The highly abstract nature of image aesthetics perception (IAP) poses significant challenge for current multimodal large language models (MLLMs). The lack of human-annotated multi-modality aesthetic data further exacerbates this dilemma, resulting in MLLMs falling short of aesthetics perception capabilities. To address the above challenge, we first introduce a comprehensively annotated Aesthetic Multi-Modality Instruction Tuning (AesMMIT) dataset, which serves as the footstone for building multi-modality aesthetics foundation models. Specifically, to align MLLMs with human aesthetics perception, we construct a corpus-rich aesthetic critique database with 21,904 diverse-sourced images and 88K human natural language feedbacks, which are collected via progressive questions, ranging from coarse-grained aesthetic grades to fine-grained aesthetic descriptions. To ensure that MLLMs can handle diverse queries, we further prompt GPT to refine the aesthetic critiques and assemble the large-scale aesthetic instruction tuning dataset, i.e. AesMMIT, which consists of 409K multi-typed instructions to activate stronger aesthetic capabilities. Based on the AesMMIT database, we fine-tune the open-sourced general foundation models, achieving multi-modality Aesthetic Expert models, dubbed AesExpert. Extensive experiments demonstrate that the proposed AesExpert models deliver significantly better aesthetic perception performances than the state-of-the-art MLLMs, including the most advanced GPT-4V and Gemini-Pro-Vision. Source data will be available at https://github.com/yipoh/AesExpert.
Previous deep learning-based event denoising methods mostly suffer from poor interpretability and difficulty in real-time processing due to their complex architecture designs. In this paper, we propose window-based event denoising, which simultaneously deals with a stack of events while existing element-based denoising focuses on one event each time. Besides, we give the theoretical analysis based on probability distributions in both temporal and spatial domains to improve interpretability. In temporal domain, we use timestamp deviations between processing events and central event to judge the temporal correlation and filter out temporal-irrelevant events. In spatial domain, we choose maximum a posteriori (MAP) to discriminate real-world event and noise, and use the learned convolutional sparse coding to optimize the objective function. Based on the theoretical analysis, we build Temporal Window (TW) module and Soft Spatial Feature Embedding (SSFE) module to process temporal and spatial information separately, and construct a novel multi-scale window-based event denoising network, named MSDNet. The high denoising accuracy and fast running speed of our MSDNet enables us to achieve real-time denoising in complex scenes. Extensive experimental results verify the effectiveness and robustness of our MSDNet. Our algorithm can remove event noise effectively and efficiently and improve the performance of downstream tasks.
Accurate medical image segmentation demands the integration of multi-scale information, spanning from local features to global dependencies. However, it is challenging for existing methods to model long-range global information, where convolutional neural networks (CNNs) are constrained by their local receptive fields, and vision transformers (ViTs) suffer from high quadratic complexity of their attention mechanism. Recently, Mamba-based models have gained great attention for their impressive ability in long sequence modeling. Several studies have demonstrated that these models can outperform popular vision models in various tasks, offering higher accuracy, lower memory consumption, and less computational burden. However, existing Mamba-based models are mostly trained from scratch and do not explore the power of pretraining, which has been proven to be quite effective for data-efficient medical image analysis. This paper introduces a novel Mamba-based model, Swin-UMamba, designed specifically for medical image segmentation tasks, leveraging the advantages of ImageNet-based pretraining. Our experimental results reveal the vital role of ImageNet-based training in enhancing the performance of Mamba-based models. Swin-UMamba demonstrates superior performance with a large margin compared to CNNs, ViTs, and latest Mamba-based models. Notably, on AbdomenMRI, Encoscopy, and Microscopy datasets, Swin-UMamba outperforms its closest counterpart U-Mamba by an average score of 3.58%. The code and models of Swin-UMamba are publicly available at: https://github.com/JiarunLiu/Swin-UMamba
Current communication technologies face limitations in terms of theoretical capacity, spectrum availability, and power resources. Pragmatic communication, leveraging terminal intelligence for selective data transmission, offers resource conservation. Existing research lacks universal intention resolution tools, limiting applicability to specific tasks. This paper proposes an image pragmatic communication framework based on a Pragmatic Agent for Communication Efficiency (PACE) using Large Language Models (LLM). In this framework, PACE sequentially performs semantic perception, intention resolution, and intention-oriented coding. To ensure the effective utilization of LLM in communication, a knowledge base is designed to supplement the necessary knowledge, dedicated prompts are introduced to facilitate understanding of pragmatic communication scenarios and task requirements, and a chain of thought is designed to assist in making reasonable trade-offs between transmission efficiency and cost. For experimental validation, this paper constructs an image pragmatic communication dataset along with corresponding evaluation standards. Simulation results indicate that the proposed method outperforms traditional and non-LLM-based pragmatic communication in terms of transmission efficiency.
