In this paper, we devise a mechanism for the addition of multi-modal information with an existing pipeline for continuous sign language recognition and translation. In our procedure, we have incorporated optical flow information with RGB images to enrich the features with movement-related information. This work studies the feasibility of such modality inclusion using a cross-modal encoder. The plugin we have used is very lightweight and doesn't need to include a separate feature extractor for the new modality in an end-to-end manner. We have applied the changes in both sign language recognition and translation, improving the result in each case. We have evaluated the performance on the RWTH-PHOENIX-2014 dataset for sign language recognition and the RWTH-PHOENIX-2014T dataset for translation. On the recognition task, our approach reduced the WER by 0.9, and on the translation task, our approach increased most of the BLEU scores by ~0.6 on the test set.
相關內容
《計算機信息》雜志發表高質量的論文，擴大了運籌學和計算的范圍，尋求有關理論、方法、實驗、系統和應用方面的原創研究論文、新穎的調查和教程論文，以及描述新的和有用的軟件工具的論文。官網鏈接： ·
數據集
·
INFORMS
·
Networking
·
Performer
·
Herein, we propose a novel dataset distillation method for constructing small informative datasets that preserve the information of the large original datasets. The development of deep learning models is enabled by the availability of large-scale datasets. Despite unprecedented success, large-scale datasets considerably increase the storage and transmission costs, resulting in a cumbersome model training process. Moreover, using raw data for training raises privacy and copyright concerns. To address these issues, a new task named dataset distillation has been introduced, aiming to synthesize a compact dataset that retains the essential information from the large original dataset. State-of-the-art (SOTA) dataset distillation methods have been proposed by matching gradients or network parameters obtained during training on real and synthetic datasets. The contribution of different network parameters to the distillation process varies, and uniformly treating them leads to degraded distillation performance. Based on this observation, we propose an importance-aware adaptive dataset distillation (IADD) method that can improve distillation performance by automatically assigning importance weights to different network parameters during distillation, thereby synthesizing more robust distilled datasets. IADD demonstrates superior performance over other SOTA dataset distillation methods based on parameter matching on multiple benchmark datasets and outperforms them in terms of cross-architecture generalization. In addition, the analysis of self-adaptive weights demonstrates the effectiveness of IADD. Furthermore, the effectiveness of IADD is validated in a real-world medical application such as COVID-19 detection.
Neural networks are vulnerable to adversarial attacks, i.e., small input perturbations can result in substantially different outputs of a neural network. Safety-critical environments require neural networks that are robust against input perturbations. However, training and formally verifying robust neural networks is challenging. We address this challenge by employing, for the first time, a end-to-end set-based training procedure that trains robust neural networks for formal verification. Our training procedure drastically simplifies the subsequent formal robustness verification of the trained neural network. While previous research has predominantly focused on augmenting neural network training with adversarial attacks, our approach leverages set-based computing to train neural networks with entire sets of perturbed inputs. Moreover, we demonstrate that our set-based training procedure effectively trains robust neural networks, which are easier to verify. In many cases, set-based trained neural networks outperform neural networks trained with state-of-the-art adversarial attacks.
Modern inference in extreme value theory faces numerous complications, such as missing data, hidden covariates or design problems. Some of those complications were exemplified in the EVA 2023 data challenge. The challenge comprises multiple individual problems which cover a variety of univariate and multivariate settings. This note presents the contribution of team genEVA in said competition, with particular focus on a detailed presentation of methodology and inference.
Recent advancements in text-to-image models have significantly enhanced image generation capabilities, yet a notable gap of open-source models persists in bilingual or Chinese language support. To address this need, we present Taiyi-Diffusion-XL, a new Chinese and English bilingual text-to-image model which is developed by extending the capabilities of CLIP and Stable-Diffusion-XL through a process of bilingual continuous pre-training. This approach includes the efficient expansion of vocabulary by integrating the most frequently used Chinese characters into CLIP's tokenizer and embedding layers, coupled with an absolute position encoding expansion. Additionally, we enrich text prompts by large vision-language model, leading to better images captions and possess higher visual quality. These enhancements are subsequently applied to downstream text-to-image models. Our empirical results indicate that the developed CLIP model excels in bilingual image-text retrieval.Furthermore, the bilingual image generation capabilities of Taiyi-Diffusion-XL surpass previous models. This research leads to the development and open-sourcing of the Taiyi-Diffusion-XL model, representing a notable advancement in the field of image generation, particularly for Chinese language applications. This contribution is a step forward in addressing the need for more diverse language support in multimodal research. The model and demonstration are made publicly available at \href{//huggingface.co/IDEA-CCNL/Taiyi-Stable-Diffusion-XL-3.5B/}{this https URL}, fostering further research and collaboration in this domain.
This paper investigates the spectrum sharing between a multiple-input single-output (MISO) secure communication system and a multiple-input multiple-output (MIMO) radar system in the presence of one suspicious eavesdropper. We jointly design the radar waveform and communication beamforming vector at the two systems, such that the interference between the base station (BS) and radar is reduced, and the detrimental radar interference to the communication system is enhanced to jam the eavesdropper, thereby increasing secure information transmission performance. In particular, by considering the imperfect channel state information (CSI) for the user and eavesdropper, we maximize the worst-case secrecy rate at the user, while ensuring the detection performance of radar system. To tackle this challenging problem, we propose a two-layer robust cooperative algorithm based on the S-lemma and semidefinite relaxation techniques. Simulation results demonstrate that the proposed algorithm achieves significant secrecy rate gains over the non-robust scheme. Furthermore, we illustrate the trade-off between secrecy rate and detection probability.
