This paper addresses the problem of image matting for transparent objects. Existing approaches often require tedious capturing procedures and long processing time, which limit their practical use. In this paper, we formulate transparent object matting as a refractive flow estimation problem, and propose a deep learning framework, called TOM-Net, for learning the refractive flow. Our framework comprises two parts, namely a multi-scale encoder-decoder network for producing a coarse prediction, and a residual network for refinement. At test time, TOM-Net takes a single image as input, and outputs a matte (consisting of an object mask, an attenuation mask and a refractive flow field) in a fast feed-forward pass. As no off-the-shelf dataset is available for transparent object matting, we create a large-scale synthetic dataset consisting of $178K$ images of transparent objects rendered in front of images sampled from the Microsoft COCO dataset. We also capture a real dataset consisting of $876$ samples using $14$ transparent objects and $60$ background images. Besides, we show that our method can be easily extended to handle the cases where a trimap or a background image is available.Promising experimental results have been achieved on both synthetic and real data, which clearly demonstrate the effectiveness of our approach.
Drones or general Unmanned Aerial Vehicles (UAVs), endowed with computer vision function by on-board cameras and embedded systems, have become popular in a wide range of applications. However, real-time scene parsing through object detection running on a UAV platform is very challenging, due to limited memory and computing power of embedded devices. To deal with these challenges, in this paper we propose to learn efficient deep object detectors through channel pruning of convolutional layers. To this end, we enforce channel-level sparsity of convolutional layers by imposing L1 regularization on channel scaling factors and prune less informative feature channels to obtain "slim" object detectors. Based on such approach, we present SlimYOLOv3 with fewer trainable parameters and floating point operations (FLOPs) in comparison of original YOLOv3 (Joseph Redmon et al., 2018) as a promising solution for real-time object detection on UAVs. We evaluate SlimYOLOv3 on VisDrone2018-Det benchmark dataset; compelling results are achieved by SlimYOLOv3 in comparison of unpruned counterpart, including ~90.8% decrease of FLOPs, ~92.0% decline of parameter size, running ~2 times faster and comparable detection accuracy as YOLOv3. Experimental results with different pruning ratios consistently verify that proposed SlimYOLOv3 with narrower structure are more efficient, faster and better than YOLOv3, and thus are more suitable for real-time object detection on UAVs. Our codes are made publicly available at https://github.com/PengyiZhang/SlimYOLOv3.
Learning to localize and name object instances is a fundamental problem in vision, but state-of-the-art approaches rely on expensive bounding box supervision. While weakly supervised detection (WSOD) methods relax the need for boxes to that of image-level annotations, even cheaper supervision is naturally available in the form of unstructured textual descriptions that users may freely provide when uploading image content. However, straightforward approaches to using such data for WSOD wastefully discard captions that do not exactly match object names. Instead, we show how to squeeze the most information out of these captions by training a text-only classifier that generalizes beyond dataset boundaries. Our discovery provides an opportunity for learning detection models from noisy but more abundant and freely-available caption data. We also validate our model on three classic object detection benchmarks and achieve state-of-the-art WSOD performance. Our code is available at https://github.com/yekeren/Cap2Det.
Most of object detection algorithms can be categorized into two classes: two-stage detectors and one-stage detectors. Recently, many efforts have been devoted to one-stage detectors for the simple yet effective architecture. Different from two-stage detectors, one-stage detectors aim to identify foreground objects from all candidates in a single stage. This architecture is efficient but can suffer from the imbalance issue with respect to two aspects: the inter-class imbalance between the number of candidates from foreground and background classes and the intra-class imbalance in the hardness of background candidates, where only a few candidates are hard to be identified. In this work, we propose a novel distributional ranking (DR) loss to handle the challenge. For each image, we convert the classification problem to a ranking problem, which considers pairs of candidates within the image, to address the inter-class imbalance problem. Then, we push the distributions of confidence scores for foreground and background towards the decision boundary. After that, we optimize the rank of the expectations of derived distributions in lieu of original pairs. Our method not only mitigates the intra-class imbalance issue in background candidates but also improves the efficiency for the ranking algorithm. By merely replacing the focal loss in RetinaNet with the developed DR loss and applying ResNet-101 as the backbone, mAP of the single-scale test on COCO can be improved from 39.1% to 41.7% without bells and whistles, which demonstrates the effectiveness of the proposed loss function. Code is available at \url{https://github.com/idstcv/DR_loss}.
