Most works of interpretable neural networks strive for learning the semantics concepts merely from single modal information such as images. However, humans usually learn semantic concepts from multiple modalities and the semantics is encoded by the brain from fused multi-modal information. Inspired by cognitive science and vision-language learning, we propose a Prototype-Concept Alignment Network (ProCoNet) for learning visual prototypes under the guidance of textual concepts. In the ProCoNet, we have designed a visual encoder to decompose the input image into regional features of prototypes, while also developing a prompt generation strategy that incorporates in-context learning to prompt large language models to generate textual concepts. To align visual prototypes with textual concepts, we leverage the multimodal space provided by the pre-trained CLIP as a bridge. Specifically, the regional features from the vision space and the cropped regions of prototypes encoded by CLIP reside on different but semantically highly correlated manifolds, i.e. follow a multi-manifold distribution. We transform the multi-manifold distribution alignment problem into optimizing the projection matrix by Cayley transform on the Stiefel manifold. Through the learned projection matrix, visual prototypes can be projected into the multimodal space to align with semantically similar textual concept features encoded by CLIP. We conducted two case studies on the CUB-200-2011 and Oxford Flower dataset. Our experiments show that the ProCoNet provides higher accuracy and better interpretability compared to the single-modality interpretable model. Furthermore, ProCoNet offers a level of interpretability not previously available in other interpretable methods.
论文检索
输入标题、作者或关键词，从 1,526 篇学术成果中精准定位
This paper introduces a novel approach to Image Quality Assessment (IQA) by presenting a new loss function, Dual-Criterion Quality (DCQ) Loss, which integrates the Mean Squared Error (MSE) framework with a Relative Perception Constraint (RPC). The RPC is comprised of two main components: the Quantitative Discrepancy Constraint (QDC) and the Qualitative Alignment Constraint (QAC). The QDC focuses on capturing the numerical relationships of relative differences by minimizing the mean squared error between the differences in predicted scores among samples within a batch size and the differences in Mean Opinion Scores (MOS). Meanwhile, the QAC aims to capture the ordinal relationships between these differences. This method is designed to closely align with human subjective assessments of image quality, which are frequently quantified using the MOS, and to enhance the interpretability and reliability of IQA. Unlike existing ranking methods that suffer from complex pipelines and the introduction of errors through the generation of pair-wise or ordering data, DCQ Loss provides a more straightforward and efficient approach. Moreover, the loss function outperforms current rank-based IQA methods in terms of convergence, stability, and the ability to emulate human perception of visual quality. The effectiveness of this approach is validated through extensive experiments on various mainstream datasets and IQA network architectures, demonstrating significant performance gains over traditional rank loss approaches and contributing to the ongoing development of IQA.
Artwork analysis is an important and fundamental skill for art appreciation, which could enrich personal aesthetic sensibility and facilitate the critical thinking ability. Understanding artworks is challenging due to its subjective nature, diverse interpretations, and complex visual elements, requiring expertise in art history, cultural background, and aesthetic theory. However, limited by the data collection and model ability, previous works for automatically analyzing artworks mainly focus on classification, retrieval, and other simple tasks, which is far from the goal of AI. To facilitate the research progress, in this paper, we step further to compose comprehensive analysis inspired by the remarkable perception and generation ability of large multimodal models. Specifically, we first propose a task of composing paragraph analysis for artworks, i.e., painting in this paper, only focusing on visual characteristics to formulate more comprehensive understanding of artworks. To support the research on formal analysis, we collect a large dataset PaintingForm, with about 19k painting images and 50k analysis paragraphs. We further introduce a superior large multimodal model for painting analysis composing, dubbed GalleryGPT, which is slightly modified and fine-tuned based on LLaVA architecture leveraging our collected data. We conduct formal analysis generation and zero-shot experiments across several datasets to assess the capacity of our model. The results show remarkable performance improvements comparing with powerful baseline LMMs, demonstrating its superb ability of art analysis and generalization. The codes and model are available at: https://github.com/steven640pixel/GalleryGPT.
