United States

Visual tracking has achieved great progress due to numerous different algorithms. However, deep trackers based on classification or Siamese network still have their specific limitations. In this work, we show how to teach machines to track a generic object in videos like humans, who can use a few search steps to perform tracking. By constructing a Markov decision process in Deep Reinforcement Learning (DRL), our agents can learn to determine hierarchical decisions on tracking mode and motion estimation. To be specific, our Hierarchical DRL framework is composed of a Siamese-based observation network which models the motion information of an arbitrary target, a policy network for mode switch and an actor-critic network for box regression. This tracking strategy is more in line with human behavior paradigm, and is effective and efficient to cope with fast motion, background clutter and large deformations. Extensive experiments on the GOT-10k, OTB-100, UAV-123, VOT and LaSOT tracking benchmarks, demonstrate that the proposed tracker achieves state-of-the-art performance while running in real-time.

AAAI 2021

Visual Tracking via Hierarchical Deep Reinforcement Learning

technical paper

The purpose of the AAAI conference is to promote research in artificial intelligence (AI) and scientific exchange among AI researchers, practitioners, scientists, and engineers in affiliated disciplines. 

Automated mathematical reasoning is a challenging problem that requires an agent to learn algebraic patterns that contain long-range dependencies. Two particular tasks that test this type of reasoning are (1)mathematical equation verification,which requires determining whether trigonometric and linear algebraic statements are valid identities or not, and (2)equation completion, which entails filling in a blank within an expression to make it true. Solving these tasks with deep learning requires that the neural model learn how to manipulate and compose various algebraic symbols, carrying this ability over to previously unseen expressions. Artificial neural net-works, including recurrent networks and transformers, struggle  to  generalize  on  these  kinds  of  difficult  compositional problems,  often  exhibiting  poor  extrapolation  performance.In  contrast,  recursive  neural  networks  (recursive-NNs)  are,theoretically, capable of achieving better extrapolation due to their tree-like design but are very difficult to optimize as the depth  of  their  underlying  tree  structure  increases.  To  over-come this, we extend recursive-NNs to utilize multiplicative,higher-order synaptic connections and, furthermore, to learn to dynamically control and manipulate an external memory.We argue that this key modification gives the neural system the ability to capture powerful transition functions for each possible input. We demonstrate the effectiveness of our pro-posed higher-order, memory-augmented recursive-NN models on two challenging mathematical equation tasks, showing improved extrapolation, stable performance, and faster convergence. We show that our models achieve 1.53% average improvement over current state-of-the-art methods in equation verification and achieve 2.22% top-1 average accuracy and 2.96% top-5 average accuracy for equation completion.

Recognizing and Verifying Mathematical Equations Using Multiplicative Differential Neural Units

One-Shot architecture search, which aims to explore all possible operations jointly based on a single model, has been an active direction of Neural Architecture Search (NAS). As a well-known one-shot solution, Differentiable Architecture Search (DARTS) performs continuous relaxation on the architecture's importance and results in a bi-level optimization problem. However, as many recent studies have shown, DARTS cannot always work robustly for new tasks, which is mainly due to the approximate solution of the bi-level optimization. In this paper, one-shot neural architecture search is addressed by adopting a directed probabilistic graphical model to represent the joint probability distribution over data and model. Then, neural architectures are searched for and optimized by Gibbs sampling. We rethink the bi-level optimization problem as the task of Gibbs sampling from the posterior distribution, which expresses the preferences for different models given the observed dataset. We evaluate our proposed NAS method -- GibbsNAS on the search space used in DARTS/ENAS and the search space of NAS-Bench-201. Experimental results on multiple search space show the efficacy and stability of our approach.

Rethinking Bi-Level Optimization in Neural Architecture Search: A Gibbs Sampling Perspective

As one of the most powerful topic models, Latent Dirichlet Allocation (LDA) has been used in a vast range of tasks, including document understanding, information retrieval and peer-reviewer assignment. Despite its tremendous popularity, the security of LDA has rarely been studied. This poses severe risks to security-critical tasks such as sentiment analysis and peer-reviewer assignment that are based on LDA. In this paper, we are interested in knowing whether LDA models are vulnerable to adversarial perturbations of benign document examples during inference time. We formalize the evasion attack to LDA models as an optimization problem and prove it to be NP-hard. We then propose a novel and efficient algorithm, EvaLDA to solve it. We show the effectiveness of EvaLDA via extensive empirical evaluations. For instance, in the NIPS dataset, EvaLDA can averagely promote the rank of a target topic from 10 to around 7 by only replacing 1% of the words with similar words in a victim document. Our work provides significant insights into the power and limitations of evasion attacks to LDA models.

