3D object detection plays a pivotal role in autonomous driving and robotics, demanding precise interpretation of Bird's Eye View (BEV) images. The dynamic nature of real-world environments necessitates the use of dynamic query mechanisms in 3D object detection to adaptively capture and process the complex spatio-temporal relationships present in these scenes. However, prior implementations of dynamic queries have often faced difficulties in effectively leveraging these relationships, particularly when it comes to integrating temporal information in a computationally efficient manner. Addressing this limitation, we introduce a framework utilizing dynamic query evolution strategy, harnesses K-means clustering and Top-K attention mechanisms for refined spatio-temporal data processing. By dynamically segmenting the BEV space and prioritizing key features through Top-K attention, our model achieves a real-time, focused analysis of pertinent scene elements. Our extensive evaluation on the nuScenes and Waymo dataset showcases a marked improvement in detection accuracy, setting a new benchmark in the domain of query-based BEV object detection. Our dynamic query evolution strategy has the potential to push the boundaries of current BEV methods with enhanced adaptability and computational efficiency. Project page: https://github.com/Jiawei-Yao0812/QE-BEV
论文检索
输入标题、作者或关键词，从 7,537 篇学术成果中精准定位
Histopathology analysis is the gold standard for medical diagnosis. Accurate classification of whole slide images (WSIs) and region-of-interests (ROIs) localization can assist pathologists in diagnosis. The gigapixel resolution of WSI and the absence of fine-grained annotations make direct classification and analysis challenging. In weakly supervised learning, multiple instance learning (MIL) presents a promising approach for WSI classification. The prevailing strategy is to use attention mechanisms to measure instance importance for classification. However, attention mechanisms fail to capture inter-instance information, and self-attention causes quadratic computational complexity. To address these challenges, we propose AMD-MIL, an agent aggregator with a mask denoise mechanism. The agent token acts as an intermediate variable between the query and key for computing instance importance. Mask and denoising matrices, mapped from agents-aggregated value, dynamically mask low-contribution representations and eliminate noise. AMD-MIL achieves better attention allocation by adjusting feature representations, capturing micro-metastases in cancer, and improving interpretability. Extensive experiments on CAMELYON-16, CAMELYON-17, TCGA-KIDNEY, and TCGA-LUNG show AMD-MIL's superiority over state-of-the-art methods.
Image aesthetics assessment (IAA) primarily examines image quality from a user-centric perspective and can be applied to guide various applications, including image capture, recommendation, and enhancement. The fundamental issue in IAA revolves around the quantification of image aesthetics. Existing methodologies rely on assigning a scalar (or a distribution) to represent aesthetic value based on conventional practices, which confines this scalar within a specific range and artificially labels it. However, conventional methods rarely incorporate research on interpretability, particularly lacking systematic responses to the following three fundamental questions: 1) Can aesthetic qualities be quantified? 2) What is the nature of quantifying aesthetics? 3) How can aesthetics be accurately quantified? In this paper, we present a law called "Special Relativity" of IAA (SR-IAA) that addresses the aforementioned core questions. We have developed a Multi-Attribute IAA Framework (MAINet), which serves as a preliminary validation for SR-IAA within the existing datasets and achieves state-of-the-art (SOTA) performance. Specifically, our metrics on multi-attribute assessment outperform the second-best performance by 8.06% (AADB), 1.67% (PARA), and 2.44% (SPAQ) in terms of SRCC. We anticipate that our research will offer innovative theoretical guidance to the IAA research community. All resources are available here.
