Class distribution shifts are particularly challenging for zero-shot classifiers, which rely on representations learned from training classes but are deployed on new, unseen ones. Common causes for such shifts are changes in attributes associated with classes, such as race or gender in person identification. In this work, we propose and analyze a model that adopts this setting, assuming that the attribute responsible for the shift is unknown during training. To address the challenge of learning data representations robust to such shifts, we introduce a framework based on hierarchical sampling to construct synthetic data environments. Despite key differences between the settings, this framework allows us to formulate class distribution shifts in zero-shot learning as out-of-distribution problems. Consequently, we present an algorithm for learning robust representations, and show that our approach significantly improves generalization to diverse class distributions in both simulations and real-world datasets.
相關內容
Experimentation in practical, end-to-end (E2E) next-generation networks deployments is becoming increasingly prevalent and significant in the realm of modern networking and wireless communications research. The prevalence of fifth-generation technology (5G) testbeds and the emergence of developing networks systems, for the purposes of research and testing, focus on the capabilities and features of analytics, intelligence, and automated management using novel testbed designs and architectures, ranging from simple simulations and setups to complex networking systems; however, with the ever-demanding application requirements for modern and future networks, 5G-and-beyond (denoted as 5G+) testbed experimentation can be useful in assessing the creation of large-scale network infrastructures that are capable of supporting E2E virtualized mobile network services. To this end, this paper presents a functional, modular E2E 5G+ system, complete with the integration of a Radio Access Network (RAN) and handling the connection of User Equipment (UE) in real-world scenarios. As well, this paper assesses and evaluates the effectiveness of emulating full network functionalities and capabilities, including a complete description of user-plane data, from UE registrations to communications sequences, and leads to the presentation of a future outlook in powering new experimentation for 6G and next-generation networks.
A conjecture in algorithmic model theory predicts that the model-checking problem for first-order logic is fixed-parameter tractable on a hereditary graph class if and only if the class is monadically dependent. Originating in model theory, this notion is defined in terms of logic, and encompasses nowhere dense classes, monadically stable classes, and classes of bounded twin-width. Working towards this conjecture, we provide the first two combinatorial characterizations of monadically dependent graph classes. This yields the following dichotomy. On the structure side, we characterize monadic dependence by a Ramsey-theoretic property called flip-breakability. This notion generalizes the notions of uniform quasi-wideness, flip-flatness, and bounded grid rank, which characterize nowhere denseness, monadic stability, and bounded twin-width, respectively, and played a key role in their respective model checking algorithms. Natural restrictions of flip-breakability additionally characterize bounded treewidth and cliquewidth and bounded treedepth and shrubdepth. On the non-structure side, we characterize monadic dependence by explicitly listing few families of forbidden induced subgraphs. This result is analogous to the characterization of nowhere denseness via forbidden subdivided cliques, and allows us to resolve one half of the motivating conjecture: First-order model checking is AW[$*$]-hard on every hereditary graph class that is monadically independent. The result moreover implies that hereditary graph classes which are small, have almost bounded twin-width, or have almost bounded flip-width, are monadically dependent. Lastly, we lift our result to also obtain a combinatorial dichotomy in the more general setting of monadically dependent classes of binary structures.
Vehicle trajectory prediction has increasingly relied on data-driven solutions, but their ability to scale to different data domains and the impact of larger dataset sizes on their generalization remain under-explored. While these questions can be studied by employing multiple datasets, it is challenging due to several discrepancies, \textit{e.g.,} in data formats, map resolution, and semantic annotation types. To address these challenges, we introduce UniTraj, a comprehensive framework that unifies various datasets, models, and evaluation criteria, presenting new opportunities for the vehicle trajectory prediction field. In particular, using UniTraj, we conduct extensive experiments and find that model performance significantly drops when transferred to other datasets. However, enlarging data size and diversity can substantially improve performance, leading to a new state-of-the-art result for the nuScenes dataset. We provide insights into dataset characteristics to explain these findings. The code can be found here: \hyperlink{//github.com/vita-epfl/UniTraj}{//github.com/vita-epfl/UniTraj}.
The scaling laws and extraordinary performance of large foundation models motivate the development and utilization of such large models in biomedicine. However, despite early promising results on some biomedical benchmarks, there are still major challenges that need to be addressed before these models can be used in real-world applications. Frontier models such as GPT-4V still have major competency gaps in multimodal capabilities for biomedical applications. Moreover, pragmatic issues such as access, cost, latency, and compliance make it hard for clinicians to use privately-hosted state-of-the-art large models directly on private patient data. In this paper, we explore training open-source small multimodal models (SMMs) to bridge biomedical competency gaps for unmet clinical needs. To maximize data efficiency, we adopt a modular approach by incorporating state-of-the-art pre-trained models for image and text modalities, and focusing on training a lightweight adapter to ground each modality to the text embedding space. We conduct a comprehensive study of this approach on radiology imaging. For training, we assemble a large dataset with over 1 million image-text pairs. For evaluation, we propose a clinically driven novel approach using GPT-4 and demonstrate its parity with expert evaluation. We also study grounding qualitatively using attention. For best practice, we conduct a systematic ablation study on various choices in data engineering and multimodal training. The resulting LLaVA-Rad (7B) model attains state-of-the-art results on radiology tasks such as report generation and cross-modal retrieval, even outperforming much larger models such as GPT-4V and Med-PaLM M (84B). LLaVA-Rad is fast and can be run on a single V100 GPU in private settings, offering a promising state-of-the-art tool for real-world clinical applications.
