We abstract the features (i.e. learned representations) of multi-modal data into 1) uni-modal features, which can be learned from uni-modal training, and 2) paired features, which can only be learned from cross-modal interactions. Multi-modal models are expected to benefit from cross-modal interactions on the basis of ensuring uni-modal feature learning. However, recent supervised multi-modal late-fusion training approaches still suffer from insufficient learning of uni-modal features on each modality. We prove that this phenomenon does hurt the model's generalization ability. To this end, we propose to choose a targeted late-fusion learning method for the given supervised multi-modal task from Uni-Modal Ensemble(UME) and the proposed Uni-Modal Teacher(UMT), according to the distribution of uni-modal and paired features. We demonstrate that, under a simple guiding strategy, we can achieve comparable results to other complex late-fusion or intermediate-fusion methods on various multi-modal datasets, including VGG-Sound, Kinetics-400, UCF101, and ModelNet40.
相關內容
Land-use decision-making processes have a long history of producing globally pervasive systemic equity and sustainability concerns. Quantitative, optimization-based planning approaches, e.g. Multi-Objective Land Allocation (MOLA), seemingly open the possibility to improve objectivity and transparency by explicitly evaluating planning priorities by the type, amount, and location of land uses. Here, we show that optimization-based planning approaches with generic planning criteria generate a series of unstable "flashpoints" whereby tiny changes in planning priorities produce large-scale changes in the amount of land use by type. We give quantitative arguments that the flashpoints we uncover in MOLA models are examples of a more general family of instabilities that occur whenever planning accounts for factors that coordinate use on- and between-sites, regardless of whether these planning factors are formulated explicitly or implicitly. We show that instabilities lead to regions of ambiguity in land-use type that we term "gray areas". By directly mapping gray areas between flashpoints, we show that quantitative methods retain utility by reducing combinatorially large spaces of possible land-use patterns to a small, characteristic set that can engage stakeholders to arrive at more efficient and just outcomes.
Modern large language models (LLMs), such as ChatGPT, exhibit a remarkable capacity for role-playing, enabling them to embody not only human characters but also non-human entities like a Linux terminal. This versatility allows them to simulate complex human-like interactions and behaviors within various contexts, as well as to emulate specific objects or systems. While these capabilities have enhanced user engagement and introduced novel modes of interaction, the influence of role-playing on LLMs' reasoning abilities remains underexplored. In this study, we introduce a strategically designed role-play prompting methodology and assess its performance under the zero-shot setting across twelve diverse reasoning benchmarks, encompassing arithmetic, commonsense reasoning, symbolic reasoning, and more. Leveraging models such as ChatGPT and Llama 2, our empirical results illustrate that role-play prompting consistently surpasses the standard zero-shot approach across most datasets. Notably, accuracy on AQuA rises from 53.5% to 63.8%, and on Last Letter from 23.8% to 84.2%. Beyond enhancing contextual understanding, we posit that role-play prompting serves as an implicit Chain-of-Thought (CoT) trigger, thereby improving the quality of reasoning. By comparing our approach with the Zero-Shot-CoT technique, which prompts the model to "think step by step", we further demonstrate that role-play prompting can generate a more effective CoT. This highlights its potential to augment the reasoning capabilities of LLMs.
Traditionally, peer-to-peer systems have relied on altruism and reciprocity. Although incentive-based models have gained prominence in new-generation peer-to-peer systems, it is essential to recognize the continued importance of cooperative principles in achieving performance, fairness, and correctness. The lack of this acknowledgment has paved the way for selfish peers to gain unfair advantages in these systems. As such, we address the challenge of selfish peers by devising a mechanism to reward sustained cooperation. Instead of relying on global accountability mechanisms, we propose a protocol that naturally aggregates local evaluations of cooperation. Traditional mechanisms are often vulnerable to Sybil and misreporting attacks. However, our approach overcomes these issues by limiting the benefits selfish peers can gain without incurring any cost. The viability of our algorithm is proven with a deployment to 27,259 Internet users and a realistic simulation of a blockchain gossip protocol. We show that our protocol sustains cooperation even in the presence of a majority of selfish peers while incurring only negligible overhead.
Rank-order coding, a form of temporal coding, has emerged as a promising scheme to explain the rapid ability of the mammalian brain. Owing to its speed as well as efficiency, rank-order coding is increasingly gaining interest in diverse research areas beyond neuroscience. However, much uncertainty still exists about the performance of rank-order coding under noise. Herein we show what information rates are fundamentally possible and what trade-offs are at stake. An unexpected finding in this paper is the emergence of a special class of errors that, in a regime, increase with less noise.