This paper introduces a novel self-supervised learning framework for enhancing 3D perception in autonomous driving scenes. Specifically, our approach, named NCLR, focuses on 2D-3D neural calibration, a novel pretext task that estimates the rigid transformation aligning camera and LiDAR coordinate systems. First, we propose the learnable transformation alignment to bridge the domain gap between image and point cloud data, converting features into a unified representation space for effective comparison and matching. Second, we identify the overlapping area between the image and point cloud with the fused features. Third, we establish dense 2D-3D correspondences to estimate the rigid transformation. The framework not only learns fine-grained matching from points to pixels but also achieves alignment of the image and point cloud at a holistic level, understanding their relative pose. We demonstrate NCLR's efficacy by applying the pre-trained backbone to downstream tasks, such as LiDAR-based 3D semantic segmentation, object detection, and panoptic segmentation. Comprehensive experiments on various datasets illustrate the superiority of NCLR over existing self-supervised methods. The results confirm that joint learning from different modalities significantly enhances the network's understanding abilities and effectiveness of learned representation. Code will be available at \url{https://github.com/Eaphan/NCLR}.
In this paper, we delve into the nuanced challenge of tailoring the Segment Anything Models (SAMs) for integration with event data, with the overarching objective of attaining robust and universal object segmentation within the event-centric domain. One pivotal issue at the heart of this endeavor is the precise alignment and calibration of embeddings derived from event-centric data such that they harmoniously coincide with those originating from RGB imagery. Capitalizing on the vast repositories of datasets with paired events and RGB images, our proposition is to harness and extrapolate the profound knowledge encapsulated within the pre-trained SAM framework. As a cornerstone to achieving this, we introduce a multi-scale feature distillation methodology. This methodology rigorously optimizes the alignment of token embeddings originating from event data with their RGB image counterparts, thereby preserving and enhancing the robustness of the overall architecture. Considering the distinct significance that token embeddings from intermediate layers hold for higher-level embeddings, our strategy is centered on accurately calibrating the pivotal token embeddings. This targeted calibration is aimed at effectively managing the discrepancies in high-level embeddings originating from both the event and image domains. Extensive experiments on different datasets demonstrate the effectiveness of the proposed distillation method. Code in http://github.com/happychenpipi/EventSAM.
Semantic communication has attracted significant interest recently due to its capability to meet the fast growing demand on user-defined and human-oriented communication services such as holographic communications, eXtended reality (XR), and human-to-machine interactions. Unfortunately, recent study suggests that the traditional Shannon information theory, focusing mainly on delivering semantic-agnostic symbols, will not be sufficient to investigate the semantic-level perceptual quality of the recovered messages at the receiver. In this paper, we study the achievable data rate of semantic communication under the symbol distortion and semantic perception constraints. Motivated by the fact that the semantic information generally involves rich intrinsic knowledge that cannot always be directly observed by the encoder, we consider a semantic information source that can only be indirectly sensed by the encoder. Both encoder and decoder can access to various types of side information that may be closely related to the user's communication preference. We derive the achievable region that characterizes the tradeoff among the data rate, symbol distortion, and semantic perception, which is then theoretically proved to be achievable by a stochastic coding scheme. We derive a closed-form achievable rate for binary semantic information source under any given distortion and perception constraints. We observe that there exists cases that the receiver can directly infer the semantic information source satisfying certain distortion and perception constraints without requiring any data communication from the transmitter. Experimental results based on the image semantic source signal have been presented to verify our theoretical observations.
