In this paper, we propose TEDL, a two-stage learning approach to quantify uncertainty for deep learning models in classification tasks, inspired by our findings in experimenting with Evidential Deep Learning (EDL) method, a recently proposed uncertainty quantification approach based on the Dempster-Shafer theory. More specifically, we observe that EDL tends to yield inferior AUC compared with models learnt by cross-entropy loss and is highly sensitive in training. Such sensitivity is likely to cause unreliable uncertainty estimation, making it risky for practical applications. To mitigate both limitations, we propose a simple yet effective two-stage learning approach based on our analysis on the likely reasons causing such sensitivity, with the first stage learning from cross-entropy loss, followed by a second stage learning from EDL loss. We also re-formulate the EDL loss by replacing ReLU with ELU to avoid the Dying ReLU issue. Extensive experiments are carried out on varied sized training corpus collected from a large-scale commercial search engine, demonstrating that the proposed two-stage learning framework can increase AUC significantly and greatly improve training robustness.
Entity linking (EL) is the process of linking entity mentions appearing in text with their corresponding entities in a knowledge base. EL features of entities (e.g., prior probability, relatedness score, and entity embedding) are usually estimated based on Wikipedia. However, for newly emerging entities (EEs) which have just been discovered in news, they may still not be included in Wikipedia yet. As a consequence, it is unable to obtain required EL features for those EEs from Wikipedia and EL models will always fail to link ambiguous mentions with those EEs correctly as the absence of their EL features. To deal with this problem, in this paper we focus on a new task of learning EL features for emerging entities in a general way. We propose a novel approach called STAMO to learn high-quality EL features for EEs automatically, which needs just a small number of labeled documents for each EE collected from the Web, as it could further leverage the knowledge hidden in the unlabeled data. STAMO is mainly based on self-training, which makes it flexibly integrated with any EL feature or EL model, but also makes it easily suffer from the error reinforcement problem caused by the mislabeled data. Instead of some common self-training strategies that try to throw the mislabeled data away explicitly, we regard self-training as a multiple optimization process with respect to the EL features of EEs, and propose both intra-slot and inter-slot optimizations to alleviate the error reinforcement problem implicitly. We construct two EL datasets involving selected EEs to evaluate the quality of obtained EL features for EEs, and the experimental results show that our approach significantly outperforms other baseline methods of learning EL features.
Shape information is a strong and valuable prior in segmenting organs in medical images. However, most current deep learning based segmentation algorithms have not taken shape information into consideration, which can lead to bias towards texture. We aim at modeling shape explicitly and using it to help medical image segmentation. Previous methods proposed Variational Autoencoder (VAE) based models to learn the distribution of shape for a particular organ and used it to automatically evaluate the quality of a segmentation prediction by fitting it into the learned shape distribution. Based on which we aim at incorporating VAE into current segmentation pipelines. Specifically, we propose a new unsupervised domain adaptation pipeline based on a pseudo loss and a VAE reconstruction loss under a teacher-student learning paradigm. Both losses are optimized simultaneously and, in return, boost the segmentation task performance. Extensive experiments on three public Pancreas segmentation datasets as well as two in-house Pancreas segmentation datasets show consistent improvements with at least 2.8 points gain in the Dice score, demonstrating the effectiveness of our method in challenging unsupervised domain adaptation scenarios for medical image segmentation. We hope this work will advance shape analysis and geometric learning in medical imaging.
The rapid development of deep learning has made a great progress in segmentation, one of the fundamental tasks of computer vision. However, the current segmentation algorithms mostly rely on the availability of pixel-level annotations, which are often expensive, tedious, and laborious. To alleviate this burden, the past years have witnessed an increasing attention in building label-efficient, deep-learning-based segmentation algorithms. This paper offers a comprehensive review on label-efficient segmentation methods. To this end, we first develop a taxonomy to organize these methods according to the supervision provided by different types of weak labels (including no supervision, coarse supervision, incomplete supervision and noisy supervision) and supplemented by the types of segmentation problems (including semantic segmentation, instance segmentation and panoptic segmentation). Next, we summarize the existing label-efficient segmentation methods from a unified perspective that discusses an important question: how to bridge the gap between weak supervision and dense prediction -- the current methods are mostly based on heuristic priors, such as cross-pixel similarity, cross-label constraint, cross-view consistency, cross-image relation, etc. Finally, we share our opinions about the future research directions for label-efficient deep segmentation.
Open information extraction (OIE) methods extract plenty of OIE triples <noun phrase, relation phrase, noun phrase> from unstructured text, which compose large open knowledge bases (OKBs). Noun phrases and relation phrases in such OKBs are not canonicalized, which leads to scattered and redundant facts. It is found that two views of knowledge (i.e., a fact view based on the fact triple and a context view based on the fact triple's source context) provide complementary information that is vital to the task of OKB canonicalization, which clusters synonymous noun phrases and relation phrases into the same group and assigns them unique identifiers. However, these two views of knowledge have so far been leveraged in isolation by existing works. In this paper, we propose CMVC, a novel unsupervised framework that leverages these two views of knowledge jointly for canonicalizing OKBs without the need of manually annotated labels. To achieve this goal, we propose a multi-view CH K-Means clustering algorithm to mutually reinforce the clustering of view-specific embeddings learned from each view by considering their different clustering qualities. In order to further enhance the canonicalization performance, we propose a training data optimization strategy in terms of data quantity and data quality respectively in each particular view to refine the learned view-specific embeddings in an iterative manner. Additionally, we propose a Log-Jump algorithm to predict the optimal number of clusters in a data-driven way without requiring any labels. We demonstrate the superiority of our framework through extensive experiments on multiple real-world OKB data sets against state-of-the-art methods.