Point cloud upsampling is crucial for 3D reconstruction, with recent research significantly benefitting from the advances in deep learning technologies. The majority of existing methods, which focus on a sequence of processes including feature extraction, augmentation, and the reconstruction of coordinates, encounter significant challenges in interpreting the geometric attributes they uncover, particularly with respect to the intricacies of transitioning feature dimensionality. In this paper, we delve deeper into modeling Partial Differential Equations (PDEs) specifically tailored for the inverse heat dissipation process in dense point clouds. Our goal is to detect gradients within the dense point cloud data distribution and refine the accuracy of interpolated points' positions along with their complex geometric nuances through a systematic iterative approximation method. Simultaneously, we adopt multivectors from geometric algebra as the primary tool for representing the geometric characteristics of point clouds, moving beyond the conventional vector space representations. The use of geometric products of multivectors enables us to capture the complex relationships between scalars, vectors, and their components more effectively. This methodology not only offers a robust framework for depicting the geometric features of point clouds but also enhances our modeling capabilities for inverse heat dissipation PDEs. Through both qualitative and quantitative assessments, we demonstrate that our results significantly outperform existing state-of-the-art techniques in terms of widely recognized point cloud evaluation metrics and 3D visual reconstruction fidelity.
By integrating various modules with the Visual Transformer (ViT), we facilitate a interpretation of image processing across each layer and attention head. This method allows us to explore the connections both within and across the layers, enabling a analysis of how images are processed at different layers. Conducting a analysis of the contributions from each layer and attention head, shedding light on the intricate interactions and functionalities within the model's layers. This in-depth exploration not only highlights the visual cues between layers but also examines their capacity to navigate the transition from abstract concepts to tangible objects. It unveils the model's mechanism to building an understanding of images, providing a strategy for adjusting attention heads between layers, thus enabling targeted pruning and enhancement of performance for specific tasks. Our research indicates that achieving a scalable understanding of transformer models is within reach, offering ways for the refinement and enhancement of such models.
For AI systems to be safely and reliably grounded in the real world, they should possess the ability of physical commonsense reasoning. Physical commonsense reasoning is essentially a multisensory task as physical properties of objects are manifested through multiple perception modalities, including both visual and auditory. In this study, we constructed two new benchmarks, called PACS-Reason and PACS-Reason+, for explainable physical audiovisual commonsense reasoning (EPACS), in which each datapoint is accompanied by a golden detailed rationale (intermediate reasoning path) to explain the answer selection. Moreover, we present PAVC-Reasoner, a multimodal large language model (LLM) designed to reason about physical commonsense attributes. The model aligns different modalities with the language modality by integrating three different perceivers for cross-modal pretraining and instruction finetuning at multiple granularities. It utilizes an LLM as a cognitive engine to process multimodal inputs and output convincing intermediate reasoning paths as justification for inferring answers. Numerous experiments have demonstrated the effectiveness and superiority of PAVC-Reasoner as a baseline model for studying EPACS. Most attractively, PAVC-Reasoner is capable of reasoning and obtaining strong interpretable explicit reasoning paths, signifying a significant stride towards real-world physical commonsense reasoning.
Prompt-Guided Image-Adaptive Neural Implicit Lookup Tables for Interpretable Image Enhancement
PDF ↗In this paper, we delve into the concept of interpretable image enhancement, a technique that enhances image quality by adjusting filter parameters with easily understandable names such as "Exposure'' and "Contrast''. Unlike using predefined image editing filters, our framework utilizes learnable filters that acquire interpretable names through training. Our contribution is two-fold. Firstly, we introduce a novel filter architecture called an image-adaptive neural implicit lookup table, which uses a multilayer perceptron to implicitly define the transformation from input feature space to output color space. By incorporating image-adaptive parameters directly into the input features, we achieve highly expressive filters. Secondly, we introduce a prompt guidance loss to assign interpretable names to each filter. We evaluate visual impressions of enhancement results, such as exposure and contrast, using a vision and language model along with guiding prompts. We define a constraint to ensure that each filter affects only the targeted visual impression without influencing other attributes, which allows us to obtain the desired filter effects. Experimental results show that our method outperforms existing predefined filter-based methods, thanks to the filters optimized to predict target results. Our source code is available at https://github.com/satoshi-kosugi/PG-IA-NILUT.