Continual Panoptic Perception: Towards Multi-modal Incremental Interpretation of Remote Sensing Images
PDF ↗Continual learning (CL) breaks off the one-way training manner and enables a model to adapt to new data, semantics and tasks continuously. However, current CL methods mainly focus on single tasks. Besides, CL models are plagued by catastrophic forgetting and semantic drift since the lack of old data, which often occurs in remote-sensing interpretation due to the intricate fine-grained semantics. In this paper, we propose Continual Panoptic Perception (CPP), a unified continual learning model that leverages multi-task joint learning covering pixel-level classification, instance-level segmentation and image-level perception for universal interpretation in remote sensing images. Concretely, we propose a collaborative cross-modal encoder (CCE) to extract the input image features, which supports pixel classification and caption generation synchronously. To inherit the knowledge from the old model without exemplar memory, we propose a task-interactive knowledge distillation (TKD) method, which leverages cross-modal optimization and task-asymmetric pseudo-labeling (TPL) to alleviate catastrophic forgetting. Furthermore, we also propose a joint optimization mechanism to achieve end-to-end multi-modal panoptic perception. Experimental results on the fine-grained panoptic perception dataset validate the effectiveness of the proposed model, and also prove that joint optimization can boost sub-task CL efficiency with over 13% relative improvement on panoptic quality. The project page is available at https://github.com/YBIO/CPP.
Zero-shot anomaly detection (ZSAD) methods detect anomalies without prior access to known normal or abnormal samples within target categories. Existing methods typically rely on pretrained multimodal models, computing similarities between manually crafted textual features representing ''normal'' or ''abnormal'' semantics and image patch features to detect anomalies. However, the generic descriptions of ''abnormal'' often fail to precisely match diverse types of anomalies across different object categories. Additionally, computing feature similarities for single patches struggles to pinpoint specific locations of anomalies with various sizes and scales. To address these issues, we propose a novel ZSAD method called FiLo, comprising two components: adaptively learned Fine-Grained Description (FG-Des) and position-enhanced High-Quality Localization (HQ-Loc). FG-Des introduces fine-grained anomaly descriptions for each category using Large Language Models (LLMs) and employs adaptively learned textual templates to enhance the accuracy and interpretability of anomaly detection. HQ-Loc, utilizing Grounding DINO for preliminary localization, position-enhanced text prompts, and Multi-scale Multi-shape Cross-modal Interaction (MMCI) module, facilitates more accurate localization of anomalies of different sizes and shapes. Experimental results on datasets like MVTec and VisA demonstrate that FiLo significantly improves the performance of ZSAD in both detection and localization, achieving state-of-the-art performance with an image-level AUC of 83.9% and a pixel-level AUC of 95.9% on the VisA dataset. Code is available at https://github.com/CASIA-IVA-Lab/FiLo.
Sparse and noisy images (SNIs), like those in spatial gene expression data, pose significant challenges for effective representation learning and clustering, which are essential for thorough data analysis and interpretation. In response to these challenges, we propose Dual Advancement of Representation Learning and Clustering (DARLC), an innovative framework that leverages contrastive learning to enhance the representations derived from masked image modeling. Simultaneously, DARLC integrates cluster assignments in a cohesive, end-to-end approach. This integrated clustering strategy addresses the "class collision problem" inherent in contrastive learning, thus improving the quality of the resulting representations. To generate more plausible positive views for contrastive learning, we employ a graph attention network-based technique that produces denoised images as augmented data. As such, our framework offers a comprehensive approach that improves the learning of representations by enhancing their local perceptibility, distinctiveness, and the understanding of relational semantics. Furthermore, we utilize a Student's t mixture model to achieve more robust and adaptable clustering of SNIs. Extensive experiments, conducted across 12 different types of datasets consisting of SNIs, demonstrate that DARLC surpasses the state-of-the-art methods in both image clustering and generating image representations that accurately capture gene interactions. Code is available at https://github.com/zipging/DARLC.
Multi-view clustering is an important machine learning task for multi-media data, encompassing various domains such as images, videos, and texts. Moreover, with the growing abundance of graph data, the significance of multi-view graph clustering (MVGC) has become evident. Most existing methods focus on graph neural networks (GNNs) to extract information from both graph structure and feature data to learn distinguishable node representations. However, traditional GNNs are designed with the assumption of homophilous graphs, making them unsuitable for widely prevalent heterophilous graphs. Several techniques have been introduced to enhance GNNs for heterophilous graphs. While these methods partially mitigate the heterophilous graph issue, they often neglect the advantages of traditional GNNs, such as their simplicity, interpretability, and efficiency. In this paper, we propose a novel multi-view graph clustering method based on dual-optimized adaptive graph reconstruction, named DOAGC. It mainly aims to reconstruct the graph structure adapted to traditional GNNs to deal with heterophilous graph issues while maintaining the advantages of traditional GNNs. Specifically, we first develop an adaptive graph reconstruction mechanism that accounts for node correlation and original structural information. To further optimize the reconstruction graph, we design a dual optimization strategy and demonstrate the feasibility of our optimization strategy through mutual information theory. Numerous experiments demonstrate that DOAGC effectively mitigates the heterophilous graph problem.