We present NOLBO, a variational observation model estimation for 3D multi-object from 2D single shot. Previous probabilistic instance-level understandings mainly consider the single-object image, not single shot with multi-object; relations between objects and the entire scene are out of their focus. The objectness of each observation also hardly join their model. Therefore, we propose a method to approximate the Bayesian observation model of scene-level 3D multi-object understanding. By exploiting variational auto-encoder (VAE), we estimate latent variables from the entire scene, which follow tractable distributions and concurrently imply 3D full shape and pose. To perform object-oriented data association and probabilistic simultaneous localization and mapping (SLAM), our observation models can easily be adopted to probabilistic inference by replacing object-oriented features with latent variables.
The success of generative modeling in continuous domains has led to a surge of interest in generating discrete data such as molecules, source code, and graphs. However, construction histories for these discrete objects are typically not unique and so generative models must reason about intractably large spaces in order to learn. Additionally, structured discrete domains are often characterized by strict constraints on what constitutes a valid object and generative models must respect these requirements in order to produce useful novel samples. Here, we present a generative model for discrete objects employing a Markov chain where transitions are restricted to a set of local operations that preserve validity. Building off of generative interpretations of denoising autoencoders, the Markov chain alternates between producing 1) a sequence of corrupted objects that are valid but not from the data distribution, and 2) a learned reconstruction distribution that attempts to fix the corruptions while also preserving validity. This approach constrains the generative model to only produce valid objects, requires the learner to only discover local modifications to the objects, and avoids marginalization over an unknown and potentially large space of construction histories. We evaluate the proposed approach on two highly structured discrete domains, molecules and Laman graphs, and find that it compares favorably to alternative methods at capturing distributional statistics for a host of semantically relevant metrics.
The ability to detect objects regardless of image distortions or weather conditions is crucial for real-world applications of deep learning like autonomous driving. We here provide an easy-to-use benchmark to assess how object detection models perform when image quality degrades. The three resulting benchmark datasets, termed Pascal-C, Coco-C and Cityscapes-C, contain a large variety of image corruptions. We show that a range of standard object detection models suffer a severe performance loss on corrupted images (down to 30--60\% of the original performance). However, a simple data augmentation trick---stylizing the training images---leads to a substantial increase in robustness across corruption type, severity and dataset. We envision our comprehensive benchmark to track future progress towards building robust object detection models. Benchmark, code and data are publicly available.
The use of RGB-D information for salient object detection has been extensively explored in recent years. However, relatively few efforts have been put towards modeling salient object detection in real-world human activity scenes with RGBD. In this work, we fill the gap by making the following contributions to RGB-D salient object detection. (1) We carefully collect a new SIP (salient person) dataset, which consists of ~1K high-resolution images that cover diverse real-world scenes from various viewpoints, poses, occlusions, illuminations, and backgrounds. (2) We conduct a large-scale (and, so far, the most comprehensive) benchmark comparing contemporary methods, which has long been missing in the field and can serve as a baseline for future research. We systematically summarize 32 popular models and evaluate 18 parts of 32 models on seven datasets containing a total of about 97K images. (3) We propose a simple general architecture, called Deep Depth-Depurator Network (D3Net). It consists of a depth depurator unit (DDU) and a three-stream feature learning module (FLM), which performs low-quality depth map filtering and cross-modal feature learning respectively. These components form a nested structure and are elaborately designed to be learned jointly. D3Net exceeds the performance of any prior contenders across all five metrics under consideration, thus serving as a strong model to advance research in this field. We also demonstrate that D3Net can be used to efficiently extract salient object masks from real scenes, enabling effective background changing application with a speed of 65fps on a single GPU. All the saliency maps, our new SIP dataset, the D3Net model, and the evaluation tools are publicly available at https://github.com/DengPingFan/D3NetBenchmark.