Deep Convolutional Neural Networks (CNNs) have demonstrated excellent performance in various multimedia application scenarios. However, complex models often require significant computational resources and energy costs. Therefore, CNN compression is crucial for addressing deployment challenges of multimedia application on resource constrained edge devices. However, existing CNN channel pruning strategies primarily focus on the "weights" or "activations" of the model, overlooking its "interpretability" information. In this paper, we explore CNN pruning strategies from the perspective of model interpretability. We model the correspondence between channel feature maps and interpretable visual perception based on class saliency maps, aiming to assess the contribution of each channel to the desired output. Additionally, we utilize Discrete Wavelet Transform (DWT) to capture the global features and structure of class saliency maps. Based on this, we propose a Channel Spatial Dependability (CSD) metric, evaluating the importance and contribution of channels in a bidirectional manner to guide model pruning. And we dynamically adjust the pruning rate of each layer based on performance changes, in order to achieve more accurate and efficient adaptive pruning. Our method achieves significant results across a range of different networks and datasets. For instance, we achieved a 51.3% pruning on the ResNet-56 model while maintaining an accuracy of 94.16%, outperforming feature-map or other State-of-the-Art (SOTA).
As the visual interpretations for convolutional neural networks (CNNs), backpropagation attribution methods have been garnering growing attention. Nevertheless, majority of these methods merely concentrate on the ultimate convolutional layer, leading to tiny and concentrated interpretations that fail to adequately clarify the model-central attention. Therefore, we propose a precise attribution method (i.e., Holistic-CAM) for high-definition visual interpretation in the holistic stage of CNNs. Specifically, we first present weighted positive gradients to guarantee the sanity of interpretations in shallow layers and leverage multi-scale fusion to improve the resolution across the holistic stage. Then, we further propose a denoising strategy based on the fundamental scale component to eliminate the faithless attribution derived from fusing larger-scale features. The proposed method is capable of simultaneously rendering fine-grained and faithful interpretations for CNNs from shallow to deep layers. Extensive experimental results demonstrate that Holistic-CAM outperforms state-of-the-art methods on common-used benchmarks, including deletion and insertion, energy-based point game as well as Remove and Debias on ImageNet-1k, it also passes the sanity check easily.
Exploring open-vocabulary video action recognition is a promising venture, which aims to recognize previously unseen actions within any arbitrary set of categories. Existing methods typically adapt pretrained image-text models to the video domain, capitalizing on their inherent strengths in generalization. A common thread among such methods is the augmentation of visual embeddings with temporal information to improve the recognition of seen actions. Yet, they compromise with standard less-informative action descriptions, thus faltering when confronted with novel actions. Drawing inspiration from human cognitive processes, we argue that augmenting text embeddings with human prior knowledge is pivotal for open-vocabulary video action recognition. To realize this, we innovatively blend video models with Large Language Models (LLMs) to devise Action-conditioned Prompts. Specifically, we harness the knowledge in LLMs to produce a set of descriptive sentences that contain distinctive features for identifying given actions. Building upon this foundation, we further introduce a multi-modal action knowledge alignment mechanism to align concepts in video and textual knowledge encapsulated within the prompts. Extensive experiments on various video benchmarks, including zero-shot, few-shot, and base-to-novel generalization settings, demonstrate that our method not only sets new SOTA performance but also possesses excellent interpretability.
Recent work shows that documents from encyclopedias serve as helpful auxiliary information for zero-shot learning. Existing methods align the entire semantics of a document with corresponding images to transfer knowledge. However, they disregard that semantic information is not equivalent between them, resulting in a suboptimal alignment. In this work, we propose a novel network to extract multi-view semantic concepts from documents and images and align the matching rather than entire concepts. Specifically, we propose a semantic decomposition module to generate multi-view semantic embeddings from visual and textual sides, providing the basic concepts for partial alignment. To alleviate the issue of information redundancy among embeddings, we propose the local-to-semantic variance loss to capture distinct local details and multiple semantic diversity loss to enforce orthogonality among embeddings. Subsequently, two losses are introduced to partially align visual-semantic embedding pairs according to their semantic relevance at the view and word-to-patch levels. Consequently, we consistently outperform state-of-the-art methods under two document sources in three standard benchmarks for document-based zero-shot learning. Qualitatively, we show that our model learns the interpretable partial association. Code is available at https://github.com/MorningStarOvO/EmDepart.