The rapid evolution of egocentric video analysis brings new insights into understanding human activities and intentions from a first-person perspective. Despite this progress, the fragmentation in tasks like action recognition, procedure learning, and moment retrieval, \etc, coupled with inconsistent annotations and isolated model development, hinders a holistic interpretation of video content. In response, we introduce the EAGLE (Egocentric AGgregated Language-video Engine) model and the EAGLE-400K dataset to provide a unified framework that integrates various egocentric video understanding tasks. EAGLE-400K, the first large-scale instruction-tuning dataset tailored for egocentric video, features 400K diverse samples to enhance a broad spectrum task from activity recognition to procedure knowledge learning. Moreover, EAGLE, a strong video multimodal large language model (MLLM), is designed to effectively capture both spatial and temporal information. In addition, we propose a set of evaluation metrics designed to facilitate a thorough assessment of MLLM for egocentric video understanding. Our extensive experiments demonstrate EAGLE's superior performance over existing models, highlighting its ability to balance task-specific understanding with holistic video interpretation. With EAGLE, we aim to pave the way for research opportunities and practical applications in real-world scenarios.
3DQA has gained considerable attention due to its enhanced spatial understanding capabilities compared to image-based VQA. However, existing 3DQA methods have explicitly focused on integrating text and color-coded point cloud features, thereby overlooking the rich high-level semantic relationships among objects. In this paper, we propose a novel graph-based 3DQA method termed 3DGraphQA, which leverages scene graph reasoning to enhance the ability to handle complex reasoning tasks in 3DQA and offers stronger interpretability. Specifically, our method first adaptively constructs dynamic scene graphs for the 3DQA task. Then we inject both the situation and the question inputs into the scene graph, forming the situation-graph and the question-graph, respectively. Based on the constructed graphs, we finally perform intra- and inter-graph feature propagation for efficient graph inference: intra-graph feature propagation is performed based on Graph Transformer in each graph to realize single-modal contextual interaction and high-order contextual interaction; inter-graph feature propagation is performed among graphs based on bilinear graph networks to realize the interaction between different contexts of situations and questions. Drawing on these intra- and inter-graph feature propagation, our approach is poised to better grasp the intricate semantic and spatial relationship issues among objects within the scene and their relations to the questions, thereby facilitating reasoning complex and compositional questions. We validate the effectiveness of our approach on SQA3D and ScanQA datasets, and expand the SQA3D dataset to SQA3D Pro with multi-view information, making it more suitable for our approach. Experimental results demonstrate that our 3DGraphQA outperforms existing methods.
Speech-language multi-modal learning presents a significant challenge due to the fine nuanced information inherent in speech styles. Therefore, a large-scale dataset providing elaborate comprehension of speech style is urgently needed to facilitate insightful interplay between speech audio and natural language. However, constructing such datasets presents a major trade-off between large-scale data collection and high-quality annotation. To tackle this challenge, we propose an automatic speech annotation system for expressiveness interpretation that annotates in-the-wild speech clips with expressive and vivid human language descriptions. Initially, speech audios are processed by a series of expert classifiers and captioning models to capture diverse speech characteristics, followed by a fine-tuned LlaMA for customized annotation generation. Unlike previous tag/templet-based annotation frameworks with limited information and diversity, our system provides in-depth understandings of speech style through tailored natural language descriptions, thereby enabling accurate and voluminous data generation for large model training. With this system, we create SpeechCraft, a fine-grained bilingual expressive speech dataset. It is distinguished by highly descriptive natural language style prompts, containing approximately 2,000 hours of audio data and encompassing over two million speech clips. Extensive experiments demonstrate that the proposed dataset significantly boosts speech-language task performance in stylist speech synthesis and speech style understanding.