We present a novel vision Transformer, named TUTOR, which is able to learn tubelet tokens, served as highly-abstracted spatiotemporal representations, for video-based human-object interaction (V-HOI) detection. The tubelet tokens structurize videos by agglomerating and linking semantically-related patch tokens along spatial and temporal domains, which enjoy two benefits: 1) Compactness: each tubelet token is learned by a selective attention mechanism to reduce redundant spatial dependencies from others; 2) Expressiveness: each tubelet token is enabled to align with a semantic instance, i.e., an object or a human, across frames, thanks to agglomeration and linking. The effectiveness and efficiency of TUTOR are verified by extensive experiments. Results shows our method outperforms existing works by large margins, with a relative mAP gain of $16.14\%$ on VidHOI and a 2 points gain on CAD-120 as well as a $4 \times$ speedup.
Community Question Answering (CQA) platforms contain plenty of CQA texts (i.e., questions and answers corresponding to the question) where named entities appear ubiquitously. In this paper, we define a new task of CQA entity linking (CQAEL) as linking the textual entity mentions detected from CQA texts with their corresponding entities in a knowledge base. This task can facilitate many downstream applications including expert finding and knowledge base enrichment. Traditional entity linking methods mainly focus on linking entities in news documents, and are suboptimal over this new task of CQAEL since they cannot effectively leverage various informative auxiliary data involved in the CQA platform to aid entity linking, such as parallel answers and two types of meta-data (i.e., topic tags and users). To remedy this crucial issue, we propose a novel transformer-based framework to effectively harness the knowledge delivered by different kinds of auxiliary data to promote the linking performance. We validate the superiority of our framework through extensive experiments over a newly released CQAEL data set against state-of-the-art entity linking methods.
The appearances of children are inherited from their parents, which makes it feasible to predict them. Predicting realistic children's faces may help settle many social problems, such as age-invariant face recognition, kinship verification, and missing child identification. It can be regarded as an image-to-image translation task. Existing approaches usually assume domain information in the image-to-image translation can be interpreted by "style", i.e., the separation of image content and style. However, such separation is improper for the child face prediction, because the facial contours between children and parents are not the same. To address this issue, we propose a new disentangled learning strategy for children's face prediction. We assume that children's faces are determined by genetic factors (compact family features, e.g., face contour), external factors (facial attributes irrelevant to prediction, such as moustaches and glasses), and variety factors (individual properties for each child). On this basis, we formulate predictions as a mapping from parents' genetic factors to children's genetic factors, and disentangle them from external and variety factors. In order to obtain accurate genetic factors and perform the mapping, we propose a ChildPredictor framework. It transfers human faces to genetic factors by encoders and back by generators. Then, it learns the relationship between the genetic factors of parents and children through a mapping function. To ensure the generated faces are realistic, we collect a large Family Face Database to train ChildPredictor and evaluate it on the FF-Database validation set. Experimental results demonstrate that ChildPredictor is superior to other well-known image-to-image translation methods in predicting realistic and diverse child faces. Implementation codes can be found at https://github.com/zhaoyuzhi/ChildPredictor.
With the rapid development of multimedia technology, Augmented Reality (AR) has become a promising next-generation mobile platform. The primary theory underlying AR is human visual confusion, which allows users to perceive the real-world scenes and augmented contents (virtual-world scenes) simultaneously by superimposing them together. To achieve good Quality of Experience (QoE), it is important to understand the interaction between two scenarios, and harmoniously display AR contents. However, studies on how this superimposition will influence the human visual attention are lacking. Therefore, in this paper, we mainly analyze the interaction effect between background (BG) scenes and AR contents, and study the saliency prediction problem in AR. Specifically, we first construct a Saliency in AR Dataset (SARD), which contains 450 BG images, 450 AR images, as well as 1350 superimposed images generated by superimposing BG and AR images in pair with three mixing levels. A large-scale eye-tracking experiment among 60 subjects is conducted to collect eye movement data. To better predict the saliency in AR, we propose a vector quantized saliency prediction method and generalize it for AR saliency prediction. For comparison, three benchmark methods are proposed and evaluated together with our proposed method on our SARD. Experimental results demonstrate the superiority of our proposed method on both of the common saliency prediction problem and the AR saliency prediction problem over benchmark methods. Our data collection methodology, dataset, benchmark methods, and proposed saliency models will be publicly available to facilitate future research.
Palmprints are private and stable information for biometric recognition. In the deep learning era, the development of palmprint recognition is limited by the lack of sufficient training data. In this paper, by observing that palmar creases are the key information to deep-learning-based palmprint recognition, we propose to synthesize training data by manipulating palmar creases. Concretely, we introduce an intuitive geometric model which represents palmar creases with parameterized B\'ezier curves. By randomly sampling B\'ezier parameters, we can synthesize massive training samples of diverse identities, which enables us to pretrain large-scale palmprint recognition models. Experimental results demonstrate that such synthetically pretrained models have a very strong generalization ability: they can be efficiently transferred to real datasets, leading to significant performance improvements on palmprint recognition. For example, under the open-set protocol, our method improves the strong ArcFace baseline by more than 10\% in terms of TAR@1e-6. And under the closed-set protocol, our method reduces the equal error rate (EER) by an order of magnitude.