Ao Wang

Zixuan Ding, Ao Wang, Hui Chen et al.

Multi-label recognition (MLR) with incomplete labels is very challenging. Recent works strive to explore the image-to-label correspondence in the vision-language model, \ie, CLIP, to compensate for insufficient annotations. In spite of promising performance, they generally overlook the valuable prior about the label-to-label correspondence. In this paper, we advocate remedying the deficiency of label supervision for the MLR with incomplete labels by deriving a structured semantic prior about the label-to-label correspondence via a semantic prior prompter. We then present a novel Semantic Correspondence Prompt Network (SCPNet), which can thoroughly explore the structured semantic prior. A Prior-Enhanced Self-Supervised Learning method is further introduced to enhance the use of the prior. Comprehensive experiments and analyses on several widely used benchmark datasets show that our method significantly outperforms existing methods on all datasets, well demonstrating the effectiveness and the superiority of our method. Our code will be available at https://github.com/jameslahm/SCPNet.

Ao Wang, Wei Li, Xin Wu et al.

Infrared small target detection (ISTD) has attracted widespread attention and been applied in various fields. Due to the small size of infrared targets and the noise interference from complex backgrounds, the performance of ISTD using convolutional neural networks (CNNs) is restricted. Moreover, the constriant that long-distance dependent features can not be encoded by the vanilla CNNs also impairs the robustness of capturing targets' shapes and locations in complex scenarios. To this end, a multi-patch attention network (MPANet) based on the axial-attention encoder and the multi-scale patch branch (MSPB) structure is proposed. Specially, an axial-attention-improved encoder architecture is designed to highlight the effective features of small targets and suppress background noises. Furthermore, the developed MSPB structure fuses the coarse-grained and fine-grained features from different semantic scales. Extensive experiments on the SIRST dataset show the superiority performance and effectiveness of the proposed MPANet compared to the state-of-the-art methods.

Ao Wang, Wenxing Xu, Hanshi Sun et al.

Monitoring electrocardiogram signals is of great significance for the diagnosis of arrhythmias. In recent years, deep learning and convolutional neural networks have been widely used in the classification of cardiac arrhythmias. However, the existing neural network applied to ECG signal detection usually requires a lot of computing resources, which is not friendlyF to resource-constrained equipment, and it is difficult to realize real-time monitoring. In this paper, a binarized convolutional neural network suitable for ECG monitoring is proposed, which is hardware-friendly and more suitable for use in resource-constrained wearable devices. Targeting the MIT-BIH arrhythmia database, the classifier based on this network reached an accuracy of 95.67% in the five-class test. Compared with the proposed baseline full-precision network with an accuracy of 96.45%, it is only 0.78% lower. Importantly, it achieves 12.65 times the computing speedup, 24.8 times the storage compression ratio, and only requires a quarter of the memory overhead.

Ao Wang, Fengyuan Sun, Hui Chen et al.

Multimodal Large Language Models (MLLMs) have recently demonstrated strong performance across a wide range of vision-language tasks, garnering significant attention in the computer vision. However, their efficient deployment remains a substantial challenge due to high computational costs and memory requirements. Recognizing the redundancy of information within the vision modality, recent studies have explored methods for compressing visual tokens in MLLMs to enhance efficiency in a training-free manner. Despite their effectiveness, existing methods like Fast rely on the attention between visual tokens and prompt text tokens as the importance indicator, overlooking the relevance to response text and thus introducing perception bias. In this paper, we demonstrate that in MLLMs, the [CLS] token in the visual encoder inherently knows which visual tokens are important for MLLMs. Building on this prior, we introduce a simple yet effective method for train-free visual token compression, called VTC-CLS. Firstly, it leverages the attention score of the [CLS] token on visual tokens as an importance indicator for pruning visual tokens. Besides, we also explore ensembling the importance scores derived by the [CLS] token from different layers to capture the key visual information more comprehensively. Extensive experiments demonstrate that our VTC-CLS achieves the state-of-the-art performance across various tasks compared with baseline methods. It also brings notably less computational costs in a training-free manner, highlighting its effectiveness and superiority. Code and models are available at \url{https://github.com/THU-MIG/VTC-CLS}.

Ao Wang, Hui Chen, Zijia Lin et al.

