Aerial Image Segmentation is a top-down perspective semantic segmentation and has several challenging characteristics such as strong imbalance in the foreground-background distribution, complex background, intra-class heterogeneity, inter-class homogeneity, and tiny objects. To handle these problems, we inherit the advantages of Transformers and propose AerialFormer, which unifies Transformers at the contracting path with lightweight Multi-Dilated Convolutional Neural Networks (MD-CNNs) at the expanding path. Our AerialFormer is designed as a hierarchical structure, in which Transformer encoder outputs multi-scale features and MD-CNNs decoder aggregates information from the multi-scales. Thus, it takes both local and global contexts into consideration to render powerful representations and high-resolution segmentation. We have benchmarked AerialFormer on three common datasets including iSAID, LoveDA, and Potsdam. Comprehensive experiments and extensive ablation studies show that our proposed AerialFormer outperforms previous state-of-the-art methods with remarkable performance. Our source code will be publicly available upon acceptance.
Rapid developments in machine vision have led to advances in a variety of industries, from medical image analysis to autonomous systems. These achievements, however, typically necessitate digital neural networks with heavy computational requirements, which are limited by high energy consumption and further hinder real-time decision-making when computation resources are not accessible. Here, we demonstrate an intelligent meta-imager that is designed to work in concert with a digital back-end to off-load computationally expensive convolution operations into high-speed and low-power optics. In this architecture, metasurfaces enable both angle and polarization multiplexing to create multiple information channels that perform positive and negatively valued convolution operations in a single shot. The meta-imager is employed for object classification, experimentally achieving 98.6% accurate classification of handwritten digits and 88.8% accuracy in classifying fashion images. With compactness, high speed, and low power consumption, this approach could find a wide range of applications in artificial intelligence and machine vision applications.
A new data-driven bilateral generalized two-dimensional quaternion principal component analysis (BiG2DQPCA) is presented to extract the features of matrix samples from both row and column directions. This general framework directly works on the 2D color images without vectorizing and well preserves the spatial and color information, which makes it flexible to fit various real-world applications. A generalized ridge regression model of BiG2DQPCA is firstly proposed with orthogonality constrains on aimed features. Applying the deflation technique and the framework of minorization-maximization, a new quaternion optimization algorithm is proposed to compute the optimal features of BiG2DQPCA and a closed-form solution is obtained at each iteration. A new approach based on BiG2DQPCA is presented for color face recognition and image reconstruction with a new data-driven weighting technique. Sufficient numerical experiments are implemented on practical color face databases and indicate the superiority of BiG2DQPCA over the state-of-the-art methods in terms of recognition accuracies and rates of image reconstruction.
Despite the huge successes made in neutral TTS, content-leakage remains a challenge. In this paper, we propose a new input representation and simple architecture to achieve improved prosody modeling. Inspired by the recent success in the use of discrete code in TTS, we introduce discrete code to the input of the reference encoder. Specifically, we leverage the vector quantizer from the audio compression model to exploit the diverse acoustic information it has already been trained on. In addition, we apply the modified MLP-Mixer to the reference encoder, making the architecture lighter. As a result, we train the prosody transfer TTS in an end-to-end manner. We prove the effectiveness of our method through both subjective and objective evaluations. We demonstrate that the reference encoder learns better speaker-independent prosody when discrete code is utilized as input in the experiments. In addition, we obtain comparable results even when fewer parameters are inputted.
Coreference resolution is the task of identifying and grouping mentions referring to the same real-world entity. Previous neural models have mainly focused on learning span representations and pairwise scores for coreference decisions. However, current methods do not explicitly capture the referential choice in the hierarchical discourse, an important factor in coreference resolution. In this study, we propose a new approach that incorporates rhetorical information into neural coreference resolution models. We collect rhetorical features from automated discourse parses and examine their impact. As a base model, we implement an end-to-end span-based coreference resolver using a partially fine-tuned multilingual entity-aware language model LUKE. We evaluate our method on the RuCoCo-23 Shared Task for coreference resolution in Russian. Our best model employing rhetorical distance between mentions has ranked 1st on the development set (74.6% F1) and 2nd on the test set (73.3% F1) of the Shared Task. We hope that our work will inspire further research on incorporating discourse information in neural coreference resolution models.