EvaLDA: Efficient Evasion Attacks Towards Latent Dirichlet Allocation

How can we track synchronized behavior in a stream of time-stamped tuples, such as mobile devices installing and uninstalling applications in the lockstep, to boost their ranks in the app store?  We model such tuples as entries in a streaming tensor, which augments attribute sizes in its modes over time. Synchronized behavior tends to form dense blocks (i.e.~subtensors) in such a tensor, signaling anomalous behavior, or interesting communities. However, existing dense block detection methods are either based on a static tensor, or lack an efficient algorithm in a streaming setting. Therefore, we propose a fast streaming algorithm, AUGSPLICING, which can detect the top dense blocks by incrementally splicing the previous detection with the incoming ones in new tuples, avoiding re-runs over all the history data at every tracking time step. AUGSPLICING is based on a splicing condition that guides the algorithm (Section 4). Compared to the state-of-the-art methods, our method is (1) effective to detect fraudulent behavior in installing data of real-world apps and find a synchronized group of students with interesting features in campus Wi-Fi data; (2) robust with splicing theory for dense block detection; (3) streaming and faster than the existing streaming algorithm, with closely comparable accuracy.

AugSplicing: Synchronized Behavior Detection in Streaming Tensors

Almost all existing amodal segmentation methods make the inferences of occluded regions by using features corresponding to the whole image. This is against the human's amodal perception, where human uses the visible part and the shape prior knowledge of the target to infer the occluded region. To mimic the behavior of human and solve the ambiguity in the learning, we propose a framework, it firstly estimates a coarse visible mask and a coarse amodal mask. Then based on the coarse prediction, our model infers the amodal mask by concentrating on the visible region and utilizing the shape prior in the memory. In this way, features corresponding to background and occlusion can be suppressed for amodal mask estimation. Consequently, the amodal mask would not be affected by what the occlusion is given the same visible regions. The leverage of shape prior makes the amodal mask estimation more robust and reasonable. Our proposed model is evaluated on three datasets. Experiments show that our proposed model outperforms existing state-of-the-art methods. The visualization of shape prior indicates that the category-specific feature in the codebook has certain interpretability. The code is available at https://github.com/YutingXiao/Amodal-Segmentation-Based-on-Visible-Region-Segmentation-and-Shape-Prior.

Amodal Segmentation Based on Visible Region Segmentation and Shape Prior

Cascaded architectures have brought significant performance improvement in object detection and instance segmentation. However, there are lingering issues regarding the disparity in the Intersection-over-Union (IoU) distribution of the samples between training and inference. This disparity can potentially exacerbate detection accuracy. This paper proposes an architecture referred to as Sample Consistency Network (SCNet) to ensure that the IoU distribution of the samples at training time is close to that at inference time. Furthermore, SCNet incorporates feature relay and utilizes global contextual information to further reinforce the reciprocal relationships among classifying, detecting, and segmenting sub-tasks. Extensive experiments on the standard COCO dataset reveal the effectiveness of the proposed method over multiple evaluation metrics, including box AP, mask AP, and inference speed. In particular, while running 38\% faster, the proposed SCNet improves the AP of the box and mask predictions by respectively 1.3 and 2.3 points compared to the strong Cascade Mask R-CNN baseline. Code is available at https://github.com/thangvubk/SCNet.

SCNet: Training Inference Sample Consistency for Instance Segmentation

TACRED is one of the largest and most widely used sentence-level relation extraction datasets. Proposed models that are evaluated using this dataset consistently set new state-of-the-art performance. However, they still exhibit large error rates despite leveraging external knowledge and unsupervised pretraining on large text corpora. A recent study suggested that this may be due to poor dataset quality. The study observed that over 50% of the most challenging sentences from the development and test sets are incorrectly labeled and account for an average drop of 8% f1-score in model performance. However, this study was limited to a small biased sample of 5k (out of a total of 106k) sentences, substantially restricting the generalizability and broader implications of its findings. In this paper, we address these shortcomings by: (i) performing a comprehensive study over the whole TACRED dataset, (ii) proposing an improved crowdsourcing strategy and deploying it to re-annotate the whole dataset, and (iii) performing a thorough analysis to understand how correcting the TACRED annotations affects previously published results. After verification, we observed that 23.9% of TACRED labels are incorrect. Moreover, evaluating several models on our revised dataset yields an average f1-score improvement of 14.3% and helps uncover significant relationships between the different models (rather than simply offsetting or scaling their scores by a constant factor). Finally, aside from our analysis we also release Re-TACRED, a new completely re-annotated version of the TACRED dataset that can be used to perform reliable evaluation of relation extraction models.

