from detections and exploits trajectory level features for motion forecasting. Specifically, the object tracks get updated at each time step by solving both the data association problem and the trajectory estimation problem. Importantly, the whole model is end-to-end trainable and benefits from joint optimization of all tasks. We validate PnPNet on two large-scale driving datasets, and show significant improvements over the state-of-the-art with better occlusion recovery and more accurate future prediction.
In this paper, we propose a fixed-size object encoding method (FOE-VRD) to improve performance of visual relationship detection tasks. Comparing with previous methods, FOE-VRD has an important feature, i.e., it uses one fixed-size vector to encoding all objects in each input image to assist the process of relationship detection. Firstly, we use a regular convolution neural network as a feature extractor to generate high-level features of input images. Then, for each relationship triplet in input images, i.e., $<$subject-predicate-object$>$, we apply ROI-pooling to get feature vectors of two regions on the feature maps that corresponding to bounding boxes of the subject and object. Besides the subject and object, our analysis implies that the results of predicate classification may also related to the rest objects in input images (we call them background objects). Due to the variable number of background objects in different images and computational costs, we cannot generate feature vectors for them one-by-one by using ROI pooling technique. Instead, we propose a novel method to encode all background objects in each image by using one fixed-size vector (i.e., FBE vector). By concatenating the 3 vectors we generate above, we successfully encode the objects using one fixed-size vector. The generated feature vector is then feed into a fully connected neural network to get predicate classification results. Experimental results on VRD database (entire set and zero-shot tests) show that the proposed method works well on both predicate classification and relationship detection.
Deep networks are currently the state-of-the-art for sensory perception in autonomous driving and robotics. However, deep models often generate overconfident predictions precluding proper probabilistic interpretation which we argue is due to the nature of the SoftMax layer. To reduce the overconfidence without compromising the classification performance, we introduce a CNN probabilistic approach based on distributions calculated in the network's Logit layer. The approach enables Bayesian inference by means of ML and MAP layers. Experiments with calibrated and the proposed prediction layers are carried out on object classification using data from the KITTI database. Results are reported for camera ($RGB$) and LiDAR (range-view) modalities, where the new approach shows promising performance compared to SoftMax.
Being able to predict human gaze behavior has obvious importance for behavioral vision and for computer vision applications. Most models have mainly focused on predicting free-viewing behavior using saliency maps, but these predictions do not generalize to goal-directed behavior, such as when a person searches for a visual target object. We propose the first inverse reinforcement learning (IRL) model to learn the internal reward function and policy used by humans during visual search. The viewer's internal belief states were modeled as dynamic contextual belief maps of object locations. These maps were learned by IRL and then used to predict behavioral scanpaths for multiple target categories. To train and evaluate our IRL model we created COCO-Search18, which is now the largest dataset of high-quality search fixations in existence. COCO-Search18 has 10 participants searching for each of 18 target-object categories in 6202 images, making about 300,000 goal-directed fixations. When trained and evaluated on COCO-Search18, the IRL model outperformed baseline models in predicting search fixation scanpaths, both in terms of similarity to human search behavior and search efficiency. Finally, reward maps recovered by the IRL model reveal distinctive target-dependent patterns of object prioritization, which we interpret as a learned object context.
Fully supervised deep neural networks for segmentation usually require a massive amount of pixel-level labels which are manually expensive to create. In this work, we develop a multi-task learning method to relax this constraint. We regard the segmentation problem as a sequence of approximation subproblems that are recursively defined and in increasing levels of approximation accuracy. The subproblems are handled by a framework that consists of 1) a segmentation task that learns from pixel-level ground truth segmentation masks of a small fraction of the images, 2) a recursive approximation task that conducts partial object regions learning and data-driven mask evolution starting from partial masks of each object instance, and 3) other problem oriented auxiliary tasks that are trained with sparse annotations and promote the learning of dedicated features. Most training images are only labeled by (rough) partial masks, which do not contain exact object boundaries, rather than by their full segmentation masks. During the training phase, the approximation task learns the statistics of these partial masks, and the partial regions are recursively increased towards object boundaries aided by the learned information from the segmentation task in a fully data-driven fashion. The network is trained on an extremely small amount of precisely segmented images and a large set of coarse labels. Annotations can thus be obtained in a cheap way. We demonstrate the efficiency of our approach in three applications with microscopy images and ultrasound images.
