Search

Image Quality Assessment (IQA) is essential in various Computer Vision tasks such as image deblurring and super-resolution. However, most IQA methods require reference images, which are not always available. While there are some reference-free IQA metrics, they have limitations in simulating human perception and discerning subtle image quality variations. We hypothesize that the JPEG quality factor is representatives of image quality measurement, and a well-trained neural network can learn to accurately evaluate image quality without requiring a clean reference, as it can recognize image degradation artifacts based on prior knowledge. Thus, we developed a reference-free quality evaluation network, dubbed "Quality Factor (QF) Predictor", which does not require any reference. Our QF Predictor is a lightweight, fully convolutional network comprising seven layers. The model is trained in a self-supervised manner: it receives JPEG compressed image patch with a random QF as input, is trained to accurately predict the corresponding QF. We demonstrate the versatility of the model by applying it to various tasks. First, our QF Predictor can generalize to measure the severity of various image artifacts, such as Gaussian Blur and Gaussian noise. Second, we show that the QF Predictor can be trained to predict the undersampling rate of images reconstructed from Magnetic Resonance Imaging (MRI) data.

Question answering over heterogeneous data requires reasoning over diverse sources of data, which is challenging due to the large scale of information and organic coupling of heterogeneous data. Various approaches have been proposed to address these challenges. One approach involves training specialized retrievers to select relevant information, thereby reducing the input length. Another approach is to transform diverse modalities of data into a single modality, simplifying the task difficulty and enabling more straightforward processing. In this paper, we propose HProPro, a novel program-based prompting framework for the hybrid question answering task. HProPro follows the code generation and execution paradigm. In addition, HProPro integrates various functions to tackle the hybrid reasoning scenario. Specifically, HProPro contains function declaration and function implementation to perform hybrid information-seeking over data from various sources and modalities, which enables reasoning over such data without training specialized retrievers or performing modal transformations. Experimental results on two typical hybrid question answering benchmarks HybridQA and MultiModalQA demonstrate the effectiveness of HProPro: it surpasses all baseline systems and achieves the best performances in the few-shot settings on both datasets.

Millimetre-wave (mmWave) radar has emerged as an attractive and cost-effective alternative for human activity sensing compared to traditional camera-based systems. mmWave radars are also non-intrusive, providing better protection for user privacy. However, as a Radio Frequency (RF) based technology, mmWave radars rely on capturing reflected signals from objects, making them more prone to noise compared to cameras. This raises an intriguing question for the deep learning community: Can we develop more effective point set-based deep learning methods for such attractive sensors? To answer this question, our work, termed MiliPoint, delves into this idea by providing a large-scale, open dataset for the community to explore how mmWave radars can be utilised for human activity recognition. Moreover, MiliPoint stands out as it is larger in size than existing datasets, has more diverse human actions represented, and encompasses all three key tasks in human activity recognition. We have also established a range of point-based deep neural networks such as DGCNN, PointNet++ and PointTransformer, on MiliPoint, which can serve to set the ground baseline for further development., Comment: Accepted at NeurIPS 2023 Datasets & Benchmarks

Objective: This study aims at investigating a novel super resolution CBCT imaging technique with the dual-layer flat panel detector (DL-FPD). Approach: In DL-FPD based CBCT imaging, the low-energy and high-energy projections acquired from the top and bottom detector layers contain intrinsically mismatched spatial information, from which super resolution CBCT images can be generated. To explain, a simple mathematical model is established according to the signal formation procedure in DL-FPD. Next, a dedicated recurrent neural network (RNN), named as suRi-Net, is designed by referring to the above imaging model to retrieve the high resolution dual-energy information. Different phantom experiments are conducted to validate the performance of this newly developed super resolution CBCT imaging method. Main Results: Results show that the proposed suRi-Net can retrieve high spatial resolution information accurately from the low-energy and high-energy projections having lower spatial resolution. Quantitatively, the spatial resolution of the reconstructed CBCT images of the top and bottom detector layers is increased by about 45% and 54%, respectively. Significance: In future, suRi-Net provides a new approach to achieve high spatial resolution dual-energy imaging in DL-FPD based CBCT systems.

