State-of-the-art 3D human pose estimation approaches typically estimate pose from the entire RGB image in a single forward run. In this paper, we develop a post-processing step to refine 3D human pose estimation from body part patches. Using local patches as input has two advantages. First, the fine details around body parts are zoomed in to high resolution for preciser 3D pose prediction. Second, it enables the part appearance to be shared between poses to benefit rare poses. In order to acquire informative representation of patches, we explore different input modalities and validate the superiority of fusing predicted segmentation with RGB. We show that our method consistently boosts the accuracy of state-of-the-art 3D human pose methods.
There has been a debate in medical image segmentation on whether to use 2D or 3D networks, where both pipelines have advantages and disadvantages. This paper presents a novel approach which thickens the input of a 2D network, so that the model is expected to enjoy both the stability and efficiency of 2D networks as well as the ability of 3D networks in modeling volumetric contexts. A major information loss happens when a large number of 2D slices are fused at the first convolutional layer, resulting in a relatively weak ability of the network in distinguishing the difference among slices. To alleviate this drawback, we propose an effective framework which (i) postpones slice fusion and (ii) adds highway connections from the pre-fusion layer so that the prediction layer receives slice-sensitive auxiliary cues. Experiments on segmenting a few abdominal targets in particular blood vessels which require strong 3D contexts demonstrate the effectiveness of our approach.
This paper focuses on learning transferable adversarial examples specifically against defense models (models to defense adversarial attacks). In particular, we show that a simple universal perturbation can fool a series of state-of-the-art defenses. Adversarial examples generated by existing attacks are generally hard to transfer to defense models. We observe the property of regional homogeneity in adversarial perturbations and suggest that the defenses are less robust to regionally homogeneous perturbations. Therefore, we propose an effective transforming paradigm and a customized gradient transformer module to transform existing perturbations into regionally homogeneous ones. Without explicitly forcing the perturbations to be universal, we observe that a well-trained gradient transformer module tends to output input-independent gradients (hence universal) benefiting from the under-fitting phenomenon. Thorough experiments demonstrate that our work significantly outperforms the prior art attacking algorithms (either image-dependent or universal ones) by an average improvement of 14.0% when attacking 9 defenses in the black-box setting. In addition to the cross-model transferability, we also verify that regionally homogeneous perturbations can well transfer across different vision tasks (attacking with the semantic segmentation task and testing on the object detection task).
Integrating multi-phase information is an effective way of boosting visual recognition. In this paper, we investigate this problem from the perspective of medical imaging analysis, in which two phases in CT scans known as arterial and venous are combined towards higher segmentation accuracy. To this end, we propose Phase Collaborative Network (PCN), an end-to-end network which contains both generative and discriminative modules to formulate phase-to-phase relations and data-to-label relations, respectively. Experiments are performed on several CT image segmentation datasets. PCN achieves superior performance with either two phases or only one phase available. Moreover, we empirically verify that the accuracy gain comes from the collaboration between phases.
Training a robotic arm to accomplish real-world tasks has been attracting increasing attention in both academia and industry. This work discusses the role of computer vision algorithms in this field. We focus on low-cost arms on which no sensors are equipped and thus all decisions are made upon visual recognition, e.g., real-time 3D pose estimation. This requires annotating a lot of training data, which is not only time-consuming but also laborious. In this paper, we present an alternative solution, which uses a 3D model to create a large number of synthetic data, trains a vision model in this virtual domain, and applies it to real-world images after domain adaptation. To this end, we design a semi-supervised approach, which fully leverages the geometric constraints among keypoints. We apply an iterative algorithm for optimization. Without any annotations on real images, our algorithm generalizes well and produces satisfying results on 3D pose estimation, which is evaluated on two real-world datasets. We also construct a vision-based control system for task accomplishment, for which we train a reinforcement learning agent in a virtual environment and apply it to the real-world. Moreover, our approach, with merely a 3D model being required, has the potential to generalize to other types of multi-rigid-body dynamic systems.
We focus on an important yet challenging problem: using a 2D deep network to deal with 3D segmentation for medical imaging analysis. Existing approaches either applied multi-view planar (2D) networks or directly used volumetric (3D) networks for this purpose, but both of them are not ideal: 2D networks cannot capture 3D contexts effectively, and 3D networks are both memory-consuming and less stable arguably due to the lack of pre-trained models. In this paper, we bridge the gap between 2D and 3D using a novel approach named Elastic Boundary Projection (EBP). The key observation is that, although the object is a 3D volume, what we really need in segmentation is to find its boundary which is a 2D surface. Therefore, we place a number of pivot points in the 3D space, and for each pivot, we determine its distance to the object boundary along a dense set of directions. This creates an elastic shell around each pivot which is initialized as a perfect sphere. We train a 2D deep network to determine whether each ending point falls within the object, and gradually adjust the shell so that it gradually converges to the actual shape of the boundary and thus achieves the goal of segmentation. EBP allows 3D segmentation without cutting the volume into slices or small patches, which stands out from conventional 2D and 3D approaches. EBP achieves promising accuracy in segmenting several abdominal organs from CT scans.
