Cross-modal retrieval has become popular in recent years, particularly with the rise of multimedia. Generally, the information from each modality exhibits distinct representations and semantic information, which makes feature tends to be in separate latent spaces encoded with dual-tower architecture and makes it difficult to establish semantic relationships between modalities, resulting in poor retrieval performance. To address this issue, we propose a novel framework for cross-modal retrieval which consists of a cross-modal mixer, a masked autoencoder for pre-training, and a cross-modal retriever for downstream tasks.In specific, we first adopt cross-modal mixer and mask modeling to fuse the original modality and eliminate redundancy. Then, an encoder-decoder architecture is applied to achieve a fuse-then-separate task in the pre-training phase.We feed masked fused representations into the encoder and reconstruct them with the decoder, ultimately separating the original data of two modalities. In downstream tasks, we use the pre-trained encoder to build the cross-modal retrieval method. Extensive experiments on 2 real-world datasets show that our approach outperforms previous state-of-the-art methods in video-audio matching tasks, improving retrieval accuracy by up to 2 times. Furthermore, we prove our model performance by transferring it to other downstream tasks as a universal model.
相關內容
Large Language Models (LLMs) have shown immense potential in multimodal applications, yet the convergence of textual and musical domains remains relatively unexplored. To address this gap, we present MusiLingo, a novel system for music caption generation and music-related query responses. MusiLingo employs a single projection layer to align music representations from the pre-trained frozen music audio model MERT with the frozen Vicuna-7B language model (an adaption of LLaMA), bridging the gap between music audio and textual contexts. We train it on an extensive music caption dataset and fine-tune it with instructional data. Due to the scarcity of high-quality music Q\&A datasets, we created the Music Instruct (MI) dataset from captions in the MusicCaps datasets, tailored for open-ended music inquiries. Empirical evaluations demonstrate its competitive performance in generating music captions and composing music-related Q&A pairs.
Vision-Language Models (VLMs) such as CLIP are trained on large amounts of image-text pairs, resulting in remarkable generalization across several data distributions. The prohibitively expensive training and data collection/curation costs of these models make them valuable Intellectual Property (IP) for organizations. This motivates a vendor-client paradigm, where a vendor trains a large-scale VLM and grants only input-output access to clients on a pay-per-query basis in a black-box setting. The client aims to minimize inference cost by distilling the VLM to a student model using the limited available task-specific data, and further deploying this student model in the downstream application. While naive distillation largely improves the In-Domain (ID) accuracy of the student, it fails to transfer the superior out-of-distribution (OOD) generalization of the VLM teacher using the limited available labeled images. To mitigate this, we propose Vision-Language to Vision-Align, Distill, Predict (VL2V-ADiP), which first aligns the vision and language modalities of the teacher model with the vision modality of a pre-trained student model, and further distills the aligned VLM embeddings to the student. This maximally retains the pre-trained features of the student, while also incorporating the rich representations of the VLM image encoder and the superior generalization of the text embeddings. The proposed approach achieves state-of-the-art results on the standard Domain Generalization benchmarks in a black-box teacher setting, and also when weights of the VLM are accessible.
This article presents the affordances that Generative Artificial Intelligence can have in disinformation context, one of the major threats to our digitalized society. We present a research framework to generate customized agent-based social networks for disinformation simulations that would enable understanding and evaluation of the phenomena whilst discussing open challenges.
Wireless network emulators are being increasingly used for developing and evaluating new solutions for Next Generation (NextG) wireless networks. However, the reliability of the solutions tested on emulation platforms heavily depends on the precision of the emulation process, model design, and parameter settings. To address, obviate, or minimize the impact of errors of emulation models, in this work, we apply the concept of Digital Twin (DT) to large-scale wireless systems. Specifically, we demonstrate the use of Colosseum, the world's largest wireless network emulator with hardware-in-the-loop, as a DT for NextG experimental wireless research at scale. As proof of concept, we leverage the Channel emulation scenario generator and Sounder Toolchain (CaST) to create the DT of a publicly available over-the-air indoor testbed for sub-6 GHz research, namely, Arena. Then, we validate the Colosseum DT through experimental campaigns on emulated wireless environments, including scenarios concerning cellular networks and jamming of Wi-Fi nodes, on both the real and digital systems. Our experiments show that the DT is able to provide a faithful representation of the real-world setup, obtaining an average similarity of up to 0.986 in throughput and 0.989 in Signal to Interference plus Noise Ratio (SINR).