Re-TACRED: Addressing Shortcomings of the TACRED Dataset

As mobile devices are becoming ubiquitous, regularly interacting with a variety of user interfaces (UIs) is a common aspect of daily life for many people. To improve the accessibility of these devices and to enable their usage in a variety of settings, building models that can assist users and accomplish tasks through the UI is vitally important. However, there are several challenges to achieve this. First, UI components of similar appearance can have different functionalities, making understanding their function more important than just analyzing their appearance. Second, domain-specific features like Document Object Model (DOM) in web pages and View Hierarchy (VH) in mobile applications provide important signals about the semantics of UI elements, but these features are not in a natural language format. Third, owing to a large diversity in UIs and absence of standard DOM or VH representations, building a UI understanding model with high coverage requires large amounts of training data. 

Inspired by the success of pre-training based approaches in NLP for tackling a variety of problems in a data-efficient way, we introduce a new pre-trained UI representation model called ActionBert. Our methodology is designed to leverage visual, linguistic and domain-specific features in user interaction traces to pre-train generic feature representations of UIs and their components. Our key intuition is that user actions, e.g., a sequence of clicks on different UI components, reveals important information about their functionality. We evaluate the proposed model on a wide variety of downstream tasks, ranging from icon classification to UI component retrieval based on its natural language description. Experiments show that the proposed ActionBert model outperforms multi-modal baselines across all downstream tasks by up to 15.5%.

ActionBert: Leveraging User Actions for Semantic Understanding of User Interfaces

Visible-infrared cross modality person re-identification (VI-ReID) is a core but challenging technology in the 24-hours intelligent surveillance system. How to eliminate the large modality gap lies in the heart of VI-ReID. Conventional methods mainly focus on directly aligning the heterogeneous modalities into the same space. However, due to the unbalanced color information between the visible and infrared images, the features of visible images tend to overfit the clothing color information, which would be harmful to the modality alignment. Besides, these methods mainly align the heterogeneous feature distributions in dataset-level while ignoring the valuable identity information, which may cause the feature misalignment of some identities and weaken the discrimination of features. To tackle above problems, we propose a novel approach for VI-ReID. It learns the color-irrelevant features through the color-irrelevant consistency learning (CICL) and aligns the identity-level feature distributions by the identity-aware modality adaptation (IAMA). The CICL and IAMA are integrated into a joint learning framework and can promote each other. Extensive experiments on two popular datasets SYSU-MM01 and RegDB demonstrate the superiority and effectiveness of our approach against the state-of-the-art methods.

Joint Color-Irrelevant Consistency Learning and Identity-Aware Modality Adaptation for Visible-Infrared Cross Modality Person Re-Identification

This paper explores meta-learning in sequential recommendation to alleviate the item cold-start problem. Sequential recommendation aims to capture user's dynamic preferences based on historical behavior sequences and acts as a key component of most online recommendation scenarios. However, most previous methods have trouble recommending cold-start items, which are prevalent in those scenarios. As there is generally no side information in sequential recommendation task, previous cold-start methods could not be applied when only user-item interactions are available. Thus, we propose a Meta-learning-based Cold-Start Sequential Recommendation Framework, namely Mecos, to mitigate the item cold-start problem in sequential recommendation. This task is non-trivial as it targets at an important problem in a novel and challenging context. Mecos effectively extracts user preference from limited interactions and learns to match the target cold-start item with the potential user. Besides, our framework can be painlessly integrated with neural network-based models. Extensive experiments conducted on three real-world datasets verify the superiority of Mecos, with the average improvement up to 99%, 91%, and 70% in HR@10 over state-of-the-art baseline methods.

Downloads

Next from AAAI 2021

Recognizing and Verifying Mathematical Equations Using Multiplicative Differential Neural Units

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from AAAI 2021

Recognizing and Verifying Mathematical Equations Using Multiplicative Differential Neural Units

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Downloads