The generation of explanation graphs is a significant task that aims to produce explanation graphs in response to user input, revealing the internal reasoning process. This task is challenging due to the significant discrepancy between unstructured user queries and structured explanation graphs. Current research commonly fine-tunes a text-based pre-trained language model on a small downstream dataset that is annotated with labeled graphs. However, due to the limited scale of available datasets, this approach may prove to be insufficient in bridging the gap between natural language text and structured graphs. In this paper, to alleviate the above limitations, we propose a novel pre-trained framework EG3P(for Explanation Graph Generation via Generative Pre-training over synthetic graphs) for the explanation graph generation task. Specifically, we first propose a text-to-graph generative task to pre-train the model with the goal of bridging the text-graph gap. Additionally, we propose an automatic corpus synthesis strategy for synthesizing a large scale of high-quality corpus, reducing the reliance on costly manual annotation methods. Experimental results on ExplaGraphs show the effectiveness of EG3P that our model surpasses all baseline systems with remarkable margins. Besides, further analysis demonstrates that EG3P is able to generate better explanation graphs on actual reasoning tasks such as CommonsenseQA and OpenbookQA., Comment: Accepted by ACL23-Findings

Low Gain Avalanche Detectors (LGAD) for the High-Granularity Timing Detector (HGTD) are crucial in reducing pileups in the High-Luminosity Large Hadron Collider. Numerous studies have been conducted on the bulk irradiation damage of LGADs. However, few studies have been carried out on the surface irradiation damage of LGAD sensors with shallow carbon implantation. In this paper, the IHEP-IME LGADs with shallow carbon implantation were irradiated up to 2 MGy using gamma irradiation to investigate surface damage. Important characteristic parameters, including leakage currents, breakdown voltage (BV), inter-pad resistances, and capacitances, were tested before and after irradiation. The results showed that the leakage current and BV increased after irradiation, whereas overall inter-pad resistance exhibited minimal change and remained above $10^9\ \Omega$ before and after irradiation. Capacitance was found to be less than 4.5 pF with a slight decrease in the gain layer depletion voltage (V$_{gl}$) after irradiation. No parameter affected by the inter-pad separation was observed before and after irradiation. All characteristic parameters meet the requirements of HGTD, and this design can be used to further optimization.

Millimetre-wave (mmWave) radars can generate 3D point clouds to represent objects in the scene. However, the accuracy and density of the generated point cloud can be lower than a laser sensor. Although researchers have used mmWave radars for various applications, there are few quantitative evaluations on the quality of the point cloud generated by the radar and there is a lack of a standard on how this quality can be assessed. This work aims to fill the gap in the literature. A radar simulator is built to evaluate the most common data processing chains of 3D point cloud construction and to examine the capability of the mmWave radar as a 3D imaging sensor under various factors. It will be shown that the radar detection can be noisy and have an imbalance distribution. To address the problem, a novel super-resolution point cloud construction (SRPC) algorithm is proposed to improve the spatial resolution of the point cloud and is shown to be able to produce a more natural point cloud and reduce outliers., Comment: 14 pages, 16 figures

For medical cone-beam computed tomography (CBCT) imaging, the native receptor array of the flat-panel detector (FPD) is usually binned into a reduced matrix size. By doing so, the signal readout speed can be increased by over 4-9 times at the expense of sacrificing the spatial resolution by at least 50%-67%. Clearly, such tradition poses a main bottleneck in generating high spatial resolution and high temporal resolution CBCT images at the same time. In addition, the conventional FPD is also difficult in generating dual-energy CBCT images. In this paper, we propose an innovative super resolution dual-energy CBCT imaging method, named as suRi, based on dual-layer FPD (DL-FPD) to overcome these aforementioned difficulties at once. With suRi, specifically, an 1D or 2D sub-pixel (half pixel in this study) shifted binning is applied to replace the conventionally aligned binning to double the spatial sampling rate during the dual-energy data acquisition. As a result, the suRi approach provides a new strategy to enable high signal readout speed and high spatial resolution CBCT imaging with FPD. Moreover, a penalized likelihood material decomposition algorithm is developed to directly reconstruct the high resolution bases from the dual-energy CBCT projections containing spatial sub-pixel shifts. Experiments based on the single-layer FPD and DL-FPD are performed with physical phantoms and biological specimen to validate this newly developed suRi method. The synthesized monochromatic CT imaging results demonstrate that suRi can significantly improve the spatial image resolution by 46.15%. We believe the developed suRi method would be capable to greatly enhance the imaging performance of the DL-FPD based dual-energy CBCT systems in future.

The low gain avalanche detectors (LGADs) are thin sensors with fast charge collection which in combination with internal gain deliver an outstanding time resolution of about 30 ps. High collision rates and consequent large particle rates crossing the detectors at the upgraded Large Hadron Collider (LHC) in 2028 will lead to radiation damage and deteriorated performance of the LGADs. The main consequence of radiation damage is loss of gain layer doping (acceptor removal) which requires an increase of bias voltage to compensate for the loss of charge collection efficiency and consequently time resolution. The Institute of High Energy Physics (IHEP), Chinese Academy of Sciences (CAS) has developed a process based on the Institute of Microelectronics (IME), CAS capability to enrich the gain layer with carbon to reduce the acceptor removal effect by radiation. After 1 MeV neutron equivalent fluence of 2.5$\times$10$^{15}$ n$_{eq}$/cm$^{2}$, which is the maximum fluence to which sensors will be exposed at ATLAS High Granularity Timing Detector (HGTD), the IHEP-IME second version (IHEP-IMEv2) 50 $\mu$m LGAD sensors already deliver adequate charge collection > 4 fC and time resolution < 50 ps at voltages < 400 V. The operation voltages of these 50 $\mu$m devices are well below those at which single event burnout may occur.

