Add to Chrome
Add to Firefox
Add to EdgeWei Yu
Cross-Modal Adapter: Parameter-Efficient Transfer Learning Approach for Vision-Language Models
Apr 19, 2024
Adapter-based parameter-efficient transfer learning has achieved exciting results in vision-language models. Traditional adapter methods often require training or fine-tuning, facing challenges such as insufficient samples or resource limitations. While some methods overcome the need for training by leveraging image modality cache and retrieval, they overlook the text modality's importance and cross-modal cues for the efficient adaptation of parameters in visual-language models. This work introduces a cross-modal parameter-efficient approach named XMAdapter. XMAdapter establishes cache models for both text and image modalities. It then leverages retrieval through visual-language bimodal information to gather clues for inference. By dynamically adjusting the affinity ratio, it achieves cross-modal fusion, decoupling different modal similarities to assess their respective contributions. Additionally, it explores hard samples based on differences in cross-modal affinity and enhances model performance through adaptive adjustment of sample learning intensity. Extensive experimental results on benchmark datasets demonstrate that XMAdapter outperforms previous adapter-based methods significantly regarding accuracy, generalization, and efficiency.
MTGA: Multi-view Temporal Granularity aligned Aggregation for Event-based Lip-reading
Apr 18, 2024Lip-reading is to utilize the visual information of the speaker's lip movements to recognize words and sentences. Existing event-based lip-reading solutions integrate different frame rate branches to learn spatio-temporal features of varying granularities. However, aggregating events into event frames inevitably leads to the loss of fine-grained temporal information within frames. To remedy this drawback, we propose a novel framework termed Multi-view Temporal Granularity aligned Aggregation (MTGA). Specifically, we first present a novel event representation method, namely time-segmented voxel graph list, where the most significant local voxels are temporally connected into a graph list. Then we design a spatio-temporal fusion module based on temporal granularity alignment, where the global spatial features extracted from event frames, together with the local relative spatial and temporal features contained in voxel graph list are effectively aligned and integrated. Finally, we design a temporal aggregation module that incorporates positional encoding, which enables the capture of local absolute spatial and global temporal information. Experiments demonstrate that our method outperforms both the event-based and video-based lip-reading counterparts. Our code will be publicly available.
Transfer Learning with Reconstruction Loss
Apr 12, 2024In most applications of utilizing neural networks for mathematical optimization, a dedicated model is trained for each specific optimization objective. However, in many scenarios, several distinct yet correlated objectives or tasks often need to be optimized on the same set of problem inputs. Instead of independently training a different neural network for each problem separately, it would be more efficient to exploit the correlations between these objectives and to train multiple neural network models with shared model parameters and feature representations. To achieve this, this paper first establishes the concept of common information: the shared knowledge required for solving the correlated tasks, then proposes a novel approach for model training by adding into the model an additional reconstruction stage associated with a new reconstruction loss. This loss is for reconstructing the common information starting from a selected hidden layer in the model. The proposed approach encourages the learned features to be general and transferable, and therefore can be readily used for efficient transfer learning. For numerical simulations, three applications are studied: transfer learning on classifying MNIST handwritten digits, the device-to-device wireless network power allocation, and the multiple-input-single-output network downlink beamforming and localization. Simulation results suggest that the proposed approach is highly efficient in data and model complexity, is resilient to over-fitting, and has competitive performances.
Soft-Prompting with Graph-of-Thought for Multi-modal Representation Learning
Apr 06, 2024The chain-of-thought technique has been received well in multi-modal tasks. It is a step-by-step linear reasoning process that adjusts the length of the chain to improve the performance of generated prompts. However, human thought processes are predominantly non-linear, as they encompass multiple aspects simultaneously and employ dynamic adjustment and updating mechanisms. Therefore, we propose a novel Aggregation-Graph-of-Thought (AGoT) mechanism for soft-prompt tuning in multi-modal representation learning. The proposed AGoT models the human thought process not only as a chain but also models each step as a reasoning aggregation graph to cope with the overlooked multiple aspects of thinking in single-step reasoning. This turns the entire reasoning process into prompt aggregation and prompt flow operations. Experiments show that our multi-modal model enhanced with AGoT soft-prompting achieves good results in several tasks such as text-image retrieval, visual question answering, and image recognition. In addition, we demonstrate that it has good domain generalization performance due to better reasoning.
Theoretical Modeling and Bio-inspired Trajectory Optimization of A Multiple-locomotion Origami Robot
Mar 19, 2024
Recent research on mobile robots has focused on increasing their adaptability to unpredictable and unstructured environments using soft materials and structures. However, the determination of key design parameters and control over these compliant robots are predominantly iterated through experiments, lacking a solid theoretical foundation. To improve their efficiency, this paper aims to provide mathematics modeling over two locomotion, crawling and swimming. Specifically, a dynamic model is first devised to reveal the influence of the contact surfaces' frictional coefficients on displacements in different motion phases. Besides, a swimming kinematics model is provided using coordinate transformation, based on which, we further develop an algorithm that systematically plans human-like swimming gaits, with maximum thrust obtained. The proposed algorithm is highly generalizable and has the potential to be applied in other soft robots with multiple joints. Simulation experiments have been conducted to illustrate the effectiveness of the proposed modeling.