Plasticity, the ability of a neural network to evolve with new data, is crucial for high-performance and sample-efficient visual reinforcement learning (VRL). Although methods like resetting and regularization can potentially mitigate plasticity loss, the influences of various components within the VRL framework on the agent's plasticity are still poorly understood. In this work, we conduct a systematic empirical exploration focusing on three primary underexplored facets and derive the following insightful conclusions: (1) data augmentation is essential in maintaining plasticity; (2) the critic's plasticity loss serves as the principal bottleneck impeding efficient training; and (3) without timely intervention to recover critic's plasticity in the early stages, its loss becomes catastrophic. These insights suggest a novel strategy to address the high replay ratio (RR) dilemma, where exacerbated plasticity loss hinders the potential improvements of sample efficiency brought by increased reuse frequency. Rather than setting a static RR for the entire training process, we propose Adaptive RR, which dynamically adjusts the RR based on the critic's plasticity level. Extensive evaluations indicate that Adaptive RR not only avoids catastrophic plasticity loss in the early stages but also benefits from more frequent reuse in later phases, resulting in superior sample efficiency.
Integrated sensing and communication (ISAC) has the advantages of efficient spectrum utilization and low hardware cost. It is promising to be implemented in the fifth-generation-advanced (5G-A) and sixth-generation (6G) mobile communication systems, having the potential to be applied in intelligent applications requiring both communication and high-accurate sensing capabilities. As the fundamental technology of ISAC, ISAC signal directly impacts the performance of sensing and communication. This article systematically reviews the literature on ISAC signals from the perspective of mobile communication systems, including ISAC signal design, ISAC signal processing algorithms and ISAC signal optimization. We first review the ISAC signal design based on 5G, 5G-A and 6G mobile communication systems. Then, radar signal processing methods are reviewed for ISAC signals, mainly including the channel information matrix method, spectrum lines estimator method and super resolution method. In terms of signal optimization, we summarize peak-to-average power ratio (PAPR) optimization, interference management, and adaptive signal optimization for ISAC signals. This article may provide the guidelines for the research of ISAC signals in 5G-A and 6G mobile communication systems.
Systems for making determinations on socially-constructed and complex concepts at scale are increasingly being deployed. To make such fuzzy concepts tractable for training and evaluating AI, aligning model outputs, or human-in-the-loop workflows, the prevailing strategy involves developing `constitutions' in the form of rules, policies, or principles. However, high-level rules often fail to capture situational nuances or have differing interpretations, resulting in inconsistent decisions. In this work, we introduce case law grounding (CLG), a hybrid workflow inspired by case law in the legal realm where past judgments on specific cases inform new decisions. Evaluating on two task domains, we find that CLG can improve alignment of decisions (+9.6% and +10.9% accuracy) and consistency ($\Delta\bar{\kappa}$ of +0.263 and +0.433) of human decision-makers, while also providing auditable rationales. We also find similarly substantial alignment improvements for an LLM decision-maker (+25% and +23% accuracy).
Deep neural networks (DNNs) are successful in many computer vision tasks. However, the most accurate DNNs require millions of parameters and operations, making them energy, computation and memory intensive. This impedes the deployment of large DNNs in low-power devices with limited compute resources. Recent research improves DNN models by reducing the memory requirement, energy consumption, and number of operations without significantly decreasing the accuracy. This paper surveys the progress of low-power deep learning and computer vision, specifically in regards to inference, and discusses the methods for compacting and accelerating DNN models. The techniques can be divided into four major categories: (1) parameter quantization and pruning, (2) compressed convolutional filters and matrix factorization, (3) network architecture search, and (4) knowledge distillation. We analyze the accuracy, advantages, disadvantages, and potential solutions to the problems with the techniques in each category. We also discuss new evaluation metrics as a guideline for future research.
Many tasks in natural language processing can be viewed as multi-label classification problems. However, most of the existing models are trained with the standard cross-entropy loss function and use a fixed prediction policy (e.g., a threshold of 0.5) for all the labels, which completely ignores the complexity and dependencies among different labels. In this paper, we propose a meta-learning method to capture these complex label dependencies. More specifically, our method utilizes a meta-learner to jointly learn the training policies and prediction policies for different labels. The training policies are then used to train the classifier with the cross-entropy loss function, and the prediction policies are further implemented for prediction. Experimental results on fine-grained entity typing and text classification demonstrate that our proposed method can obtain more accurate multi-label classification results.
The recent proliferation of knowledge graphs (KGs) coupled with incomplete or partial information, in the form of missing relations (links) between entities, has fueled a lot of research on knowledge base completion (also known as relation prediction). Several recent works suggest that convolutional neural network (CNN) based models generate richer and more expressive feature embeddings and hence also perform well on relation prediction. However, we observe that these KG embeddings treat triples independently and thus fail to cover the complex and hidden information that is inherently implicit in the local neighborhood surrounding a triple. To this effect, our paper proposes a novel attention based feature embedding that captures both entity and relation features in any given entity's neighborhood. Additionally, we also encapsulate relation clusters and multihop relations in our model. Our empirical study offers insights into the efficacy of our attention based model and we show marked performance gains in comparison to state of the art methods on all datasets.
小貼士
登錄享
相關主題
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191