Search

The widespread use of face recognition technology has given rise to privacy concerns, as many individuals are worried about the collection and utilization of their facial data. To address these concerns, researchers are actively exploring the concept of ``unlearnable examples", by adding imperceptible perturbation to data in the model training stage, which aims to prevent the model from learning discriminate features of the target face. However, current methods are inefficient and cannot guarantee transferability and robustness at the same time, causing impracticality in the real world. To remedy it, we propose a novel method called Segue: Side-information guided generative unlearnable examples. Specifically, we leverage a once-trained multiple-used model to generate the desired perturbation rather than the time-consuming gradient-based method. To improve transferability, we introduce side information such as true labels and pseudo labels, which are inherently consistent across different scenarios. For robustness enhancement, a distortion layer is integrated into the training pipeline. Extensive experiments demonstrate that the proposed Segue is much faster than previous methods (1000$\times$) and achieves transferable effectiveness across different datasets and model architectures. Furthermore, it can resist JPEG compression, adversarial training, and some standard data augmentations.

Hyperspectrally compressed ultrafast photography (HCUP) based on compressed sensing and the time- and spectrum-to-space mappings can simultaneously realize the temporal and spectral imaging of non-repeatable or difficult-to-repeat transient events passively in a single exposure. It possesses an incredibly high frame rate of tens of trillions of frames per second and a sequence depth of several hundred, and plays a revolutionary role in single-shot ultrafast optical imaging. However, due to the ultra-high data compression ratio induced by the extremely large sequence depth as well as the limited fidelities of traditional reconstruction algorithms over the reconstruction process, HCUP suffers from a poor image reconstruction quality and fails to capture fine structures in complex transient scenes. To overcome these restrictions, we propose a flexible image reconstruction algorithm based on the total variation (TV) and cascaded denoisers (CD) for HCUP, named the TV-CD algorithm. It applies the TV denoising model cascaded with several advanced deep learning-based denoising models in the iterative plug-and-play alternating direction method of multipliers framework, which can preserve the image smoothness while utilizing the deep denoising networks to obtain more priori, and thus solving the common sparsity representation problem in local similarity and motion compensation. Both simulation and experimental results show that the proposed TV-CD algorithm can effectively improve the image reconstruction accuracy and quality of HCUP, and further promote the practical applications of HCUP in capturing high-dimensional complex physical, chemical and biological ultrafast optical scenes., Comment: 25 pages, 5 figures and 1 table

Empowering chatbots in the field of mental health is receiving increasing amount of attention, while there still lacks exploration in developing and evaluating chatbots in psychiatric outpatient scenarios. In this work, we focus on exploring the potential of ChatGPT in powering chatbots for psychiatrist and patient simulation. We collaborate with psychiatrists to identify objectives and iteratively develop the dialogue system to closely align with real-world scenarios. In the evaluation experiments, we recruit real psychiatrists and patients to engage in diagnostic conversations with the chatbots, collecting their ratings for assessment. Our findings demonstrate the feasibility of using ChatGPT-powered chatbots in psychiatric scenarios and explore the impact of prompt designs on chatbot behavior and user experience.

Controlling chatbot utterance generation with multiple attributes such as personalities, emotions and dialogue acts is a practically useful but under-studied problem. We propose a novel framework called DASC that possesses strong controllability with a weighted decoding paradigm, while improving generation quality with the grounding in an attribute semantics space. Generation with multiple attributes is then intuitively implemented with an interpolation of multiple attribute embeddings, which results in substantial reduction in the model sizes. Experiments show that DASC can achieve high control accuracy in generation task with the simultaneous control of 3 aspects while also producing interesting and reasonably sensible responses, even in an out-of-distribution robustness test., Comment: EMNLP 2023

Compared with ample visual-text pre-training research, few works explore audio-text pre-training, mostly due to the lack of sufficient parallel audio-text data. Most existing methods incorporate the visual modality as a pivot for audio-text pre-training, which inevitably induces data noise. In this paper, we propose to utilize audio captioning to generate text directly from audio, without the aid of the visual modality so that potential noise from modality mismatch is eliminated. Furthermore, we propose caption generation under the guidance of AudioSet tags, leading to more accurate captions. With the above two improvements, we curate high-quality, large-scale parallel audio-text data, based on which we perform audio-text pre-training. We comprehensively demonstrate the performance of the pre-trained model on a series of downstream audio-related tasks, including single-modality tasks like audio classification and tagging, as well as cross-modal tasks consisting of audio-text retrieval and audio-based text generation. Experimental results indicate that our approach achieves state-of-the-art zero-shot classification performance on most datasets, suggesting the effectiveness of our synthetic data. The audio encoder also serves as an efficient pattern recognition model by fine-tuning it on audio-related tasks. Synthetic data and pre-trained models are available online.