Meta-Learning-Based Fronthaul Compression for Cloud Radio Access Networks
Mar 13, 2024
This paper investigates the fronthaul compression problem in a user-centric cloud radio access network, in which single-antenna users are served by a central processor (CP) cooperatively via a cluster of remote radio heads (RRHs). To satisfy the fronthaul capacity constraint, this paper proposes a transform-compress-forward scheme, which consists of well-designed transformation matrices and uniform quantizers. The transformation matrices perform dimension reduction in the uplink and dimension expansion in the downlink. To reduce the communication overhead for designing the transformation matrices, this paper further proposes a deep learning framework to first learn a suboptimal transformation matrix at each RRH based on the local channel state information (CSI), and then to refine it iteratively. To facilitate the refinement process, we propose an efficient signaling scheme that only requires the transmission of low-dimensional effective CSI and its gradient between the CP and RRH, and further, a meta-learning based gated recurrent unit network to reduce the number of signaling transmission rounds. For the sum-rate maximization problem, simulation results show that the proposed two-stage neural network can perform close to the fully cooperative global CSI based benchmark with significantly reduced communication overhead for both the uplink and the downlink. Moreover, using the first stage alone can already outperform the existing local CSI based benchmark.
Active Sensing for Reciprocal MIMO Channels
Feb 29, 2024
This paper addresses the design of transmit precoder and receive combiner matrices to support $N_{\rm s}$ independent data streams over a time-division duplex (TDD) point-to-point massive multiple-input multiple-output (MIMO) channel with either a fully digital or a hybrid structure. The optimal precoder and combiner design amounts to finding the top-$N_{\rm s}$ singular vectors of the channel matrix, but the explicit estimation of the entire high-dimensional channel would require significant pilot overhead. Alternatively, prior works seek to find the precoding and combining matrices directly by exploiting channel reciprocity and by using the power iteration method, but its performance degrades in the low SNR regime. To tackle this challenging problem, this paper proposes a learning-based active sensing framework, where the transmitter and the receiver send pilots alternately using sensing beamformers that are actively designed as functions of previously received pilots. This is accomplished by using recurrent neural networks to summarize information from the historical observations into hidden state vectors, then using fully connected neural networks to learn the appropriate sensing beamformers in the next pilot stage and finally the transmit precoding and receive combiner matrices for data communications. Simulations demonstrate that the learning-based method outperforms existing approaches significantly and maintains superior performance even in low SNR regimes both in fully digital and hybrid MIMO scenarios.
Dual-Context Aggregation for Universal Image Matting
Feb 28, 2024Natural image matting aims to estimate the alpha matte of the foreground from a given image. Various approaches have been explored to address this problem, such as interactive matting methods that use guidance such as click or trimap, and automatic matting methods tailored to specific objects. However, existing matting methods are designed for specific objects or guidance, neglecting the common requirement of aggregating global and local contexts in image matting. As a result, these methods often encounter challenges in accurately identifying the foreground and generating precise boundaries, which limits their effectiveness in unforeseen scenarios. In this paper, we propose a simple and universal matting framework, named Dual-Context Aggregation Matting (DCAM), which enables robust image matting with arbitrary guidance or without guidance. Specifically, DCAM first adopts a semantic backbone network to extract low-level features and context features from the input image and guidance. Then, we introduce a dual-context aggregation network that incorporates global object aggregators and local appearance aggregators to iteratively refine the extracted context features. By performing both global contour segmentation and local boundary refinement, DCAM exhibits robustness to diverse types of guidance and objects. Finally, we adopt a matting decoder network to fuse the low-level features and the refined context features for alpha matte estimation. Experimental results on five matting datasets demonstrate that the proposed DCAM outperforms state-of-the-art matting methods in both automatic matting and interactive matting tasks, which highlights the strong universality and high performance of DCAM. The source code is available at \url{https://github.com/Windaway/DCAM}.
Hybrid Online-Offline Learning for Task Offloading in Mobile Edge Computing Systems
Feb 27, 2024We consider a multi-user multi-server mobile edge computing (MEC) system, in which users arrive on a network randomly over time and generate computation tasks, which will be computed either locally on their own computing devices or be offloaded to one of the MEC servers. Under such a dynamic network environment, we propose a novel task offloading policy based on hybrid online-offline learning, which can efficiently reduce the overall computation delay and energy consumption only with information available at nearest MEC servers from each user. We provide a practical signaling and learning framework that can train deep neural networks for both online and offline learning and can adjust its offloading policy based on the queuing status of each MEC server and network dynamics. Numerical results demonstrate that the proposed scheme significantly reduces the average computation delay for a broad class of network environments compared to the conventional offloading methods. It is further shown that the proposed hybrid online-offline learning framework can be extended to a general cost function reflecting both delay and energy-dependent metrics.
* accepted by IEEE Transactions on Wireless Communications