Multi-view clustering (MVC) methods based on non-negative matrix factorization (NMF) have gained popularity owing to their ability to provide interpretable clustering results. However, these NMF-based MVC methods generally process each view independently and thus ignore the potential relationship between views. Besides, they are limited in the ability to capture nonlinear data structures. To overcome these weaknesses and inspired by deep learning, we propose a multi-view clustering method based on deep non-negative tensor factorization (MVC-DNTF). With deep tensor factorization, our method can well exploit the spatial structure of the original data and is capable of extracting more deep and nonlinear features embedded in different views. To further extract the complementary information of different views, we adopt the weighted tensor Schatten p-norm regularization term. An optimization algorithm is developed to effectively solve the MVC-DNTF objective. Extensive experiments are performed to demonstrate the effectiveness and superiority of our method.
Image captioning, which generates natural language descriptions of images, is a crucial task in vision-language research. Previous models have typically addressed this task by aligning the generative capabilities of machines with humans through statistical fitting existing datasets. While effective for normal images, they may struggle to accurately describe those where certain parts of the image are obscured or edited, unlike humans who excel in such cases. These weaknesses, including hallucinations and limited interpretability, often hinder performance in scenarios with shifted association patterns. In this paper, we present a generic image captioning framework that employs causal inference to make existing models more capable of interventional tasks, and counterfactually explainable. Our approach includes two variants leveraging either total effect or natural direct effect. Integrating them into the training process enables models to handle counterfactual scenarios, increasing their generalizability. Extensive experiments on various datasets show that our method effectively reduces hallucinations and improves the model's faithfulness to images, demonstrating high portability across both small-scale and large-scale image-to-text models. The code is available at https://github.com/Aman-4-Real/See-or-Guess.
Image captioning evaluation metrics can be divided into two categories, reference-based metrics and reference-free metrics. However, reference-based approaches may struggle to evaluate descriptive captions with abundant visual details produced by advanced multimodal large language models, due to their heavy reliance on limited human-annotated references. In contrast, previous reference-free metrics have been proven effective via CLIP cross-modality similarity. Nonetheless, CLIP-based metrics, constrained by their solution of global image-text compatibility, often have a deficiency in detecting local textual hallucinations and are insensitive to small visual objects. Besides, their single-scale designs are unable to provide an interpretable evaluation process such as pinpointing the position of caption mistakes and identifying visual regions that have not been described. To move forward, we propose a novel reference-free metric for image captioning evaluation, dubbed Hierarchical Image Captioning Evaluation Score (HICE-S). By detecting local visual regions and textual phrases, HICE-S builds an interpretable hierarchical scoring mechanism, breaking through the barriers of the single-scale structure of existing reference-free metrics. Comprehensive experiments indicate that our proposed metric achieves the SOTA performance on several benchmarks, outperforming existing reference-free metrics like CLIP-S and PAC-S, and reference-based metrics like METEOR and CIDEr. Moreover, several case studies reveal that the assessment process of HICE-S on detailed captions closely resembles interpretable human judgments. Our code is available at https://github.com/joeyz0z/HICE.
Understanding a meme is a challenging task, due to the metaphorical information contained in the meme that requires intricate interpretation to grasp its intended meaning fully. In previous works, attempts have been made to facilitate computational understanding of memes through introducing human-annotated metaphors as extra input features into machine learning models. However, these approaches mainly focus on formulating linguistic representation of a metaphor (extracted from the texts appearing in memes), while ignoring the connection between the metaphor and corresponding visual features (e.g., objects in meme images). In this paper, we argue that a more comprehensive understanding of memes can only be achieved through a joint modelling of both visual and linguistic features of memes. To this end, we propose an approach to generate Multimodal Metaphorical feature for Meme Classification, named MMMC. MMMC derives visual characteristics from linguistic attributes of metaphorical concepts, which more effectively convey the underlying metaphorical concept, leveraging a text-conditioned generative adversarial network. The linguistic and visual features are then integrated into a set of multimodal metaphorical features for classification purpose. We perform extensive experiments on a benchmark metaphorical meme dataset, MET-Meme. Experimental results show that MMMC significantly outperforms existing baselines on the task of emotion classification and intention detection. Our code and dataset are available at https://github.com/liaolianfoka/MMMC.