Multi-modal emotion recognition has recently gained a lot of attention since it can leverage diverse and complementary relationships over multiple modalities, such as audio, visual, and text. Most state-of-the-art methods for multimodal fusion rely on recurrent networks or conventional attention mechanisms that do not effectively leverage the complementary nature of the modalities. In this paper, we focus on dimensional emotion recognition based on the fusion of facial, vocal, and text modalities extracted from videos. Specifically, we propose a recursive cross-modal attention (RCMA) to effectively capture the complementary relationships across the modalities in a recursive fashion. The proposed model is able to effectively capture the inter-modal relationships by computing the cross-attention weights across the individual modalities and the joint representation of the other two modalities. To further improve the inter-modal relationships, the obtained attended features of the individual modalities are again fed as input to the cross-modal attention to refine the feature representations of the individual modalities. In addition to that, we have used Temporal convolution networks (TCNs) to capture the temporal modeling (intra-modal relationships) of the individual modalities. By deploying the TCNs as well cross-modal attention in a recursive fashion, we are able to effectively capture both intra- and inter-modal relationships across the audio, visual, and text modalities. Experimental results on validation-set videos from the AffWild2 dataset indicate that our proposed fusion model is able to achieve significant improvement over the baseline for the sixth challenge of Affective Behavior Analysis in-the-Wild 2024 (ABAW6) competition.
Network calculus (NC), particularly its min-plus branch, has been extensively utilized to construct service models and compute delay bounds for time-sensitive networks (TSNs). This paper provides a revisit to the fundamental results. In particular, counterexamples to the most basic min-plus service models, which have been proposed for TSNs and used for computing delay bounds, indicate that the packetization effect has often been overlooked. To address, the max-plus branch of NC is also considered in this paper, whose models handle packetized traffic more explicitly. It is found that mapping the min-plus models to the max-plus models may bring in an immediate improvement over delay bounds derived from the min-plus analysis. In addition, an integrated analytical approach that combines models from both the min-plus and the max-plus NC branches is introduced. In this approach, the max-plus $g$-server model is extended and the extended model, called $g^{x}$-server, is used together with the min-plus arrival curve traffic model. By applying the integrated NC approach, service and delay bounds are derived for several settings that are fundamental in TSNs.
Deep learning-based algorithms have seen a massive popularity in different areas of remote sensing image analysis over the past decade. Recently, transformers-based architectures, originally introduced in natural language processing, have pervaded computer vision field where the self-attention mechanism has been utilized as a replacement to the popular convolution operator for capturing long-range dependencies. Inspired by recent advances in computer vision, remote sensing community has also witnessed an increased exploration of vision transformers for a diverse set of tasks. Although a number of surveys have focused on transformers in computer vision in general, to the best of our knowledge we are the first to present a systematic review of recent advances based on transformers in remote sensing. Our survey covers more than 60 recent transformers-based methods for different remote sensing problems in sub-areas of remote sensing: very high-resolution (VHR), hyperspectral (HSI) and synthetic aperture radar (SAR) imagery. We conclude the survey by discussing different challenges and open issues of transformers in remote sensing. Additionally, we intend to frequently update and maintain the latest transformers in remote sensing papers with their respective code at: //github.com/VIROBO-15/Transformer-in-Remote-Sensing
The existence of representative datasets is a prerequisite of many successful artificial intelligence and machine learning models. However, the subsequent application of these models often involves scenarios that are inadequately represented in the data used for training. The reasons for this are manifold and range from time and cost constraints to ethical considerations. As a consequence, the reliable use of these models, especially in safety-critical applications, is a huge challenge. Leveraging additional, already existing sources of knowledge is key to overcome the limitations of purely data-driven approaches, and eventually to increase the generalization capability of these models. Furthermore, predictions that conform with knowledge are crucial for making trustworthy and safe decisions even in underrepresented scenarios. This work provides an overview of existing techniques and methods in the literature that combine data-based models with existing knowledge. The identified approaches are structured according to the categories integration, extraction and conformity. Special attention is given to applications in the field of autonomous driving.
Generative commonsense reasoning which aims to empower machines to generate sentences with the capacity of reasoning over a set of concepts is a critical bottleneck for text generation. Even the state-of-the-art pre-trained language generation models struggle at this task and often produce implausible and anomalous sentences. One reason is that they rarely consider incorporating the knowledge graph which can provide rich relational information among the commonsense concepts. To promote the ability of commonsense reasoning for text generation, we propose a novel knowledge graph augmented pre-trained language generation model KG-BART, which encompasses the complex relations of concepts through the knowledge graph and produces more logical and natural sentences as output. Moreover, KG-BART can leverage the graph attention to aggregate the rich concept semantics that enhances the model generalization on unseen concept sets. Experiments on benchmark CommonGen dataset verify the effectiveness of our proposed approach by comparing with several strong pre-trained language generation models, particularly KG-BART outperforms BART by 5.80, 4.60, in terms of BLEU-3, 4. Moreover, we also show that the generated context by our model can work as background scenarios to benefit downstream commonsense QA tasks.
Deep Learning (DL) is vulnerable to out-of-distribution and adversarial examples resulting in incorrect outputs. To make DL more robust, several posthoc anomaly detection techniques to detect (and discard) these anomalous samples have been proposed in the recent past. This survey tries to provide a structured and comprehensive overview of the research on anomaly detection for DL based applications. We provide a taxonomy for existing techniques based on their underlying assumptions and adopted approaches. We discuss various techniques in each of the categories and provide the relative strengths and weaknesses of the approaches. Our goal in this survey is to provide an easier yet better understanding of the techniques belonging to different categories in which research has been done on this topic. Finally, we highlight the unsolved research challenges while applying anomaly detection techniques in DL systems and present some high-impact future research directions.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191