United States

Hand and face play an important role in expressing sign language. Their features are usually especially leveraged to improve system performance. However, to effectively extract visual representations and capture trajectories for hands and face, previous methods always come at high computations with increased training complexity. They usually employ extra heavy pose-estimation networks to locate human body keypoints or rely on additional pre-extracted heatmaps for supervision. To relieve this problem, we propose a self-emphasizing network (SEN) to emphasize informative spatial regions in a self-motivated way, with few extra computations and without additional expensive supervision. Specifically, SEN first employs a lightweight subnetwork to incorporate local spatial-temporal features to identify informative regions, and then dynamically augment original features via attention maps. It&#39;s also observed that not all frames contribute equally to recognition. We present a temporal self-emphasizing module to adaptively emphasize those discriminative frames and suppress redundant ones. A comprehensive comparison with previous methods equipped with hand and face features demonstrates the superiority of our method, even though they always require huge computations and rely on expensive extra supervision. Remarkably, with few extra computations, SEN achieves new state-of-the-art accuracy on four large-scale datasets, PHOENIX14, PHOENIX14-T, CSL-Daily, and CSL. Visualizations verify the effects of SEN on emphasizing informative spatial and temporal features.

AAAI 2023

Self-Emphasizing Network for Continuous Sign Language Recognition

lightweight multi-scale architecture

hands and face features

continuous sign language recognition

The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines. AAAI-23 is the Thirty-Seventh AAAI Conference on Artificial Intelligence. The theme of this conference is to create collaborative bridges within and beyond AI. Like previous AAAI conferences, AAAI-23 will feature technical paper presentations, special tracks, invited speakers, workshops, tutorials, poster sessions, senior member presentations, competitions, and exhibit programs, and two new activities: a Bridge Program and a Lab Program. Many of these activities are tailored to the theme of bridges and all are selected according to the highest standards, with additional programs for students and young researchers. 
AAAI is providing you with a conference planner, which you can use to help organize your itinerary of activities. This includes talks to attend in person, talks to attend remotely, breaks with colleagues and your site seeing activities. To access this conference planner, please go to [https://aaai-2023.takemobi.io](https://aaai-2023.takemobi.io).

In order to access this site, you need to register. If you haven't already, please register [here](https://aaai.org/Conferences/AAAI-23/registration/).


The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines.

Hand and face play an important role in expressing sign language. Their features are usually especially leveraged to improve system performance. However, to effectively extract visual representations and capture trajectories for hands and face, previous methods always come at high computations with increased training complexity. They usually employ extra heavy pose-estimation networks to locate human body keypoints or rely on additional pre-extracted heatmaps for supervision. To relieve this problem, we propose a self-emphasizing network (SEN) to emphasize informative spatial regions in a self-motivated way, with few extra computations and without additional expensive supervision. Specifically, SEN first employs a lightweight subnetwork to incorporate local spatial-temporal features to identify informative regions, and then dynamically augment original features via attention maps. It's also observed that not all frames contribute equally to recognition. We present a temporal self-emphasizing module to adaptively emphasize those discriminative frames and suppress redundant ones. A comprehensive comparison with previous methods equipped with hand and face features demonstrates the superiority of our method, even though they always require huge computations and rely on expensive extra supervision. Remarkably, with few extra computations, SEN achieves new state-of-the-art accuracy on four large-scale datasets, PHOENIX14, PHOENIX14-T, CSL-Daily, and CSL. Visualizations verify the effects of SEN on emphasizing informative spatial and temporal features.

poster

Although multilingual pretrained models (mPLMs) enabled support of various natural language processing in diverse languages, its limited coverage of 100+ languages lets 6500+ languages remain ‘unseen’. One common approach for an unseen language is specializing the model for it as target, by performing additional masked language modeling (MLM) with the target language corpus. However, we argue that, due to the discrepancy from multilingual MLM pretraining, a naive specialization as such can be suboptimal. Specifically, we pose three discrepancies to overcome. Script and linguistic discrepancy of the target language from the related seen languages, hinder a positive transfer, for which we propose to maximize representation similarity, unlike existing approaches maximizing overlaps. In addition, label space for MLM prediction can vary across languages, for which we propose to reinitialize top layers for a more effective adaptation. Experiments over four different language families and three tasks shows that our method improves the task performance of unseen languages with statistical significance, while previous approach fails to.