We consider the challenging problem of zero-shot video object segmentation (VOS). That is, segmenting and tracking multiple moving objects within a video fully automatically, without any manual initialization. We treat this as a grouping problem by exploiting object proposals and making a joint inference about grouping over both space and time. We propose a network architecture for tractably performing proposal selection and joint grouping. Crucially, we then show how to train this network with reinforcement learning so that it learns to perform the optimal non-myopic sequence of grouping decisions to segment the whole video. Unlike standard supervised techniques, this also enables us to directly optimize for the non-differentiable overlap-based metrics used to evaluate VOS. We show that the proposed method, which we call ALBA outperforms the previous stateof-the-art on three benchmarks: DAVIS 2017 [2], FBMS [20] and Youtube-VOS [27].
Graph Convolutional Network (GCN) has achieved extraordinary success in learning effective task-specific representations of nodes in graphs. However, regarding Heterogeneous Information Network (HIN), existing HIN-oriented GCN methods still suffer from two deficiencies: (1) they cannot flexibly explore all possible meta-paths and extract the most useful ones for a target object, which hinders both effectiveness and interpretability; (2) they often need to generate intermediate meta-path based dense graphs, which leads to high computational complexity. To address the above issues, we propose an interpretable and efficient Heterogeneous Graph Convolutional Network (ie-HGCN) to learn the representations of objects in HINs. It is designed as a hierarchical aggregation architecture, i.e., object-level aggregation first, followed by type-level aggregation. The novel architecture can automatically extract useful meta-paths for each object from all possible meta-paths (within a length limit), which brings good model interpretability. It can also reduce the computational cost by avoiding intermediate HIN transformation and neighborhood attention. We provide theoretical analysis about the proposed ie-HGCN in terms of evaluating the usefulness of all possible meta-paths, its connection to the spectral graph convolution on HINs, and its quasi-linear time complexity. Extensive experiments on three real network datasets demonstrate the superiority of ie-HGCN over the state-of-the-art methods.
In object recognition applications, object images usually appear with different quality levels. Practically, it is very important to indicate object image qualities for better application performance, e.g. filtering out low-quality object image frames to maintain robust video object recognition results and speed up inference. However, no previous works are explicitly proposed for addressing the problem. In this paper, we define the problem of object quality assessment for the first time and propose an effective approach named Object-QA to assess high-reliable quality scores for object images. Concretely, Object-QA first employs a well-designed relative quality assessing module that learns the intra-class-level quality scores by referring to the difference between object images and their estimated templates. Then an absolute quality assessing module is designed to generate the final quality scores by aligning the quality score distributions in inter-class. Besides, Object-QA can be implemented with only object-level annotations, and is also easily deployed to a variety of object recognition tasks. To our best knowledge this is the first work to put forward the definition of this problem and conduct quantitative evaluations. Validations on 5 different datasets show that Object-QA can not only assess high-reliable quality scores according with human cognition, but also improve application performance.
We present a new method that views object detection as a direct set prediction problem. Our approach streamlines the detection pipeline, effectively removing the need for many hand-designed components like a non-maximum suppression procedure or anchor generation that explicitly encode our prior knowledge about the task. The main ingredients of the new framework, called DEtection TRansformer or DETR, are a set-based global loss that forces unique predictions via bipartite matching, and a transformer encoder-decoder architecture. Given a fixed small set of learned object queries, DETR reasons about the relations of the objects and the global image context to directly output the final set of predictions in parallel. The new model is conceptually simple and does not require a specialized library, unlike many other modern detectors. DETR demonstrates accuracy and run-time performance on par with the well-established and highly-optimized Faster RCNN baseline on the challenging COCO object detection dataset. Moreover, DETR can be easily generalized to produce panoptic segmentation in a unified manner. We show that it significantly outperforms competitive baselines. Training code and pretrained models are available at https://github.com/facebookresearch/detr.
