Large multi-modal models (LMMs) hold the potential to usher in a new era of automated visual assistance for people who are blind or low vision (BLV). Yet, these models have not been systematically evaluated on data captured by BLV users. We address this by empirically assessing CLIP, a widely-used LMM likely to underpin many assistive technologies. Testing 25 CLIP variants in a zero-shot classification task, we find that their accuracy is 15 percentage points lower on average for images captured by BLV users than web-crawled images. This disparity stems from CLIP's sensitivities to 1) image content (e.g. not recognizing disability objects as well as other objects); 2) image quality (e.g. not being robust to lighting variation); and 3) text content (e.g. not recognizing objects described by tactile adjectives as well as visual ones). We delve deeper with a textual analysis of three common pre-training datasets: LAION-400M, LAION-2B and DataComp-1B, showing that disability content is rarely mentioned. We then provide three examples that illustrate how the performance disparities extend to three downstream models underpinned by CLIP: OWL-ViT, CLIPSeg and DALL-E2. We find that few-shot learning with as few as 5 images can mitigate CLIP's quality-of-service disparities for BLV users in some scenarios, which we discuss alongside a set of other possible mitigations.
相關內容
The rapid advancement in artificial intelligence (AI), particularly through deep neural networks, has catalyzed significant progress in fields such as vision and text processing. Nonetheless, the pursuit of AI systems that exhibit human-like reasoning and interpretability continues to pose a substantial challenge. The Neural-Symbolic paradigm, which integrates the deep learning prowess of neural networks with the reasoning capabilities of symbolic systems, presents a promising pathway toward developing more transparent and comprehensible AI systems. Within this paradigm, the Knowledge Graph (KG) emerges as a crucial element, offering a structured and dynamic method for representing knowledge through interconnected entities and relationships, predominantly utilizing the triple (subject, predicate, object). This paper explores recent advancements in neural-symbolic integration based on KG, elucidating how KG underpins this integration across three key categories: enhancing the reasoning and interpretability of neural networks through the incorporation of symbolic knowledge (Symbol for Neural), refining the completeness and accuracy of symbolic systems via neural network methodologies (Neural for Symbol), and facilitating their combined application in Hybrid Neural-Symbolic Integration. It highlights current trends and proposes directions for future research in the domain of Neural-Symbolic AI.
The unique solvability and error analysis of the original Lagrange multiplier approach proposed in [8] for gradient flows is studied in this paper. We identify a necessary and sufficient condition that must be satisfied for the nonlinear algebraic equation arising from the original Lagrange multiplier approach to admit a unique solution in the neighborhood of its exact solution, and propose a modified Lagrange multiplier approach so that the computation can continue even if the aforementioned condition is not satisfied. Using Cahn-Hilliard equation as an example, we prove rigorously the unique solvability and establish optimal error estimates of a second-order Lagrange multiplier scheme assuming this condition and that the time step is sufficient small. We also present numerical results to demonstrate that the modified Lagrange multiplier approach is much more robust and can use much larger time step than the original Lagrange multiplier approach.
The evaluation of text-generative vision-language models is a challenging yet crucial endeavor. By addressing the limitations of existing Visual Question Answering (VQA) benchmarks and proposing innovative evaluation methodologies, our research seeks to advance our understanding of these models' capabilities. We propose a novel VQA benchmark based on well-known visual classification datasets which allows a granular evaluation of text-generative vision-language models and their comparison with discriminative vision-language models. To improve the assessment of coarse answers on fine-grained classification tasks, we suggest using the semantic hierarchy of the label space to ask automatically generated follow-up questions about the ground-truth category. Finally, we compare traditional NLP and LLM-based metrics for the problem of evaluating model predictions given ground-truth answers. We perform a human evaluation study upon which we base our decision on the final metric. We apply our benchmark to a suite of vision-language models and show a detailed comparison of their abilities on object, action, and attribute classification. Our contributions aim to lay the foundation for more precise and meaningful assessments, facilitating targeted progress in the exciting field of vision-language modeling.