Script, Language, and Labels: Overcoming Three Discrepancies for Low-Resource Language Specialization

Positional encoding is important for vision transformer (ViT) to capture the spatial structure of the input image. General effectiveness has been proven in ViT. In our work we propose to train ViT to recognize the positional label of patches of the input image, this apparently simple task actually yields a meaningful self-supervisory task. Based on previous work on ViT positional encoding, we propose two positional labels dedicated to 2D images including absolute position and relative position. Our positional labels can be easily plugged into various current ViT variants. It can work in two ways: (a) As an auxiliary training target for vanilla ViT (e.g., ViT-B and Swin-B) for better performance. (b) Combine the self-supervised ViT (e.g., MAE) to provide a more powerful self-supervised signal for semantic feature learning. Experiments demonstrate that with the proposed self-supervised methods, ViT-B and Swin-B gain improvements of 1.20% (top-1 Acc) and 0.74% (top-1 Acc) on ImageNet, respectively, and 6.15% and 1.14% improvement on Mini-ImageNet. The code is publicly available at https://github.com/zhangzhemin/PositionalLabel.

Positional Label for Self-Supervised Vision Transformer

Entity linking (EL) is the task of linking the text segments to the referring entities in the knowledge graph, typically decomposed into mention detection, and entity disambiguation. Compared to traditional methods treating the two tasks separately, recent end-to-end entity linking methods exploit the mutual dependency between mentions and entities to achieve better performance. However, existing end-to-end EL methods have problems utilizing the dependency of mentions and entities in the task. To this end, we propose to model the EL task as a hierarchical decision-making process and design a hierarchical reinforcement learning algorithm to solve the problem. We conduct extensive experiments to show that the proposed method achieves state-of-the-art performance in several EL benchmark datasets.

End-to-end Entity Linking with Hierarchical Reinforcement Learning

 It has been witnessed that masked image modeling (MIM) has shown a huge potential in self-supervised learning in the past year. Benefiting from the universal backbone vision transformer, MIM learns self-supervised visual representations through masking a part of patches of the image while attempting to recover the missing pixels. Most previous works mask patches of the image randomly, which underutilizes the semantic information that is beneficial to visual representation learning. On the other hand, due to the large size of the backbone, most previous works have to spend much time on pre-training. In this paper, we propose Attention-driven Masking and Throwing Strategy (AMT), which could solve both problems above. We first leverage the self-attention mechanism to obtain the semantic information of the image during the training process automatically without using any supervised methods. Masking strategy can be guided by that information to mask areas selectively, which is helpful for representation learning. Moreover, a redundant patch throwing strategy is proposed, which makes learning more efficient. As a plug-and-play module for masked image modeling, AMT improves the linear probing accuracy of MAE by 2.9% ~ 5.9% on CIFAR-10/100, STL-10, Tiny ImageNet, and ImageNet-1K, and obtains an improved performance with respect to fine-tuning accuracy of MAE and SimMIM. Moreover, this design also achieves superior performance on downstream detection and segmentation tasks.

Good helper is around you: Attention-driven Masked Image Modeling

Restless multi-armed bandits (RMABs) are an important model to optimize allocation of limited resources in sequential decision-making settings. Typical RMABs assume the budget --- the number of arms pulled --- to be fixed for each step in the planning horizon. However, for realistic real-world planning, resources are not necessarily limited at each planning step; we may be able to distribute surplus resources in one round to an earlier or later round. In real-world planning settings, this flexibility in budget is often constrained to within a subset of consecutive planning steps, e.g., weekly planning of a monthly budget. In this paper we define a general class of RMABs with flexible budget, which we term F-RMABs, and provide an algorithm to optimally solve for them. We derive a min-max formulation to find optimal policies for F-RMABs and leverage gradient primal-dual algorithms to solve for reward-maximizing policies with flexible budgets. We introduce a scheme to sample expected gradients to apply primal-dual algorithms to the F-RMAB setting and make an otherwise computationally expensive approach tractable. Additionally, we provide heuristics that trade off solution quality for efficiency and present experimental comparisons of different F-RMAB solution approaches.

Flexible Budgets in Restless Bandits: A Primal-Dual Algorithm for Efficient Budget Allocation

Recently there are great efforts on leveraging machine learning and logical reasoning. Many approaches start from a given knowledge base, and then try to utilize the knowledge to help machine learning. In real practice, however, the given knowledge base can often be incomplete or even noisy, and thus, it is crucial to develop the ability of knowledge refinement or enhancement. This paper proposes to enable the Abductive learning (ABL) paradigm to have the ability of knowledge refinement/enhancement. In particular, we focus on the problem that, in contrast to closed-environment tasks where a fixed set of symbols are enough to represent the concepts in the domain, in open-environment tasks new concepts may emerge. Ignoring those new concepts can lead to significant performance decay, whereas it is challenging to identify new concepts and add them to the existing knowledge base with potential conflicts resolved. We propose the ABL$_{nc}$ approach which exploits machine learning in ABL to identify new concepts from data, exploits knowledge graph to match them with entities, and refines existing knowledge base to resolve conflicts. The refined/enhanced knowledge base can then be used in the next loop of ABL and help improve the performance of machine learning. Experiments on three neuro-symbolic learning tasks verified the effectiveness of the proposed approach.

