Abstract:We present REMM, a rotation-equivariant framework for end-to-end multimodal image matching, which fully encodes rotational differences of descriptors in the whole matching pipeline. Previous learning-based methods mainly focus on extracting modal-invariant descriptors, while consistently ignoring the rotational invariance. In this paper, we demonstrate that our REMM is very useful for multimodal image matching, including multimodal feature learning module and cyclic shift module. We first learn modal-invariant features through the multimodal feature learning module. Then, we design the cyclic shift module to rotationally encode the descriptors, greatly improving the performance of rotation-equivariant matching, which makes them robust to any angle. To validate our method, we establish a comprehensive rotation and scale-matching benchmark for evaluating the anti-rotation performance of multimodal images, which contains a combination of multi-angle and multi-scale transformations from four publicly available datasets. Extensive experiments show that our method outperforms existing methods in benchmarking and generalizes well to independent datasets. Additionally, we conducted an in-depth analysis of the key components of the REMM to validate the improvements brought about by the cyclic shift module. Code and dataset at https://github.com/HanNieWHU/REMM.
Abstract:The paper focuses on improving the interpretability of Grammatical Error Correction (GEC) metrics, which receives little attention in previous studies. To bridge the gap, we propose CLEME2.0, a reference-based evaluation strategy that can describe four elementary dimensions of GEC systems, namely hit-correction, error-correction, under-correction, and over-correction. They collectively contribute to revealing the critical characteristics and locating drawbacks of GEC systems. Evaluating systems by Combining these dimensions leads to high human consistency over other reference-based and reference-less metrics. Extensive experiments on 2 human judgement datasets and 6 reference datasets demonstrate the effectiveness and robustness of our method. All the codes will be released after the peer review.
Abstract:Synthetic data generation has gained significant attention recently for its utility in training large vision and language models. However, the application of synthetic data to the training of multimodal context-augmented generation systems has been relatively unexplored. This gap in existing work is important because existing vision and language models (VLMs) are not trained specifically for context-augmented generation. Resources for adapting such models are therefore crucial for enabling their use in retrieval-augmented generation (RAG) settings, where a retriever is used to gather relevant information that is then subsequently provided to a generative model via context augmentation. To address this challenging problem, we generate SK-VQA: a large synthetic multimodal dataset containing over 2 million question-answer pairs which require external knowledge to determine the final answer. Our dataset is both larger and significantly more diverse than existing resources of its kind, possessing over 11x more unique questions and containing images from a greater variety of sources than previously-proposed datasets. Through extensive experiments, we demonstrate that our synthetic dataset can not only serve as a challenging benchmark, but is also highly effective for adapting existing generative multimodal models for context-augmented generation.
Abstract:Terahertz (THz) cell-free massive multiple-input-multiple-output (mMIMO) networks have been envisioned as a prospective technology for achieving higher system capacity, improved performance, and ultra-high reliability in 6G networks. However, due to severe attenuation and limited scattering in THz transmission, as well as high power consumption for increased number of access points (APs), further improvement of network capacity becomes challenging. Reconfigurable intelligent surface (RIS) has been introduced as a low-cost solution to reduce AP deployment and assist in data transmission. However, due to the ultra-wide bandwidth and frequency-dependent characteristics of RISs, beam split effect has become an unavoidable obstacle. To compensate the severe performance degradation caused by beam split effect, we introduce additional time delay (TD) layers at both access points (APs) and RISs. Accordingly, we propose a joint precoding framework at APs and RISs to fully unleash the potential of the considered network. Specifically, we first formulate the joint precoding as a non-convex optimization problem. Then, given the location of unchanged RISs, we adjust the time delays (TDs) of APs to align the generated beams towards RISs. After that, with knowledge of the optimal TDs of APs, we decouple the optimization problem into three subproblems of optimizing the baseband beamformers, RISs and TDs of RISs, respectively. Exploiting multidimensional complex quadratic transform, we transform the subproblems into convex forms and solve them under alternate optimizing framework. Numerical results verify that the proposed method can effectively mitigate beam split effect and significantly improve the achievable rate compared with conventional cell-free mMIMO networks.
Abstract:Edge detection is a long standing problem in computer vision. Recent deep learning based algorithms achieve state of-the-art performance in publicly available datasets. Despite the efficiency of these algorithms, their performance, however, relies heavily on the pretrained weights of the backbone network on the ImageNet dataset. This limits heavily the design space of deep learning based edge detectors. Whenever we want to devise a new model, we have to train this new model on the ImageNet dataset first, and then fine tune the model using the edge detection datasets. The comparison would be unfair otherwise. However, it is usually not feasible for many researchers to train a model on the ImageNet dataset due to the limited computation resources. In this work, we study the performance that can be achieved by state-of-the-art deep learning based edge detectors in publicly available datasets when they are trained from scratch, and devise a new network architecture, the multi-stream and multi scale fusion net (msmsfnet), for edge detection. We show in our experiments that by training all models from scratch to ensure the fairness of comparison, out model outperforms state-of-the art deep learning based edge detectors in three publicly available datasets.