Mental disease detection (MDD) from social media has suffered from poor generalizability and interpretability, due to lack of symptom modeling. This paper introduces PsySym, the first annotated symptom identification corpus of multiple psychiatric disorders, to facilitate further research progress. PsySym is annotated according to a knowledge graph of the 38 symptom classes related to 7 mental diseases complied from established clinical manuals and scales, and a novel annotation framework for diversity and quality. Experiments show that symptom-assisted MDD enabled by PsySym can outperform strong pure-text baselines. We also exhibit the convincing MDD explanations provided by symptom predictions with case studies, and point to their further potential applications.

Depression is a prominent health challenge to the world, and early risk detection (ERD) of depression from online posts can be a promising technique for combating the threat. Early depression detection faces the challenge of efficiently tackling streaming data, balancing the tradeoff between timeliness, accuracy and explainability. To tackle these challenges, we propose a psychiatric scale guided risky post screening method that can capture risky posts related to the dimensions defined in clinical depression scales, and providing interpretable diagnostic basis. A Hierarchical Attentional Network equipped with BERT (HAN-BERT) is proposed to further advance explainable predictions. For ERD, we propose an online algorithm based on an evolving queue of risky posts that can significantly reduce the number of model inferences to boost efficiency. Experiments show that our method outperforms the competitive feature-based and neural models under conventional depression detection settings, and achieves simultaneous improvement in both efficacy and efficiency for ERD., Comment: IJCAI 2022 AI for Good

Automated audio captioning aims at generating textual descriptions for an audio clip. To evaluate the quality of generated audio captions, previous works directly adopt image captioning metrics like SPICE and CIDEr, without justifying their suitability in this new domain, which may mislead the development of advanced models. This problem is still unstudied due to the lack of human judgment datasets on caption quality. Therefore, we firstly construct two evaluation benchmarks, AudioCaps-Eval and Clotho-Eval. They are established with pairwise comparison instead of absolute rating to achieve better inter-annotator agreement. Current metrics are found in poor correlation with human annotations on these datasets. To overcome their limitations, we propose a metric named FENSE, where we combine the strength of Sentence-BERT in capturing similarity, and a novel Error Detector to penalize erroneous sentences for robustness. On the newly established benchmarks, FENSE outperforms current metrics by 14-25% accuracy. Code, data and web demo available at: https://github.com/blmoistawinde/fense, Comment: ICASSP 2022

Audio tagging aims at predicting sound events occurred in a recording. Traditional models require enormous laborious annotations, otherwise performance degeneration will be the norm. Therefore, we investigate robust audio tagging models in low-resource scenarios with the enhancement of knowledge graphs. Besides existing ontological knowledge, we further propose a semi-automatic approach that can construct temporal knowledge graphs on diverse domain-specific label sets. Moreover, we leverage a variant of relation-aware graph neural network, D-GCN, to combine the strength of the two knowledge types. Experiments on AudioSet and SONYC urban sound tagging datasets suggest the effectiveness of the introduced temporal knowledge, and the advantage of the combined KGs with D-GCN over single knowledge source., Comment: CIKM 2021

Product descriptions on e-commerce websites often suffer from missing important aspects. Clarification question generation (CQGen) can be a promising approach to help alleviate the problem. Unlike traditional QGen assuming the existence of answers in the context and generating questions accordingly, CQGen mimics user behaviors of asking for unstated information. The generated CQs can serve as a sanity check or proofreading to help e-commerce merchant to identify potential missing information before advertising their product, and improve consumer experience consequently. Due to the variety of possible user backgrounds and use cases, the information need can be quite diverse but also specific to a detailed topic, while previous works assume generating one CQ per context and the results tend to be generic. We thus propose the task of Diverse CQGen and also tackle the challenge of specificity. We propose a new model named KPCNet, which generates CQs with Keyword Prediction and Conditioning, to deal with the tasks. Automatic and human evaluation on 2 datasets (Home & Kitchen, Office) showed that KPCNet can generate more specific questions and promote better group-level diversity than several competing baselines., Comment: 11 pages, 3 figures, WWW 2021

In Mandarin text-to-speech (TTS) system, the front-end text processing module significantly influences the intelligibility and naturalness of synthesized speech. Building a typical pipeline-based front-end which consists of multiple individual components requires extensive efforts. In this paper, we proposed a unified sequence-to-sequence front-end model for Mandarin TTS that converts raw texts to linguistic features directly. Compared to the pipeline-based front-end, our unified front-end can achieve comparable performance in polyphone disambiguation and prosody word prediction, and improve intonation phrase prediction by 0.0738 in F1 score. We also implemented the unified front-end with Tacotron and WaveRNN to build a Mandarin TTS system. The synthesized speech by that got a comparable MOS (4.38) with the pipeline-based front-end (4.37) and close to human recordings (4.49)., Comment: Submitted to ICASSP 2020