Recent research has offered insights into the extraordinary capabilities of Large Multimodal Models (LMMs) in various general vision and language tasks. There is growing interest in how LMMs perform in more specialized domains. Social media content, inherently multimodal, blends text, images, videos, and sometimes audio. To effectively understand such content, models need to interpret the intricate interactions between these diverse communication modalities and their impact on the conveyed message. Understanding social multimedia content remains a challenging problem for contemporary machine learning frameworks. In this talk, we evaluate GPT-4V(ision)'s capabilities for social multimedia analysis. We select five representative tasks, including sentiment analysis, hate speech detection, fake news identification, demographic inference, and political ideology detection, to evaluate GPT-4V. Our investigation begins with a preliminary quantitative analysis for each task using existing benchmark datasets, followed by a careful review of the results and a selection of qualitative samples that illustrate GPT-4V's potential in understanding multimodal social media content. GPT-4V demonstrates remarkable efficacy in these tasks, showcasing strengths such as joint understanding of image-text pairs, contextual and cultural awareness, and extensive commonsense knowledge. In addition to the known hallucination problem, notable challenges remain as GPT-4V struggles with tasks involving multilingual social multimedia comprehension and has difficulties in generalizing to the latest trends in social media. We further present several attempts to improve the performance on some tasks. The insights gleaned from our findings underscore a promising future for LMMs in enhancing our comprehension of social media content and its users through the analysis of multimodal information.
As technology pervades our lives in an increasingly rich ecosystem of digital devices, those devices can capture huge amounts of long-term personal data. A core theme of my research has been to create systems and interfaces that enable people to harness and control that personal data and its use. To do this, I have designed systems from their very foundations so that they support scrutability [2]. This means that the user should be able to scrutinise the user model that a system builds from their personal data. The term, scrutability highlights a user-centred view of Explainable AI (XAI) [4]. It has a particularly important role in supporting people in lifelong, life-wide learning, especially from long term data [3]. This is because it can support key metacognitive processes of self-monitoring, reflection and planning. In learning contexts, the user model is often called a learner model and the interfaces onto it are called Open Learner Models (OLMs). Increasingly, learning contexts have been able to make use of rich forms of multi-modal data [1]. This talk will share insights from a series of case studies. The first case studies explored how to harness data from wearables, such as smart watches, for personal informatics interfaces. These are designed to enable people learn about themselves over the long term. One case study created interfaces that enable people to take account of wearing adherence, with its implications for interpreting such data [6]. A second shares analysis of a large dataset (over 140,000 people) from a public health initiative [5] and another involves use of Virtual Reality games for exercise [7]. The second set of case studies are from formal education settings. These use diverse forms of data to support individual learners, teams of learners who are learning how to collaborate and teachers who want to understand how their students are progressing. I will share key insights that have emerged for a research agenda: OLMs for life-wide learning; the nature of the different interfaces needed for fast, versus slow and considered thinking; communicating uncertainty; scaffolding people to really learn about themselves from their multimodal data; and how these link to urgent challenges of education in an age of AI, fake news and truth decay.
In recent years, the use of AI/ML technologies in the medical device industry has increased significantly, with a boom in the radiology sector. AI/ML-tech based Software as Medical Devices (SaMD) support healthcare professionals in their clinical routine, saving medical time, decreasing workload while improving image readouts. But more importantly, AI/ML technologies offer the ability to extract valuable and reliable insights from medical images, catching the unseen and paving the way for medical breakthroughs while improving the care pathway for diseases monitored by medical images. A striking example is the use of AI/ML technologies in the management of lung cancer, the world's deadliest cancer. Most lung cancer patients are diagnosed at an advanced stage of the disease, when they cannot be cured anymore. Enabling to accurately identify the malignant vs benign status of a nodule based on CT scan images, AI/ML technologies allow diagnosis of the disease at its earliest onset, when patients can still be cured. Introducing AI in radiology changes lung cancer patients' prognostic and can help save millions of lives globally. Median Technologies develops eyonisTM, a suite of unique end-to-end AI/ML technology-based CADe/CADx SaMD that automatically integrates and optimizes the entire medical imaging interpretation workflow, aiding radiologists and clinicians in the screening, diagnosis at the earliest stage and clinical management of cancer patients. eyonis? most advanced and flagship clinical development program is eyonis? Lung Cancer Screening (LCS) [1][2], a next-generation AI/ML tech-based SaMD providing Computer-Aided Detection (CADe) and Computer-Aided Diagnosis (CADx) [3][4] features for very early lung cancer diagnosis in lung cancer screening procedures [5]. The presentation will detail the evolution of eyonisTM LCS, from initial proof of concept to full SaMD.