Abstract:To support extremely high data rates, reconfigurable intelligent surface (RIS)-assisted terahertz (THz) communication is considered to be a promising technology for future sixth-generation networks. However, due to the typical employment of hybrid beamforming architecture in THz systems, as well as the passive nature of RIS which lacks the capability to process pilot signals, obtaining channel state information (CSI) is facing significant challenges. To accurately estimate the cascaded channel, we propose a novel low-complexity channel estimation scheme, which includes three steps. Specifically, we first estimate full CSI within a small subset of subcarriers (SCs). Then, we acquire angular information at base station and RIS based on the full CSI. Finally, we derive spatial directions and recover full-CSI for the remaining SCs. Theoretical analysis and simulation results demonstrate that the proposed scheme can achieve superior performance in terms of normalized mean-square-error and exhibit a lower computational complexity compared with the existing algorithms.
Abstract:Recent studies have used unsupervised domain adaptive object detection (UDAOD) methods to bridge the domain gap in remote sensing (RS) images. However, UDAOD methods typically assume that the source domain data can be accessed during the domain adaptation process. This setting is often impractical in the real world due to RS data privacy and transmission difficulty. To address this challenge, we propose a practical source-free object detection (SFOD) setting for RS images, which aims to perform target domain adaptation using only the source pre-trained model. We propose a new SFOD method for RS images consisting of two parts: perturbed domain generation and alignment. The proposed multilevel perturbation constructs the perturbed domain in a simple yet efficient form by perturbing the domain-variant features at the image level and feature level according to the color and style bias. The proposed multilevel alignment calculates feature and label consistency between the perturbed domain and the target domain across the teacher-student network, and introduces the distillation of feature prototype to mitigate the noise of pseudo-labels. By requiring the detector to be consistent in the perturbed domain and the target domain, the detector is forced to focus on domaininvariant features. Extensive results of three synthetic-to-real experiments and three cross-sensor experiments have validated the effectiveness of our method which does not require access to source domain RS images. Furthermore, experiments on computer vision datasets show that our method can be extended to other fields as well. Our code will be available at: https://weixliu.github.io/ .
Abstract:Recently, the flourishing large language models(LLM), especially ChatGPT, have shown exceptional performance in language understanding, reasoning, and interaction, attracting users and researchers from multiple fields and domains. Although LLMs have shown great capacity to perform human-like task accomplishment in natural language and natural image, their potential in handling remote sensing interpretation tasks has not yet been fully explored. Moreover, the lack of automation in remote sensing task planning hinders the accessibility of remote sensing interpretation techniques, especially to non-remote sensing experts from multiple research fields. To this end, we present Remote Sensing ChatGPT, an LLM-powered agent that utilizes ChatGPT to connect various AI-based remote sensing models to solve complicated interpretation tasks. More specifically, given a user request and a remote sensing image, we utilized ChatGPT to understand user requests, perform task planning according to the tasks' functions, execute each subtask iteratively, and generate the final response according to the output of each subtask. Considering that LLM is trained with natural language and is not capable of directly perceiving visual concepts as contained in remote sensing images, we designed visual cues that inject visual information into ChatGPT. With Remote Sensing ChatGPT, users can simply send a remote sensing image with the corresponding request, and get the interpretation results as well as language feedback from Remote Sensing ChatGPT. Experiments and examples show that Remote Sensing ChatGPT can tackle a wide range of remote sensing tasks and can be extended to more tasks with more sophisticated models such as the remote sensing foundation model. The code and demo of Remote Sensing ChatGPT is publicly available at https://github.com/HaonanGuo/Remote-Sensing-ChatGPT .
Abstract:An important open question pertaining to the use of large language models for knowledge-intensive tasks is how to effectively integrate knowledge from three sources: the model's parametric memory, external structured knowledge, and external unstructured knowledge. Most existing prompting methods either rely solely on one or two of these sources, or require repeatedly invoking large language models to generate similar or identical content. In this work, we overcome these limitations by introducing a novel semi-structured prompting approach that seamlessly integrates the model's parametric memory with unstructured knowledge from text documents and structured knowledge from knowledge graphs. Experimental results on open-domain multi-hop question answering datasets demonstrate that our prompting method significantly surpasses existing techniques, even exceeding those which require fine-tuning.
Abstract:Answering time-sensitive questions from long documents requires temporal reasoning over the times in questions and documents. An important open question is whether large language models can perform such reasoning solely using a provided text document, or whether they can benefit from additional temporal information extracted using other systems. We address this research question by applying existing temporal information extraction systems to construct temporal graphs of events, times, and temporal relations in questions and documents. We then investigate different approaches for fusing these graphs into Transformer models. Experimental results show that our proposed approach for fusing temporal graphs into input text substantially enhances the temporal reasoning capabilities of Transformer models with or without fine-tuning. Additionally, our proposed method outperforms various graph convolution-based approaches and establishes a new state-of-the-art performance on SituatedQA and three splits of TimeQA.