The escalating complexity of micro-services architecture in cloud-native technologies poses significant challenges for maintaining system stability and efficiency. To conduct root cause analysis (RCA) and resolution of alert events, we propose a pioneering framework, multi-Agent Blockchain-inspired Collaboration for root cause analysis in micro-services architecture (mABC), to revolutionize the AI for IT operations (AIOps) domain, where multiple agents based on the powerful large language models (LLMs) perform blockchain-inspired voting to reach a final agreement following a standardized process for processing tasks and queries provided by Agent Workflow. Specifically, seven specialized agents derived from Agent Workflow each provide valuable insights towards root cause analysis based on their expertise and the intrinsic software knowledge of LLMs collaborating within a decentralized chain. To avoid potential instability issues in LLMs and fully leverage the transparent and egalitarian advantages inherent in a decentralized structure, mABC adopts a decision-making process inspired by blockchain governance principles while considering the contribution index and expertise index of each agent. Experimental results on the public benchmark AIOps challenge dataset and our created train-ticket dataset demonstrate superior performance in accurately identifying root causes and formulating effective solutions, compared to previous strong baselines. The ablation study further highlights the significance of each component within mABC, with Agent Workflow, multi-agent, and blockchain-inspired voting being crucial for achieving optimal performance. mABC offers a comprehensive automated root cause analysis and resolution in micro-services architecture and achieves a significant improvement in the AIOps domain compared to existing baselines
The emerging behaviors of swarms have fascinated scientists and gathered significant interest in the field of robotics. Traditionally, swarms are viewed as egalitarian, with robots sharing identical roles and capabilities. However, recent findings highlight the importance of hierarchy for deploying robot swarms more effectively in diverse scenarios. Despite nature's preference for hierarchies, the robotics field has clung to the egalitarian model, partly due to a lack of empirical evidence for the conditions favoring hierarchies. Our research demonstrates that while egalitarian swarms excel in environments proportionate to their collective sensing abilities, they struggle in larger or more complex settings. Hierarchical swarms, conversely, extend their sensing reach efficiently, proving successful in larger, more unstructured environments with fewer resources. We validated these concepts through simulations and physical robot experiments, using a complex radiation cleanup task. This study paves the way for developing adaptable, hierarchical swarm systems applicable in areas like planetary exploration and autonomous vehicles. Moreover, these insights could deepen our understanding of hierarchical structures in biological organisms.
The complex challenge of detecting sarcasm in Arabic speech on social media is increased by the language diversity and the nature of sarcastic expressions. There is a significant gap in the capability of existing models to effectively interpret sarcasm in Arabic, which mandates the necessity for more sophisticated and precise detection methods. In this paper, we investigate the impact of a fundamental preprocessing component on sarcasm speech detection. While emojis play a crucial role in mitigating the absence effect of body language and facial expressions in modern communication, their impact on automated text analysis, particularly in sarcasm detection, remains underexplored. We investigate the impact of emoji exclusion from datasets on the performance of sarcasm detection models in social media content for Arabic as a vocabulary-super rich language. This investigation includes the adaptation and enhancement of AraBERT pre-training models, specifically by excluding emojis, to improve sarcasm detection capabilities. We use AraBERT pre-training to refine the specified models, demonstrating that the removal of emojis can significantly boost the accuracy of sarcasm detection. This approach facilitates a more refined interpretation of language, eliminating the potential confusion introduced by non-textual elements. The evaluated AraBERT models, through the focused strategy of emoji removal, adeptly navigate the complexities of Arabic sarcasm. This study establishes new benchmarks in Arabic natural language processing and presents valuable insights for social media platforms.