People are increasingly turning to large language models (LLMs) for complex information tasks like academic research or planning a move to another city. However, while they often require working in a nonlinear manner - e.g., to arrange information spatially to organize and make sense of it, current interfaces for interacting with LLMs are generally linear to support conversational interaction. To address this limitation and explore how we can support LLM-powered exploration and sensemaking, we developed Sensecape, an interactive system designed to support complex information tasks with an LLM by enabling users to (1) manage the complexity of information through multilevel abstraction and (2) seamlessly switch between foraging and sensemaking. Our within-subject user study reveals that Sensecape empowers users to explore more topics and structure their knowledge hierarchically. We contribute implications for LLM-based workflows and interfaces for information tasks.
LLM-powered chatbots are becoming widely adopted in applications such as healthcare, personal assistants, industry hiring decisions, etc. In many of these cases, chatbots are fed sensitive, personal information in their prompts, as samples for in-context learning, retrieved records from a database, or as part of the conversation. The information provided in the prompt could directly appear in the output, which might have privacy ramifications if there is sensitive information there. As such, in this paper, we aim to understand the input copying and regurgitation capabilities of these models during inference and how they can be directly instructed to limit this copying by complying with regulations such as HIPAA and GDPR, based on their internal knowledge of them. More specifically, we find that when ChatGPT is prompted to summarize cover letters of a 100 candidates, it would retain personally identifiable information (PII) verbatim in 57.4% of cases, and we find this retention to be non-uniform between different subgroups of people, based on attributes such as gender identity. We then probe ChatGPT's perception of privacy-related policies and privatization mechanisms by directly instructing it to provide compliant outputs and observe a significant omission of PII from output.
Hearing aids are typically equipped with multiple microphones to exploit spatial information for source localisation and speech enhancement. Especially for hearing aids, a good source localisation is important: it not only guides source separation methods but can also be used to enhance spatial cues, increasing user-awareness of important events in their surroundings. We use a state-of-the-art deep neural network (DNN) to perform binaural direction-of-arrival (DoA) estimation, where the DNN uses information from all microphones at both ears. However, hearing aids have limited bandwidth to exchange this data. Bluetooth low-energy (BLE) is emerging as an attractive option to facilitate such data exchange, with the LC3plus codec offering several bitrate and latency trade-off possibilities. In this paper, we investigate the effect of such lossy codecs on localisation accuracy. Specifically, we consider two conditions: processing at one ear vs processing at a central point, which influences the number of channels that need to be encoded. Performance is benchmarked against a baseline that allows full audio-exchange - yielding valuable insights into the usage of DNNs under lossy encoding. We also extend the Pyroomacoustics library to include hearing-device and head-related transfer functions (HD-HRTFs) to suitably train the networks. This can also benefit other researchers in the field.
Node classification is a substantial problem in graph-based fraud detection. Many existing works adopt Graph Neural Networks (GNNs) to enhance fraud detectors. While promising, currently most GNN-based fraud detectors fail to generalize to the low homophily setting. Besides, label utilization has been proved to be significant factor for node classification problem. But we find they are less effective in fraud detection tasks due to the low homophily in graphs. In this work, we propose GAGA, a novel Group AGgregation enhanced TrAnsformer, to tackle the above challenges. Specifically, the group aggregation provides a portable method to cope with the low homophily issue. Such an aggregation explicitly integrates the label information to generate distinguishable neighborhood information. Along with group aggregation, an attempt towards end-to-end trainable group encoding is proposed which augments the original feature space with the class labels. Meanwhile, we devise two additional learnable encodings to recognize the structural and relational context. Then, we combine the group aggregation and the learnable encodings into a Transformer encoder to capture the semantic information. Experimental results clearly show that GAGA outperforms other competitive graph-based fraud detectors by up to 24.39% on two trending public datasets and a real-world industrial dataset from Anonymous. Even more, the group aggregation is demonstrated to outperform other label utilization methods (e.g., C&S, BoT/UniMP) in the low homophily setting.
News recommender systems (NRS) have been widely applied for online news websites to help users find relevant articles based on their interests. Recent methods have demonstrated considerable success in terms of recommendation performance. However, the lack of explanation for these recommendations can lead to mistrust among users and lack of acceptance of recommendations. To address this issue, we propose a new explainable news model to construct a topic-aware explainable recommendation approach that can both accurately identify relevant articles and explain why they have been recommended, using information from associated topics. Additionally, our model incorporates two coherence metrics applied to assess topic quality, providing measure of the interpretability of these explanations. The results of our experiments on the MIND dataset indicate that the proposed explainable NRS outperforms several other baseline systems, while it is also capable of producing interpretable topics compared to those generated by a classical LDA topic model. Furthermore, we present a case study through a real-world example showcasing the usefulness of our NRS for generating explanations.