We propose ALFA - a novel late fusion algorithm for object detection. ALFA is based on agglomerative clustering of object detector predictions taking into consideration both the bounding box locations and the class scores. Each cluster represents a single object hypothesis whose location is a weighted combination of the clustered bounding boxes. ALFA was evaluated using combinations of a pair (SSD and DeNet) and a triplet (SSD, DeNet and Faster R-CNN) of recent object detectors that are close to the state-of-the-art. ALFA achieves state of the art results on PASCAL VOC 2007 and PASCAL VOC 2012, outperforming the individual detectors as well as baseline combination strategies, achieving up to 32% lower error than the best individual detectors and up to 6% lower error than the reference fusion algorithm DBF - Dynamic Belief Fusion.
In this paper, we demonstrate a novel algorithm that uses ellipse fitting to estimate the bounding box rotation angle and size with the segmentation(mask) on the target for online and real-time visual object tracking. Our method, SiamMask_E, improves the bounding box fitting procedure of the state-of-the-art object tracking algorithm SiamMask and still retains a fast-tracking frame rate (80 fps) on a system equipped with GPU (GeForce GTX 1080 Ti or higher). We tested our approach on the visual object tracking datasets (VOT2016, VOT2018, and VOT2019) that were labeled with rotated bounding boxes. By comparing with the original SiamMask, we achieved an improved Accuracy of 0.652 and 0.309 EAO on VOT2019, which is 0.056 and 0.026 higher than the original SiamMask. The implementation is available on GitHub: https://github.com/baoxinchen/siammask_e.
3D object detection from LiDAR point cloud is a challenging problem in 3D scene understanding and has many practical applications. In this paper, we extend our preliminary work PointRCNN to a novel and strong point-cloud-based 3D object detection framework, the part-aware and aggregation neural network (Part-$A^2$ net). The whole framework consists of the part-aware stage and the part-aggregation stage. Firstly, the part-aware stage for the first time fully utilizes free-of-charge part supervisions derived from 3D ground-truth boxes to simultaneously predict high quality 3D proposals and accurate intra-object part locations. The predicted intra-object part locations within the same proposal are grouped by our new-designed RoI-aware point cloud pooling module, which results in an effective representation to encode the geometry-specific features of each 3D proposal. Then the part-aggregation stage learns to re-score the box and refine the box location by exploring the spatial relationship of the pooled intra-object part locations. Extensive experiments are conducted to demonstrate the performance improvements from each component of our proposed framework. Our Part-$A^2$ net outperforms all existing 3D detection methods and achieves new state-of-the-art on KITTI 3D object detection dataset by utilizing only the LiDAR point cloud data. Code is available at https://github.com/sshaoshuai/PointCloudDet3D.
We investigate the problem of learning category-specific 3D shape reconstruction from a variable number of RGB views of previously unobserved object instances. Most approaches for multiview shape reconstruction operate on sparse shape representations, or assume a fixed number of views. We present a method that can estimate dense 3D shape, and aggregate shape across multiple and varying number of input views. Given a single input view of an object instance, we propose a representation that encodes the dense shape of the visible object surface as well as the surface behind line of sight occluded by the visible surface. When multiple input views are available, the shape representation is designed to be aggregated into a single 3D shape using an inexpensive union operation. We train a 2D CNN to learn to predict this representation from a variable number of views (1 or more). We further aggregate multiview information by using permutation equivariant layers that promote order-agnostic view information exchange at the feature level. Experiments show that our approach is able to produce dense 3D reconstructions of objects that improve in quality as more views are added.