Segment Anything Model (SAM) has shown impressive zero-shot transfer performance for various computer vision tasks recently. However, its heavy computation costs remain daunting for practical applications. MobileSAM proposes to replace the heavyweight image encoder in SAM with TinyViT by employing distillation, which results in a significant reduction in computational requirements. However, its deployment on resource-constrained mobile devices still encounters challenges due to the substantial memory and computational overhead caused by self-attention mechanisms. Recently, RepViT achieves the state-of-the-art performance and latency trade-off on mobile devices by incorporating efficient architectural designs of ViTs into CNNs. Here, to achieve real-time segmenting anything on mobile devices, following MobileSAM, we replace the heavyweight image encoder in SAM with RepViT model, ending up with the RepViT-SAM model. Extensive experiments show that RepViT-SAM can enjoy significantly better zero-shot transfer capability than MobileSAM, along with nearly $10\times$ faster inference speed. The code and models are available at \url{https://github.com/THU-MIG/RepViT}.

Linhao Li, Ming Xu, Yongfeng Dong et al.

The abductive natural language inference task ($α$NLI) is proposed to infer the most plausible explanation between the cause and the event. In the $α$NLI task, two observations are given, and the most plausible hypothesis is asked to pick out from the candidates. Existing methods model the relation between each candidate hypothesis separately and penalize the inference network uniformly. In this paper, we argue that it is unnecessary to distinguish the reasoning abilities among correct hypotheses; and similarly, all wrong hypotheses contribute the same when explaining the reasons of the observations. Therefore, we propose to group instead of ranking the hypotheses and design a structural loss called ``joint softmax focal loss'' in this paper. Based on the observation that the hypotheses are generally semantically related, we have designed a novel interactive language model aiming at exploiting the rich interaction among competing hypotheses. We name this new model for $α$NLI: Interactive Model with Structural Loss (IMSL). The experimental results show that our IMSL has achieved the highest performance on the RoBERTa-large pretrained model, with ACC and AUC results increased by about 1\% and 5\% respectively.

Jiangjie Chen, Ao Wang, Haiyun Jiang et al.

A type description is a succinct noun compound which helps human and machines to quickly grasp the informative and distinctive information of an entity. Entities in most knowledge graphs (KGs) still lack such descriptions, thus calling for automatic methods to supplement such information. However, existing generative methods either overlook the grammatical structure or make factual mistakes in generated texts. To solve these problems, we propose a head-modifier template-based method to ensure the readability and data fidelity of generated type descriptions. We also propose a new dataset and two automatic metrics for this task. Experiments show that our method improves substantially compared with baselines and achieves state-of-the-art performance on both datasets.

Jindong Chen, Ao Wang, Jiangjie Chen et al.

Taxonomies play an important role in machine intelligence. However, most well-known taxonomies are in English, and non-English taxonomies, especially Chinese ones, are still very rare. In this paper, we focus on automatic Chinese taxonomy construction and propose an effective generation and verification framework to build a large-scale and high-quality Chinese taxonomy. In the generation module, we extract isA relations from multiple sources of Chinese encyclopedia, which ensures the coverage. To further improve the precision of taxonomy, we apply three heuristic approaches in verification module. As a result, we construct the largest Chinese taxonomy with high precision about 95% called CN-Probase. Our taxonomy has been deployed on Aliyun, with over 82 million API calls in six months.

Ke Ji, Jianbiao Lin, Hui Li et al.

With the rapid development of the multimedia,the secure of the multimedia is get more concerned. as far as we know , Digital watermarking is an effective way to protect copyright. The watermark must be generally hidden does not affect the quality of the original image. In this paper,a novel way based on discrete cosine transform(DCT) and singular value decomposition(SVD) .In the proposed way,we decomposition the image into 8*8 blocks, next we use the DCT to get the transformed block,then we choose the diagonal to embed the information, after we do this, we recover the image and then we decomposition the image to 8*8 blocks,we use the SVD way to get the diagonal matrix and embed the information in the matrix. next we extract the information use both inverse of DCT and SVD, as we all know,after we embed the information seconded time , the information we first information we embed must be changed, we choose a measure way called Peak Signal to Noise Ratio(PSNR) to estimate the similarity of the two image, and set a threshold to ensure whether the information is same or not.