With the recent success of generative models in image and text, the evaluation of generative models has gained a lot of attention. Whereas most generative models are compared in terms of scalar values such as Frechet Inception Distance (FID) or Inception Score (IS), in the last years (Sajjadi et al., 2018) proposed a definition of precision-recall curve to characterize the closeness of two distributions. Since then, various approaches to precision and recall have seen the light (Kynkaanniemi et al., 2019; Naeem et al., 2020; Park & Kim, 2023). They center their attention on the extreme values of precision and recall, but apart from this fact, their ties are elusive. In this paper, we unify most of these approaches under the same umbrella, relying on the work of (Simon et al., 2019). Doing so, we were able not only to recover entire curves, but also to expose the sources of the accounted pitfalls of the concerned metrics. We also provide consistency results that go well beyond the ones presented in the corresponding literature. Last, we study the different behaviors of the curves obtained experimentally.
In large-scale systems there are fundamental challenges when centralised techniques are used for task allocation. The number of interactions is limited by resource constraints such as on computation, storage, and network communication. We can increase scalability by implementing the system as a distributed task-allocation system, sharing tasks across many agents. However, this also increases the resource cost of communications and synchronisation, and is difficult to scale. In this paper we present four algorithms to solve these problems. The combination of these algorithms enable each agent to improve their task allocation strategy through reinforcement learning, while changing how much they explore the system in response to how optimal they believe their current strategy is, given their past experience. We focus on distributed agent systems where the agents' behaviours are constrained by resource usage limits, limiting agents to local rather than system-wide knowledge. We evaluate these algorithms in a simulated environment where agents are given a task composed of multiple subtasks that must be allocated to other agents with differing capabilities, to then carry out those tasks. We also simulate real-life system effects such as networking instability. Our solution is shown to solve the task allocation problem to 6.7% of the theoretical optimal within the system configurations considered. It provides 5x better performance recovery over no-knowledge retention approaches when system connectivity is impacted, and is tested against systems up to 100 agents with less than a 9% impact on the algorithms' performance.
Deep Learning (DL) is the most widely used tool in the contemporary field of computer vision. Its ability to accurately solve complex problems is employed in vision research to learn deep neural models for a variety of tasks, including security critical applications. However, it is now known that DL is vulnerable to adversarial attacks that can manipulate its predictions by introducing visually imperceptible perturbations in images and videos. Since the discovery of this phenomenon in 2013~[1], it has attracted significant attention of researchers from multiple sub-fields of machine intelligence. In [2], we reviewed the contributions made by the computer vision community in adversarial attacks on deep learning (and their defenses) until the advent of year 2018. Many of those contributions have inspired new directions in this area, which has matured significantly since witnessing the first generation methods. Hence, as a legacy sequel of [2], this literature review focuses on the advances in this area since 2018. To ensure authenticity, we mainly consider peer-reviewed contributions published in the prestigious sources of computer vision and machine learning research. Besides a comprehensive literature review, the article also provides concise definitions of technical terminologies for non-experts in this domain. Finally, this article discusses challenges and future outlook of this direction based on the literature reviewed herein and [2].
Nowadays, the Convolutional Neural Networks (CNNs) have achieved impressive performance on many computer vision related tasks, such as object detection, image recognition, image retrieval, etc. These achievements benefit from the CNNs outstanding capability to learn the input features with deep layers of neuron structures and iterative training process. However, these learned features are hard to identify and interpret from a human vision perspective, causing a lack of understanding of the CNNs internal working mechanism. To improve the CNN interpretability, the CNN visualization is well utilized as a qualitative analysis method, which translates the internal features into visually perceptible patterns. And many CNN visualization works have been proposed in the literature to interpret the CNN in perspectives of network structure, operation, and semantic concept. In this paper, we expect to provide a comprehensive survey of several representative CNN visualization methods, including Activation Maximization, Network Inversion, Deconvolutional Neural Networks (DeconvNet), and Network Dissection based visualization. These methods are presented in terms of motivations, algorithms, and experiment results. Based on these visualization methods, we also discuss their practical applications to demonstrate the significance of the CNN interpretability in areas of network design, optimization, security enhancement, etc.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191