In the field of multi-modal learning, model parameters are typically large, necessitating the use of parameter-efficient fine-tuning (PEFT) techniques. These methods have been pivotal in enhancing training efficiency for downstream tasks in almost all situations. However, directly applying PEFT methods struggles to fully address the intricate demands of multi-modal tasks, such as multi-modal sarcasm detection (MSD), which demands the extraction and comparison of cues from different modalities. MSD, particularly when reliant on textual and visual modalities, faces challenges in identifying sarcasm's incongruity. This issue often arises from the lack of intermodality interaction during tuning, resulting in a disconnect between textual and visual information. In this paper, we introduce a novel approach called Bi-directional Adapter (BA), designated as MoBA. This approach is designed to minimize training parameters while enhancing the model's ability to interpret sarcasm across modalities. By facilitating an exchange between textual and visual information through a low-rank representation, our method adeptly captures the nuances of sarcastic expressions with a reduced number of training parameters. Our empirical studies, carried out on two publicly accessible and emerging datasets, demonstrate that our model substantially improves sarcasm detection accuracy. These findings indicate that our approach provides a more reliable and efficient solution to address the complexities of MSD.
Semantic-aware Next-Best-View for Multi-DoFs Mobile System in Search-and-Acquisition based Visual Perception
PDF ↗Efficient visual perception using mobile systems is crucial, particularly in unknown environments such as search and rescue operations, where swift and comprehensive perception of objects of interest is essential. In such real-world applications, objects of interest are often situated in complex settings, making the selection of the 'Next Best' view based solely on maximizing visibility gain suboptimal. We argue that incorporating semantics-providing a higher-level interpretation of perception-can significantly contribute to the selection of viewpoints for various perception tasks. In this study, we formulate a novel information gain that integrates both visibility and semantic gain in a unified form to select the semantic-aware Next-Best-View. We also design an adaptive strategy with termination criterion to facilitate the two-stage search-and-acquisition manoeuvre on multiple objects of interest aided by a multi-degree-of-freedoms (Multi-DoFs) mobile system. To evaluate our approach, we introduce several semantically relevant reconstruction metrics, including perspective directivity and the region of interest (ROI)-to-full reconstruction volume ratio. Simulation experiments demonstrate that our approach outperforms the existing methods by up to 27.46% in the ROI-to-full reconstruction volume ratio and 0.88234 in average perspective directivity. Furthermore, the planned motion trajectory exhibits better perceiving coverage toward the target.
The rapid advancement of generation methods has sparked significant concerns about potential misuse, emphasizing the urgency to detect new types of forgeries in open-world settings. Although pioneering works have explored the classification of open-world deepfakes (OW-DF), they neglect the influence of new forgery techniques, which struggle to handle a greater variety of manipulable objects and increasingly realistic artifacts. To align research with the evolving technologies of forgery, we propose a new task named Open-World Deepfake Interpretation (OW-DFI). This task involves the localization of imperceptible artifacts across diverse manipulated objects and deciphering forgery methods, especially new forgery techniques. To this end, we leverage non-casual semantics from large visual models (LVMs) and eliminate them from the nuanced manipulated artifacts. Our proposed model includes Semantic Intervention Learning (SIL) and Correlation-based Incremental Learning (CIL). SIL enhances the inconsistency of forgery artifacts with refined semantics from LVMs, while CIL combats catastrophic forgetting and semantic overfitting through an inter-forgery inheritance transpose and a targeted semantic intervention. Exploiting LVMs, our proposed method adopts an unconventional strategy that aligns with the semantic direction of LVMs, moving beyond just uncovering limited forgery-related features for deepfake detection. To assess the effectiveness of our approach in discovering new forgeries, we construct an Open-World Deepfake Interpretation (OW-DFI) benchmark and conduct experiments in an incremental form. Comprehensive experiments demonstrate our method's superiority on the OW-DFI benchmark, showcasing outstanding performance in localizing forgeries and decoding new forgery techniques.
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.