Semantic communication initiates a new direction for future communication. In this paper, we aim to establish a systematic framework of semantic information theory (SIT). First, we propose a semantic communication model and define the synonymous mapping to indicate the critical relationship between semantic information and syntactic information. Based on this core concept, we introduce the measures of semantic information, such as semantic entropy $H_s(\tilde{U})$, up/down semantic mutual information $I^s(\tilde{X};\tilde{Y})$ $(I_s(\tilde{X};\tilde{Y}))$, semantic capacity $C_s=\max_{p(x)}I^s(\tilde{X};\tilde{Y})$, and semantic rate-distortion function $R_s(D)=\min_{p(\hat{x}|x):\mathbb{E}d_s(\tilde{x},\hat{\tilde{x}})\leq D}I_s(\tilde{X};\hat{\tilde{X}})$. Furthermore, we prove three coding theorems of SIT, that is, the semantic source coding theorem, semantic channel coding theorem, and semantic rate-distortion coding theorem. We find that the limits of information theory are extended by using synonymous mapping, that is, $H_s(\tilde{U})\leq H(U)$, $C_s\geq C$ and $R_s(D)\leq R(D)$. All these works composite the basis of semantic information theory. In summary, the theoretic framework proposed in this paper is a natural extension of classic information theory and may reveal great performance potential for future communication.
Hierarchical structures are popular in recent vision transformers, however, they require sophisticated designs and massive datasets to work well. In this paper, we explore the idea of nesting basic local transformers on non-overlapping image blocks and aggregating them in a hierarchical way. We find that the block aggregation function plays a critical role in enabling cross-block non-local information communication. This observation leads us to design a simplified architecture that requires minor code changes upon the original vision transformer. The benefits of the proposed judiciously-selected design are threefold: (1) NesT converges faster and requires much less training data to achieve good generalization on both ImageNet and small datasets like CIFAR; (2) when extending our key ideas to image generation, NesT leads to a strong decoder that is 8$\times$ faster than previous transformer-based generators; and (3) we show that decoupling the feature learning and abstraction processes via this nested hierarchy in our design enables constructing a novel method (named GradCAT) for visually interpreting the learned model. Source code is available //github.com/google-research/nested-transformer.
Images can convey rich semantics and induce various emotions in viewers. Recently, with the rapid advancement of emotional intelligence and the explosive growth of visual data, extensive research efforts have been dedicated to affective image content analysis (AICA). In this survey, we will comprehensively review the development of AICA in the recent two decades, especially focusing on the state-of-the-art methods with respect to three main challenges -- the affective gap, perception subjectivity, and label noise and absence. We begin with an introduction to the key emotion representation models that have been widely employed in AICA and description of available datasets for performing evaluation with quantitative comparison of label noise and dataset bias. We then summarize and compare the representative approaches on (1) emotion feature extraction, including both handcrafted and deep features, (2) learning methods on dominant emotion recognition, personalized emotion prediction, emotion distribution learning, and learning from noisy data or few labels, and (3) AICA based applications. Finally, we discuss some challenges and promising research directions in the future, such as image content and context understanding, group emotion clustering, and viewer-image interaction.
Generative commonsense reasoning which aims to empower machines to generate sentences with the capacity of reasoning over a set of concepts is a critical bottleneck for text generation. Even the state-of-the-art pre-trained language generation models struggle at this task and often produce implausible and anomalous sentences. One reason is that they rarely consider incorporating the knowledge graph which can provide rich relational information among the commonsense concepts. To promote the ability of commonsense reasoning for text generation, we propose a novel knowledge graph augmented pre-trained language generation model KG-BART, which encompasses the complex relations of concepts through the knowledge graph and produces more logical and natural sentences as output. Moreover, KG-BART can leverage the graph attention to aggregate the rich concept semantics that enhances the model generalization on unseen concept sets. Experiments on benchmark CommonGen dataset verify the effectiveness of our proposed approach by comparing with several strong pre-trained language generation models, particularly KG-BART outperforms BART by 5.80, 4.60, in terms of BLEU-3, 4. Moreover, we also show that the generated context by our model can work as background scenarios to benefit downstream commonsense QA tasks.
Transformers have a potential of learning longer-term dependency, but are limited by a fixed-length context in the setting of language modeling. We propose a novel neural architecture Transformer-XL that enables learning dependency beyond a fixed length without disrupting temporal coherence. It consists of a segment-level recurrence mechanism and a novel positional encoding scheme. Our method not only enables capturing longer-term dependency, but also resolves the context fragmentation problem. As a result, Transformer-XL learns dependency that is 80% longer than RNNs and 450% longer than vanilla Transformers, achieves better performance on both short and long sequences, and is up to 1,800+ times faster than vanilla Transformers during evaluation. Notably, we improve the state-of-the-art results of bpc/perplexity to 0.99 on enwiki8, 1.08 on text8, 18.3 on WikiText-103, 21.8 on One Billion Word, and 54.5 on Penn Treebank (without finetuning). When trained only on WikiText-103, Transformer-XL manages to generate reasonably coherent, novel text articles with thousands of tokens. Our code, pretrained models, and hyperparameters are available in both Tensorflow and PyTorch.
小貼士
登錄享
相關主題
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191