For object detection, how to address the contradictory requirement between feature map resolution and receptive field on high-resolution inputs still remains an open question. In this paper, to tackle this issue, we build a novel architecture, called Attention-guided Context Feature Pyramid Network (AC-FPN), that exploits discriminative information from various large receptive fields via integrating attention-guided multi-path features. The model contains two modules. The first one is Context Extraction Module (CEM) that explores large contextual information from multiple receptive fields. As redundant contextual relations may mislead localization and recognition, we also design the second module named Attention-guided Module (AM), which can adaptively capture the salient dependencies over objects by using the attention mechanism. AM consists of two sub-modules, i.e., Context Attention Module (CxAM) and Content Attention Module (CnAM), which focus on capturing discriminative semantics and locating precise positions, respectively. Most importantly, our AC-FPN can be readily plugged into existing FPN-based models. Extensive experiments on object detection and instance segmentation show that existing models with our proposed CEM and AM significantly surpass their counterparts without them, and our model successfully obtains state-of-the-art results. We have released the source code at https://github.com/Caojunxu/AC-FPN.
We study in this paper the problem of novel human-object interaction (HOI) detection, aiming at improving the generalization ability of the model to unseen scenarios. The challenge mainly stems from the large compositional space of objects and predicates, which leads to the lack of sufficient training data for all the object-predicate combinations. As a result, most existing HOI methods heavily rely on object priors and can hardly generalize to unseen combinations. To tackle this problem, we propose a unified framework of adversarial domain generalization to learn object-invariant features for predicate prediction. To measure the performance improvement, we create a new split of the HICO-DET dataset, where the HOIs in the test set are all unseen triplet categories in the training set. Our experiments show that the proposed framework significantly increases the performance by up to 50% on the new split of HICO-DET dataset and up to 125% on the UnRel dataset for auxiliary evaluation in detecting novel HOIs.
Detecting partially occluded objects is a difficult task. Our experimental results show that deep learning approaches, such as Faster R-CNN, are not robust at object detection under occlusion. Compositional convolutional neural networks (CompositionalNets) have been shown to be robust at classifying occluded objects by explicitly representing the object as a composition of parts. In this work, we propose to overcome two limitations of CompositionalNets which will enable them to detect partially occluded objects: 1) CompositionalNets, as well as other DCNN architectures, do not explicitly separate the representation of the context from the object itself. Under strong object occlusion, the influence of the context is amplified which can have severe negative effects for detection at test time. In order to overcome this, we propose to segment the context during training via bounding box annotations. We then use the segmentation to learn a context-aware CompositionalNet that disentangles the representation of the context and the object. 2) We extend the part-based voting scheme in CompositionalNets to vote for the corners of the object's bounding box, which enables the model to reliably estimate bounding boxes for partially occluded objects. Our extensive experiments show that our proposed model can detect objects robustly, increasing the detection performance of strongly occluded vehicles from PASCAL3D+ and MS-COCO by 41% and 35% respectively in absolute performance relative to Faster R-CNN.
In recent years, deep learning based methods have achieved promising performance in standard object detection. However, these methods lack sufficient capabilities to handle underwater object detection due to these challenges: (1) Objects in real applications are usually small and their images are blurry, and (2) images in the underwater datasets and real applications accompany heterogeneous noise. To address these two problems, we first propose a novel neural network architecture, namely Sample-WeIghted hyPEr Network (SWIPENet), for small object detection. SWIPENet consists of high resolution and semantic rich Hyper Feature Maps which can significantly improve small object detection accuracy. In addition, we propose a novel sample-weighted loss function which can model sample weights for SWIPENet, which uses a novel sample re-weighting algorithm, namely Invert Multi-Class Adaboost (IMA), to reduce the influence of noise on the proposed SWIPENet. Experiments on two underwater robot picking contest datasets URPC2017 and URPC2018 show that the proposed SWIPENet+IMA framework achieves better performance in detection accuracy against several state-of-the-art object detection approaches.