Learning visual features from unlabeled image data is an important yet challenging task, which is often achieved by training a model on some annotation-free information. We consider spatial contexts, for which we solve so-called jigsaw puzzles, i.e., each image is cut into grids and then disordered, and the goal is to recover the correct configuration. Existing approaches formulated it as a classification task by defining a fixed mapping from a small subset of configurations to a class set, but these approaches ignore the underlying relationship between different configurations and also limit their application to more complex scenarios. This paper presents a novel approach which applies to jigsaw puzzles with an arbitrary grid size and dimensionality. We provide a fundamental and generalized principle, that weaker cues are easier to be learned in an unsupervised manner and also transfer better. In the context of puzzle recognition, we use an iterative manner which, instead of solving the puzzle all at once, adjusts the order of the patches in each step until convergence. In each step, we combine both unary and binary features on each patch into a cost function judging the correctness of the current configuration. Our approach, by taking similarity between puzzles into consideration, enjoys a more reasonable way of learning visual knowledge. We verify the effectiveness of our approach in two aspects. First, it is able to solve arbitrarily complex puzzles, including high-dimensional puzzles, that prior methods are difficult to handle. Second, it serves as a reliable way of network initialization, which leads to better transfer performance in a few visual recognition tasks including image classification, object detection, and semantic segmentation.
Optimizing a deep neural network is a fundamental task in computer vision, yet direct training methods often suffer from over-fitting. Teacher-student optimization aims at providing complementary cues from a model trained previously, but these approaches are often considerably slow due to the pipeline of training a few generations in sequence, i.e., time complexity is increased by several times. This paper presents snapshot distillation (SD), the first framework which enables teacher-student optimization in one generation. The idea of SD is very simple: instead of borrowing supervision signals from previous generations, we extract such information from earlier epochs in the same generation, meanwhile make sure that the difference between teacher and student is sufficiently large so as to prevent under-fitting. To achieve this goal, we implement SD in a cyclic learning rate policy, in which the last snapshot of each cycle is used as the teacher for all iterations in the next cycle, and the teacher signal is smoothed to provide richer information. In standard image classification benchmarks such as CIFAR100 and ILSVRC2012, SD achieves consistent accuracy gain without heavy computational overheads. We also verify that models pre-trained with SD transfers well to object detection and semantic segmentation in the PascalVOC dataset.
Computer vision is difficult, partly because the mathematical function connecting input and output data is often complex, fuzzy and thus hard to learn. A currently popular solution is to design a deep neural network and optimize it on a large-scale dataset. However, as the number of parameters increases, the generalization ability is often not guaranteed, e.g., the model can over-fit due to the limited amount of training data, or fail to converge because the desired function is too difficult to learn. This paper presents an effective framework named progressive recurrent learning (PRL). The core idea is similar to curriculum learning which gradually increases the difficulty of training data. We generalize it to a wide range of vision problems that were previously considered less proper to apply curriculum learning. PRL starts with inserting a recurrent prediction scheme, based on the motivation of feeding the prediction of a vision model to the same model iteratively, so that the auxiliary cues contained in it can be exploited to improve the quality of itself. In order to better optimize this framework, we start with providing perfect prediction, i.e., ground-truth, to the second stage, but gradually replace it with the prediction of the first stage. In the final status, the ground-truth information is not needed any more, so that the entire model works on the real data distribution as in the testing process. We apply PRL to two challenging visual recognition tasks, namely, object localization and semantic segmentation, and demonstrate consistent accuracy gain compared to the baseline training strategy, especially in the scenarios of more difficult vision tasks.
We introduce PreCo, a large-scale English dataset for coreference resolution. The dataset is designed to embody the core challenges in coreference, such as entity representation, by alleviating the challenge of low overlap between training and test sets and enabling separated analysis of mention detection and mention clustering. To strengthen the training-test overlap, we collect a large corpus of about 38K documents and 12.4M words which are mostly from the vocabulary of English-speaking preschoolers. Experiments show that with higher training-test overlap, error analysis on PreCo is more efficient than the one on OntoNotes, a popular existing dataset. Furthermore, we annotate singleton mentions making it possible for the first time to quantify the influence that a mention detector makes on coreference resolution performance. The dataset is freely available at https://preschool-lab.github.io/PreCo/.