Video object segmentation (VOS) aims at pixel-level object tracking given only the annotations in the first frame. Due to the large visual variations of objects in video and the lack of training samples, it remains a difficult task despite the upsurging development of deep learning. Toward solving the VOS problem, we bring in several new insights by the proposed unified framework consisting of object proposal, tracking and segmentation components. The object proposal network transfers objectness information as generic knowledge into VOS; the tracking network identifies the target object from the proposals; and the segmentation network is performed based on the tracking results with a novel dynamic-reference based model adaptation scheme. Extensive experiments have been conducted on the DAVIS'17 dataset and the YouTube-VOS dataset, our method achieves the state-of-the-art performance on several video object segmentation benchmarks. We make the code publicly available at https://github.com/sydney0zq/PTSNet.
The study of object representations in computer vision has primarily focused on developing representations that are useful for image classification, object detection, or semantic segmentation as downstream tasks. In this work we aim to learn object representations that are useful for control and reinforcement learning (RL). To this end, we introduce Transporter, a neural network architecture for discovering concise geometric object representations in terms of keypoints or image-space coordinates. Our method learns from raw video frames in a fully unsupervised manner, by transporting learnt image features between video frames using a keypoint bottleneck. The discovered keypoints track objects and object parts across long time-horizons more accurately than recent similar methods. Furthermore, consistent long-term tracking enables two notable results in control domains -- (1) using the keypoint co-ordinates and corresponding image features as inputs enables highly sample-efficient reinforcement learning; (2) learning to explore by controlling keypoint locations drastically reduces the search space, enabling deep exploration (leading to states unreachable through random action exploration) without any extrinsic rewards.
Data augmentation is a critical component of training deep learning models. Although data augmentation has been shown to significantly improve image classification, its potential has not been thoroughly investigated for object detection. Given the additional cost for annotating images for object detection, data augmentation may be of even greater importance for this computer vision task. In this work, we study the impact of data augmentation on object detection. We first demonstrate that data augmentation operations borrowed from image classification may be helpful for training detection models, but the improvement is limited. Thus, we investigate how learned, specialized data augmentation policies improve generalization performance for detection models. Importantly, these augmentation policies only affect training and leave a trained model unchanged during evaluation. Experiments on the COCO dataset indicate that an optimized data augmentation policy improves detection accuracy by more than +2.3 mAP, and allow a single inference model to achieve a state-of-the-art accuracy of 50.7 mAP. Importantly, the best policy found on COCO may be transferred unchanged to other detection datasets and models to improve predictive accuracy. For example, the best augmentation policy identified with COCO improves a strong baseline on PASCAL-VOC by +2.7 mAP. Our results also reveal that a learned augmentation policy is superior to state-of-the-art architecture regularization methods for object detection, even when considering strong baselines. Code for training with the learned policy is available online at https://github.com/tensorflow/tpu/tree/master/models/official/detection
In recent years, Convolutional Neural Networks (CNNs) have shown superior capability in visual learning tasks. While accuracy-wise CNNs provide unprecedented performance, they are also known to be computationally intensive and energy demanding for modern computer systems. In this paper, we propose Virtual Pooling (ViP), a model-level approach to improve speed and energy consumption of CNN-based image classification and object detection tasks, with a provable error bound. We show the efficacy of ViP through experiments on four CNN models, three representative datasets, both desktop and mobile platforms, and two visual learning tasks, i.e., image classification and object detection. For example, ViP delivers 2.1x speedup with less than 1.5% accuracy degradation in ImageNet classification on VGG-16, and 1.8x speedup with 0.025 mAP degradation in PASCAL VOC object detection with Faster-RCNN. ViP also reduces mobile GPU and CPU energy consumption by up to 55% and 70%, respectively. As a complementary method to existing acceleration approaches, ViP achieves 1.9x speedup on ThiNet leading to a combined speedup of 5.23x on VGG-16. Furthermore, ViP provides a knob for machine learning practitioners to generate a set of CNN models with varying trade-offs between system speed/energy consumption and accuracy to better accommodate the requirements of their tasks. Code is available at https://github.com/cmu-enyac/VirtualPooling.