In the object detection task, merging various datasets from similar contexts but with different sets of Objects of Interest (OoI) is an inexpensive way (in terms of labor cost) for crafting a large-scale dataset covering a wide range of objects. Moreover, merging datasets allows us to train one integrated object detector, instead of training several ones, which in turn resulting in the reduction of computational and time costs. However, merging the datasets from similar contexts causes samples with partial labeling as each constituent dataset is originally annotated for its own set of OoI and ignores to annotate those objects that are become interested after merging the datasets. With the goal of training \emph{one integrated robust object detector with high generalization performance}, we propose a training framework to overcome missing-label challenge of the merged datasets. More specifically, we propose a computationally efficient self-supervised framework to create on-the-fly pseudo-labels for the unlabeled positive instances in the merged dataset in order to train the object detector jointly on both ground truth and pseudo labels. We evaluate our proposed framework for training Yolo on a simulated merged dataset with missing rate $\approx\!48\%$ using VOC2012 and VOC2007. We empirically show that generalization performance of Yolo trained on both ground truth and the pseudo-labels created by our method is on average $4\%$ higher than the ones trained only with the ground truth labels of the merged dataset.
Machine learning approaches to auditory object recognition are traditionally based on engineered features such as those derived from the spectrum or cepstrum. More recently, end-to-end classification systems in image and auditory recognition systems have been developed to learn features jointly with classification and result in improved classification accuracy. In this paper, we propose a novel end-to-end deep neural network to map the raw waveform inputs to sound class labels. Our network includes an "inception nucleus" that optimizes the size of convolutional filters on the fly that results in reducing engineering efforts dramatically. Classification results compared favorably against current state-of-the-art approaches, besting them by 10.4 percentage points on the Urbansound8k dataset. Analyses of learned representations revealed that filters in the earlier hidden layers learned wavelet-like transforms to extract features that were informative for classification.
The learning of the region proposal in object detection using the deep neural networks (DNN) is divided into two tasks: binary classification and bounding box regression task. However, traditional RPN (Region Proposal Network) defines these two tasks as different problems, and they are trained independently. In this paper, we propose a new region proposal learning method that considers the bounding box offset's uncertainty in the objectness score. Our method redefines RPN to a problem of minimizing the KL-divergence, difference between the two probability distributions. We applied KL-RPN, which performs region proposal using KL-Divergence, to the existing two-stage object detection framework and showed that it can improve the performance of the existing method. Experiments show that it achieves 2.6% and 2.0% AP improvements on MS COCO test-dev in Faster R-CNN with VGG-16 and R-FCN with ResNet-101 backbone, respectively.
We present an interpretable deep model for fine-grained visual recognition. At the core of our method lies the integration of region-based part discovery and attribution within a deep neural network. Our model is trained using image-level object labels, and provides an interpretation of its results via the segmentation of object parts and the identification of their contributions towards classification. To facilitate the learning of object parts without direct supervision, we explore a simple prior of the occurrence of object parts. We demonstrate that this prior, when combined with our region-based part discovery and attribution, leads to an interpretable model that remains highly accurate. Our model is evaluated on major fine-grained recognition datasets, including CUB-200, CelebA and iNaturalist. Our results compare favorably to state-of-the-art methods on classification tasks, and our method outperforms previous approaches on the localization of object parts.
For many years, multi-object tracking benchmarks have focused on a handful of categories. Motivated primarily by surveillance and self-driving applications, these datasets provide tracks for people, vehicles, and animals, ignoring the vast majority of objects in the world. By contrast, in the related field of object detection, the introduction of large-scale, diverse datasets (e.g., COCO) have fostered significant progress in developing highly robust solutions. To bridge this gap, we introduce a similarly diverse dataset for Tracking Any Object (TAO). It consists of 2,907 high resolution videos, captured in diverse environments, which are half a minute long on average. Importantly, we adopt a bottom-up approach for discovering a large vocabulary of 833 categories, an order of magnitude more than prior tracking benchmarks. To this end, we ask annotators to label objects that move at any point in the video, and give names to them post factum. Our vocabulary is both significantly larger and qualitatively different from existing tracking datasets. To ensure scalability of annotation, we employ a federated approach that focuses manual effort on labeling tracks for those relevant objects in a video (e.g., those that move). We perform an extensive evaluation of state-of-the-art trackers and make a number of important discoveries regarding large-vocabulary tracking in an open-world. In particular, we show that existing single- and multi-object trackers struggle when applied to this scenario in the wild, and that detection-based, multi-object trackers are in fact competitive with user-initialized ones. We hope that our dataset and analysis will boost further progress in the tracking community.