Food waste and food insecurity are two problems that co-exist worldwide. A major force to combat food waste and insecurity, food rescue platforms (FRP) match food donations to low-resource communities. Since they rely on external volunteers to deliver the food, communicating rescue task difficulty to volunteers is very important for volunteer engagement and retention. We develop a hybrid model with tabular and natural language data to predict the difficulty of a given rescue trip, which significantly outperforms baselines in identifying easy and hard rescues. Furthermore, using storyboards, we conducted interviews with different stakeholders to understand their perspectives on how to integrate such predictions into volunteers' workflow. Motivated by our findings, we developed three explanation methods to generate interpretable insights for volunteers to better understand the predictions. The results from this study are in the process of being adopted at Food Rescue Hero, a large FRP serving over 25 cities across the United States.
Sketch-based drawing assessments are useful in understanding individuals' cognitive and psychological states, such as cognitive impairment or mental disorders. Hence, these assessments have been developed and applied on a large scale, such as in schools and workplaces, to screen individuals who may require further clinical examination. However, the interpretation of a large number of drawing assessments solely relies on human experts, requiring much time and cost. To address this issue, we introduce a novel scene-level sketch dataset, SceneDAPR, which can be used to automatically analyze the drawing assessment, Draw-A-Person-in-the-Rain (DAPR), a popular psychological drawing assessment used for identifying stressful experiences and coping behavior. The proposed dataset consists of 6,420 objects depicted in 1,399 scene sketches drawn by humans, along with detailed supplementary information about the participants. SceneDAPR includes free-hand drawings from different age groups: children & adolescents, adults, and seniors. Leveraging the proposed SceneDAPR, we develop a web-based drawing assessment system. The extensive experiments demonstrate that our system shows a robust performance across the different age groups in the object detection task as well as a considerable performance compared to human experts. We believe that the proposed new sketch dataset can be used to develop an automatic system for psychological drawing assessments, which can support human experts by reducing the time and cost of analyzing the drawing assessments for a large population. SceneDAPR and experimental code are available at https://github.com/DSAIL-SKKU/SceneDAPR.
In an era dominated by web-based intelligent customer services, the applications of Sentence Pair Matching are profoundly broad. Web agents, for example, automatically respond to customer queries by finding similar past questions, significantly reducing customer service expenses. While current large language models (LLMs) offer powerful text generation capabilities, they often struggle with opacity, potential text toxicity, and difficulty managing domain-specific and confidential business inquiries. Consequently, the widespread adoption of web-based intelligent customer services in real-world business still greatly relies on query-based interactions. In this paper, we introduce a series of model-agnostic techniques aimed at enhancing both the accuracy and interpretability of Chinese pairwise sentence-matching models. Our contributions include (1) An Edit-distance-weighted fine-tuning method, (2) A Bayesian Iterative Prediction algorithm, (3) A Lexical-based Dual Ranking Interpreter, and (4) A Bi-criteria Denoising strategy. Experimental results on the Large-scale Chinese Question Matching Corpus (LCQMC) with a disturbed test demonstrate that our fine-tuning and prediction methods can steadily improve matching accuracy, building on the current state-of-the-art models. Besides, our interpreter with denoising strategy markedly enhances token-level interpretation in rationality and loyalty. In both matching accuracy and interpretation, our approaches outperform classic methods and even LLMs.