Device-free wireless sensing has recently attracted significant interest due to its potential to support a wide range of immersive human-machine interactive applications. However, data heterogeneity in wireless signals and data privacy regulation of distributed sensing have been considered as the major challenges that hinder the wide applications of wireless sensing in large area networking systems. Motivated by the observation that signals recorded by wireless receivers are closely related to a set of physical-layer semantic features, in this paper we propose a novel zero-shot wireless sensing solution that allows models constructed in one or a limited number of locations to be directly transferred to other locations without any labeled data. We develop a novel physical-layer semantic-aware network (pSAN) framework to characterize the correlation between physical-layer semantic features and the sensing data distributions across different receivers. We then propose a pSAN-based zero-shot learning solution in which each receiver can obtain a location-specific gesture recognition model by directly aggregating the already constructed models of other receivers. We theoretically prove that models obtained by our proposed solution can approach the optimal model without requiring any local model training. Experimental results once again verify that the accuracy of models derived by our proposed solution matches that of the models trained by the real labeled data based on supervised learning approach.
In coded aperture snapshot spectral imaging (CASSI) systems, a core problem is to recover the 3D hyperspectral image (HSI) from the 2D measurement. Current deep unfolding networks (DUNs) for the HSI reconstruction mainly suffered from three issues. Firstly, in previous DUNs, the DNNs across different stages were unable to share the feature representations learned from different stages, leading to parameter sparsity, which in turn limited their reconstruction potential. Secondly, previous DUNs fail to estimate degradation-related parameters within a unified framework, including the degradation matrix in the data subproblem and the noise level in the prior subproblem. Consequently, either the accuracy of solving the data or the prior subproblem is compromised. Thirdly, exploiting both local and non-local priors for the HSI reconstruction is crucial, and it remains a key issue to be addressed. In this paper, we first transform the DUN into a Recurrent Neural Network (RNN) by sharing parameters across stages, which allows the DNN in each stage could learn feature representation from different stages, enhancing the representativeness of the DUN. Secondly, we incorporate the Degradation Estimation Network into the RNN (DERNN), which simultaneously estimates the degradation matrix and the noise level by residual learning with reference to the sensing matrix. Thirdly, we propose a Local and Non-Local Transformer (LNLT) to effectively exploit both local and non-local priors in HSIs. By integrating the LNLT into the DERNN for solving the prior subproblem, we propose the DERNN-LNLT, which achieves state-of-the-art performance.
Existing industrial anomaly detection (IAD) methods predict anomaly scores for both anomaly detection and localization. However, they struggle to perform a multi-turn dialog and detailed descriptions for anomaly regions, e.g., color, shape, and categories of industrial anomalies. Recently, large multimodal (i.e., vision and language) models (LMMs) have shown eminent perception abilities on multiple vision tasks such as image captioning, visual understanding, visual reasoning, etc., making it a competitive potential choice for more comprehensible anomaly detection. However, the knowledge about anomaly detection is absent in existing general LMMs, while training a specific LMM for anomaly detection requires a tremendous amount of annotated data and massive computation resources. In this paper, we propose a novel large multi-modal model by applying vision experts for industrial anomaly detection (dubbed Myriad), which leads to definite anomaly detection and high-quality anomaly description. Specifically, we adopt MiniGPT-4 as the base LMM and design an Expert Perception module to embed the prior knowledge from vision experts as tokens which are intelligible to Large Language Models (LLMs). To compensate for the errors and confusions of vision experts, we introduce a domain adapter to bridge the visual representation gaps between generic and industrial images. Furthermore, we propose a Vision Expert Instructor, which enables the Q-Former to generate IAD domain vision-language tokens according to vision expert prior. Extensive experiments on MVTec-AD and VisA benchmarks demonstrate that our proposed method not only performs favorably against state-of-the-art methods under the 1-class and few-shot settings, but also provide definite anomaly prediction along with detailed descriptions in IAD domain.