Deep learning has proven effective in several areas, including computer vision, natural language processing, and disease prediction, which can support clinicians in making decisions along the clinical pathway. However, in order to successfully integrate these algorithms into clinical practice, it is important that their decision-making processes are transparent, explainable, and interpretable. Firstly, this tutorial will introduce targeted eXplainable Artificial Intelligence (XAI) methods to address the urgent need for explainability of deep learning in healthcare applications. In particular, it focuses on algorithms for raw biosignals without prior feature extraction that enable medical diagnoses, specifically electrocardiograms (ECG) -- stemming from the heart -- and electroencephalograms (EEG) representing the electrical activity of the brain. Secondly, participants are provided with a comprehensive workflow that includes both data processing and an introduction to relevant network architectures. Subsequently, various XAI methods are described and it is shown, how the resulting relevance attributions can be visualized on biosignals. Finally, two compelling real-world use cases are presented that demonstrate the effectiveness of XAI in analyzing ECG and EEG signals for disease prediction and sleep classification, respectively. In summary, the tutorial will provide the skills required for gaining insight into the decision process of deep neural networks processing authentic clinical biosignal data.
Visual concept recognition aims to capture the basic attributes of an image and reason about the relationships among them to determine whether the image satisfies a certain concept, and has been widely used in various tasks such as human action recognition and image risk warning. Most existing works adopt deep neural networks for visual concept recognition, which are black-box and incomprehensible to humans, thus making them unacceptable for sensitive domains such as prohibited event detection and risk early warning etc. To address this issue, we propose to combine large language model (LLM) with explainable symbolic reasoning via curriculum reweighting to increase the interpretability and accuracy of visual concept recognition in this paper. However, realizing this goal is challenging given that i) the performance of symbolic representations are limited by the lack of annotated reasoning symbols and rules for most tasks, and ii) the LLMs may suffer from knowlege hallucination and dynamic open environment. To address these issues, in this paper, we propose CurLLM-Reasoner, a curriculum reasoning method based on symbolic reasoning and large language model for visual concept recognition. Specifically, we propose a novel rule enhancement module with a tool library, which fully leverage the reasoning capability of large language models and can generate human-understandable rules without any annotation. We further propose a curriculum data resampling methodology to help the large language model accurately extract from easy to complex rules at different reasoning stages. Extensive experiments on various datasets demonstrate that CurLLM-Reasoner can achieve the state-of-the-art visual concept recognition results with explainable rules while free of human annotations.
Interpretability of Deep Neural Networks using concept-based models offers a promising way to explain model behavior through human understandable concepts. A parallel line of research focuses on disentangling the data distribution into its underlying generative factors, in turn explaining the data generation process. While both directions have received extensive attention, little work has been done on explaining concepts in terms of generative factors to unify mathematically disentangled representations and human-understandable concepts as an explanation for downstream tasks. In this paper, we propose a novel method CoLiDR - which utilizes a disentangled representation learning setup for learning mutually independent generative factors and subsequently learns to aggregate the said representations into human-understandable concepts using a novel aggregation/decomposition module. Experiments are conducted on datasets with both known and unknown latent generative factors. Our method successfully aggregates disentangled generative factors into concepts while maintaining parity with state-of-the-art concept-based approaches. Quantitative and visual analysis of the learned aggregation procedure demonstrates the advantages of our work compared to commonly used concept-based models over four challenging datasets. Lastly, our work is generalizable to an arbitrary number of concepts and generative factors - making it flexible enough to be suitable for various types of data.
We introduce the Robustness of Hierarchically Organized Time Series (RHiOTS) framework, designed to assess the robustness of hierarchical time series forecasting models and algorithms on real-world datasets. Hierarchical time series, where lower-level forecasts must sum to upper-level ones, are prevalent in various contexts, such as retail sales across countries. Current empirical evaluations of forecasting methods are often limited to a small set of benchmark datasets, offering a narrow view of algorithm behavior. RHiOTS addresses this gap by systematically altering existing datasets and modifying the characteristics of individual series and their interrelations. It uses a set of parameterizable transformations to simulate those changes in the data distribution. Additionally, RHiOTS incorporates an innovative visualization component, turning complex, multidimensional robustness evaluation results into intuitive, easily interpretable visuals. This approach allows an in-depth analysis of algorithm and model behavior under diverse conditions. We illustrate the use of RHiOTS by analyzing the predictive performance of several algorithms. Our findings show that traditional statistical methods are more robust than state-of-the-art deep learning algorithms, except when the transformation effect is highly disruptive. Furthermore, we found no significant differences in the robustness of the algorithms when applying specific reconciliation methods, such as MinT. RHiOTS provides researchers with a comprehensive tool for understanding the nuanced behavior of forecasting algorithms, offering a more reliable basis for selecting the most appropriate method for a given problem.