Enabling Knowledge Refinement upon New Concepts in Abductive Learning

Point cloud compression with a higher compression ratio and tiny loss is essential for efficient data transportation. However, previous methods that depend on 3D convolution or frequent multi-head self-attention operations bring huge computations. To address this problem, we propose an octree-based Transformer compression method called OctFormer, which does not rely on the occupancy information of sibling nodes. Our method uses non-overlapped context windows to construct octree node sequences and share the result of a multi-head self-attention operation among a sequence of nodes. Besides, we introduce a locally-enhance module for exploiting the sibling features and a positional encoding generator for enhancing the translation invariance of the octree node sequence. Compared to the previous state-of-the-art works, our method obtains up to 17% Bpp savings compared to the voxel-context-based baseline and saves an overall 99% coding time compared to the attention-based baseline.

OctFormer: Efficient Octree-based Transformer for Point Cloud Compression with Local Enhancement

Recent work for continual relation learning has achieved remarkable progress. However, most existing methods only focus on tackling catastrophic forgetting to improve performance in the existing setup, while continually learning relations in the real-world must overcome many other challenges. One is that the data possibly comes in an online streaming fashion with data distributions gradually changing and without distinct task boundaries. Another is that noisy labels are inevitable in real-world, as relation samples may be contaminated by label inconsistencies or labeled with distant supervision. In this work, therefore, we propose a novel continual relation learning framework that simultaneously addresses both online and noisy relation learning challenges. Our framework contains three key modules: (i) a sample separated online purifying module that divides the online data stream into clean and noisy samples, (ii) a self-supervised online learning module that circumvents inferior training signals caused by noisy data, and (iii) a semi-supervised offline finetuning module that ensures the participation of both clean and noisy samples. Experimental results on FewRel, TACRED and NYT-H with real-world noise demonstrate that our framework greatly outperforms the combinations of the state-of-the-art online continual learning and noisy label learning methods.

Online Noisy Continual Relation Learning

Probably Approximately Correct (i.e., PAC) learning is a core concept of sample complexity theory, and efficient PAC learnability is often seen as a natural counterpart to the class P in classical computational complexity. But while the nascent theory of parameterized complexity has allowed us to push beyond the P-NP "dichotomy" in classical computational complexity and identify the exact boundaries of tractability for numerous problems, there is no analogue in the domain of sample complexity that could push beyond efficient PAC learnability.

As our core contribution, we fill this gap by developing a theory of parameterized PAC learning  which allows us to shed new light on several recent PAC learning results that incorporated elements of parameterized complexity. Within the theory, we identify not one but two notions of fixed-parameter learnability that both form distinct counterparts to the class FPT - the core concept at the center of the parameterized complexity paradigm - and develop the machinery required to exclude fixed-parameter learnability. We then showcase the applications of this theory to identify refined boundaries of tractability for CNF and DNF learning as well as for a range of learning problems on graphs.

A Parameterized Theory of PAC Learning

Knowledge graph embedding (KGE), which maps entities and relations in a knowledge graph into continuous vector spaces, has achieved great success in predicting missing links in knowledge graphs. However, knowledge graphs often contain incomplete triples that are difficult to inductively infer by KGEs. To address this challenge, we resort to analogical inference and propose a novel and general self-supervised framework AnKGE to enhance KGE models with analogical inference capability. We propose an analogical object retriever that retrieves appropriate analogical objects from entity-level, relation-level, and triple-level. And in AnKGE, we train an analogy function for each level of analogical inference with the original element embedding from a well-trained KGE model as input, which outputs the analogical object embedding. In order to combine inductive inference capability from the original KGE model and analogical inference capability enhanced by AnKGE, we interpolate the analogy score with the base model score and introduce the adaptive weights in the score function for prediction. Through extensive experiments on FB15k-237 and WN18RR datasets, we show that AnKGE achieves competitive results on link prediction task and well performs analogical inference. 

Premium content

Self-Emphasizing Network for Continuous Sign Language Recognition

Downloads

Next from AAAI 2023

Script, Language, and Labels: Overcoming Three Discrepancies for Low-Resource Language Specialization

Similar lecture

OPT-GAN: A Broad-Spectrum Global Optimizer for Black-box Problems by Learning Distribution