Extracting and predicting object structure and dynamics from videos without supervision is a major challenge in machine learning. To address this challenge, we adopt a keypoint-based image representation and learn a stochastic dynamics model of the keypoints. Future frames are reconstructed from the keypoints and a reference frame. By modeling dynamics in the keypoint coordinate space, we achieve stable learning and avoid compounding of errors in pixel space. Our method improves upon unstructured representations both for pixel-level video prediction and for downstream tasks requiring object-level understanding of motion dynamics. We evaluate our model on diverse datasets: a multi-agent sports dataset, the Human3.6M dataset, and datasets based on continuous control tasks from the DeepMind Control Suite. The spatially structured representation outperforms unstructured representations on a range of motion-related tasks such as object tracking, action recognition and reward prediction.
Scientific imaging techniques such as optical and electron microscopy and computed tomography (CT) scanning are used to study the 3D structure of an object through 2D observations. These observations are related to the original 3D object through orthogonal integral projections. For common 3D reconstruction algorithms, computational efficiency requires the modeling of the 3D structures to take place in Fourier space by applying the Fourier slice theorem. At present, it is unclear how to differentiate through the projection operator, and hence current learning algorithms can not rely on gradient based methods to optimize 3D structure models. In this paper we show how back-propagation through the projection operator in Fourier space can be achieved. We demonstrate the validity of the approach with experiments on 3D reconstruction of proteins. We further extend our approach to learning probabilistic models of 3D objects. This allows us to predict regions of low sampling rates or estimate noise. A higher sample efficiency can be reached by utilizing the learned uncertainties of the 3D structure as an unsupervised estimate of the model fit. Finally, we demonstrate how the reconstruction algorithm can be extended with an amortized inference scheme on unknown attributes such as object pose. Through empirical studies we show that joint inference of the 3D structure and the object pose becomes more difficult when the ground truth object contains more symmetries. Due to the presence of for instance (approximate) rotational symmetries, the pose estimation can easily get stuck in local optima, inhibiting a fine-grained high-quality estimate of the 3D structure.
Solving complex, temporally-extended tasks is a long-standing problem in reinforcement learning (RL). We hypothesize that one critical element of solving such problems is the notion of compositionality. With the ability to learn concepts and sub-skills that can be composed to solve longer tasks, i.e. hierarchical RL, we can acquire temporally-extended behaviors. However, acquiring effective yet general abstractions for hierarchical RL is remarkably challenging. In this paper, we propose to use language as the abstraction, as it provides unique compositional structure, enabling fast learning and combinatorial generalization, while retaining tremendous flexibility, making it suitable for a variety of problems. Our approach learns an instruction-following low-level policy and a high-level policy that can reuse abstractions across tasks, in essence, permitting agents to reason using structured language. To study compositional task learning, we introduce an open-source object interaction environment built using the MuJoCo physics engine and the CLEVR engine. We find that, using our approach, agents can learn to solve to diverse, temporally-extended tasks such as object sorting and multi-object rearrangement, including from raw pixel observations. Our analysis reveals that the compositional nature of language is critical for learning diverse sub-skills and systematically generalizing to new sub-skills in comparison to non-compositional abstractions that use the same supervision.
Objects are composed of a set of geometrically organized parts. We introduce an unsupervised capsule autoencoder (SCAE), which explicitly uses geometric relationships between parts to reason about objects. Since these relationships do not depend on the viewpoint, our model is robust to viewpoint changes. SCAE consists of two stages. In the first stage, the model predicts presences and poses of part templates directly from the image and tries to reconstruct the image by appropriately arranging the templates. In the second stage, SCAE predicts parameters of a few object capsules, which are then used to reconstruct part poses. Inference in this model is amortized and performed by off-the-shelf neural encoders, unlike in previous capsule networks. We find that object capsule presences are highly informative of the object class, which leads to state-of-the-art results for unsupervised classification on SVHN (55%) and MNIST (98.7%). The code is available at https://github.com/google-research/google-research/tree/master/stacked_capsule_autoencoders