It is common to model a deterministic response function, such as the output of a computer experiment, as a Gaussian process with a Mat\'ern covariance kernel. The smoothness parameter of a Mat\'ern kernel determines many important properties of the model in the large data limit, including the rate of convergence of the conditional mean to the response function. We prove that the maximum likelihood estimate of the smoothness parameter cannot asymptotically undersmooth the truth when the data are obtained on a fixed bounded subset of $\mathbb{R}^d$. That is, if the data-generating response function has Sobolev smoothness $\nu_0 > d/2$, then the smoothness parameter estimate cannot be asymptotically less than $\nu_0$. The lower bound is sharp. Additionally, we show that maximum likelihood estimation recovers the true smoothness for a class of compactly supported self-similar functions. For cross-validation we prove an asymptotic lower bound $\nu_0 - d/2$, which however is unlikely to be sharp. The results are based on approximation theory in Sobolev spaces and some general theorems that restrict the set of values that the parameter estimators can take.
Free text comments (FTC) in patient-reported outcome measures (PROMs) data are typically analysed using manual methods, such as content analysis, which is labour-intensive and time-consuming. Machine learning analysis methods are largely unsupervised, necessitating post-analysis interpretation. Weakly supervised text classification (WSTC) can be a valuable method of analysis to classify domain-specific text data in which there is limited labelled data. In this paper, we apply five WSTC techniques to FTC in PROMs data to identify health-related quality of life (HRQoL) themes reported by colorectal cancer patients. The WSTC methods label all the themes mentioned in the FTC. The results showed moderate performance on the PROMs data, mainly due to the precision of the models, and variation between themes. Evaluation of the classification performance illustrated the potential and limitations of keyword based WSTC to label PROMs FTC when labelled data is limited.
Event-based motion deblurring has shown promising results by exploiting low-latency events. However, current approaches are limited in their practical usage, as they assume the same spatial resolution of inputs and specific blurriness distributions. This work addresses these limitations and aims to generalize the performance of event-based deblurring in real-world scenarios. We propose a scale-aware network that allows flexible input spatial scales and enables learning from different temporal scales of motion blur. A two-stage self-supervised learning scheme is then developed to fit real-world data distribution. By utilizing the relativity of blurriness, our approach efficiently ensures the restored brightness and structure of latent images and further generalizes deblurring performance to handle varying spatial and temporal scales of motion blur in a self-distillation manner. Our method is extensively evaluated, demonstrating remarkable performance, and we also introduce a real-world dataset consisting of multi-scale blurry frames and events to facilitate research in event-based deblurring.
Multi-object tracking (MOT) at low frame rates can reduce computational, storage and power overhead to better meet the constraints of edge devices. Many existing MOT methods suffer from significant performance degradation in low-frame-rate videos due to significant location and appearance changes between adjacent frames. To this end, we propose to explore collaborative tracking learning (ColTrack) for frame-rate-insensitive MOT in a query-based end-to-end manner. Multiple historical queries of the same target jointly track it with richer temporal descriptions. Meanwhile, we insert an information refinement module between every two temporal blocking decoders to better fuse temporal clues and refine features. Moreover, a tracking object consistency loss is proposed to guide the interaction between historical queries. Extensive experimental results demonstrate that in high-frame-rate videos, ColTrack obtains higher performance than state-of-the-art methods on large-scale datasets Dancetrack and BDD100K, and outperforms the existing end-to-end methods on MOT17. More importantly, ColTrack has a significant advantage over state-of-the-art methods in low-frame-rate videos, which allows it to obtain faster processing speeds by reducing frame-rate requirements while maintaining higher performance. Code will be released at //github.com/yolomax/ColTrack
Knowledge graph embedding, which aims to represent entities and relations as low dimensional vectors (or matrices, tensors, etc.), has been shown to be a powerful technique for predicting missing links in knowledge graphs. Existing knowledge graph embedding models mainly focus on modeling relation patterns such as symmetry/antisymmetry, inversion, and composition. However, many existing approaches fail to model semantic hierarchies, which are common in real-world applications. To address this challenge, we propose a novel knowledge graph embedding model---namely, Hierarchy-Aware Knowledge Graph Embedding (HAKE)---which maps entities into the polar coordinate system. HAKE is inspired by the fact that concentric circles in the polar coordinate system can naturally reflect the hierarchy. Specifically, the radial coordinate aims to model entities at different levels of the hierarchy, and entities with smaller radii are expected to be at higher levels; the angular coordinate aims to distinguish entities at the same level of the hierarchy, and these entities are expected to have roughly the same radii but different angles. Experiments demonstrate that HAKE can effectively model the semantic hierarchies in knowledge graphs, and significantly outperforms existing state-of-the-art methods on benchmark datasets for the link prediction task.
The problem of Multiple Object Tracking (MOT) consists in following the trajectory of different objects in a sequence, usually a video. In recent years, with the rise of Deep Learning, the algorithms that provide a solution to this problem have benefited from the representational power of deep models. This paper provides a comprehensive survey on works that employ Deep Learning models to solve the task of MOT on single-camera videos. Four main steps in MOT algorithms are identified, and an in-depth review of how Deep Learning was employed in each one of these stages is presented. A complete experimental comparison of the presented works on the three MOTChallenge datasets is also provided, identifying a number of similarities among the top-performing methods and presenting some possible future research directions.
小貼士
登錄享
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191