Low Gain Avalanche Diode (LGAD) is applied for the High-Granularity Timing Detector (HGTD), and it will be used to upgrade the ATLAS experiment. The first batch IHEP-IME LGAD sensors were designed by the Institute of High Energy Physics (IHEP) and fabricated by the Institute of Microelectronics (IME). Three IHEP-IME sensors (W1, W7 and W8) were irradiated by the neutrons up to the fluence of 2.5 x 10^15 n_eq/cm^2 to study the effect of the shallow carbon and deep N++ layer on the irradiation hardness. Taking W7 as a reference, W1 has an extra shallow carbon applied, and W8 has a deeper N++ layer., Comment: This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible

The performances of Low Gain Avalanche diode (LGAD) sensors from a neutron irradiation campaign with fluences of 0.8 x 10^15, 15 x 10^15 and 2.5 x 10^15 neq/cm2 are reported in this article. These LGAD sensors are developed by the Institute of High Energy Physics, Chinese Academy of Sciences and the Novel Device Laboratory for the High Granularity Timing Detector of the High Luminosity Large Hadron Collider. The timing resolution and collected charge of the LGAD sensors were measured with electrons from a beta source. After irradiation with a fluence of 2.5 x 10^15 neq/cm2, the collected charge decreases from 40 fC to 7 fC, the signal-to-noise ratio deteriorates from 48 to 12, and the timing resolution increases from 29 ps to 39 ps.

We report precise TCAD simulations of IHEP-IME-v1 Low Gain Avalanche Diode (LGAD) calibrated by secondary ion mass spectroscopy (SIMS). Our setup allows us to evaluate the leakage current, capacitance, and breakdown voltage of LGAD, which agree with measurements' results before irradiation. And we propose an improved LGAD Radiation Damage Model (LRDM) which combines local acceptor removal with global deep energy levels. The LRDM is applied to the IHEP-IME-v1 LGAD and able to predict the leakage current well at -30 $^{\circ}$C after an irradiation fluence of $ \Phi_{eq}=2.5 \times 10^{15} ~n_{eq}/cm^{2}$. The charge collection efficiency (CCE) is under development.

Conventional detection networks usually need abundant labeled training samples, while humans can learn new concepts incrementally with just a few examples. This paper focuses on a more challenging but realistic class-incremental few-shot object detection problem (iFSD). It aims to incrementally transfer the model for novel objects from only a few annotated samples without catastrophically forgetting the previously learned ones. To tackle this problem, we propose a novel method LEAST, which can transfer with Less forgetting, fEwer training resources, And Stronger Transfer capability. Specifically, we first present the transfer strategy to reduce unnecessary weight adaptation and improve the transfer capability for iFSD. On this basis, we then integrate the knowledge distillation technique using a less resource-consuming approach to alleviate forgetting and propose a novel clustering-based exemplar selection process to preserve more discriminative features previously learned. Being a generic and effective method, LEAST can largely improve the iFSD performance on various benchmarks.

This paper studies a WiFi indoor localisation technique based on using a deep learning model and its transfer strategies. We take CSI packets collected via the WiFi standard channel sounding as the training dataset and verify the CNN model on the subsets collected in three experimental environments. We achieve a localisation accuracy of 46.55 cm in an ideal $(6.5m \times 2.5m)$ office with no obstacles, 58.30 cm in an office with obstacles, and 102.8 cm in a sports hall $(40 \times 35m)$. Then, we evaluate the transfer ability of the proposed model to different environments. The experimental results show that, for a trained localisation model, feature extraction layers can be directly transferred to other models and only the fully connected layers need to be retrained to achieve the same baseline accuracy with non-transferred base models. This can save 60% of the training parameters and reduce the training time by more than half. Finally, an ablation study of the training dataset shows that, in both office and sport hall scenarios, after reusing the feature extraction layers of the base model, only 55% of the training data is required to obtain the models' accuracy similar to the base models., Comment: 5 pages, 5 figures, has been accepted for lecture presentation at the 2021 IEEE Radar Conference (IEEE RadarConf 2021)

This paper studies the indoor localisation of WiFi devices based on a commodity chipset and standard channel sounding. First, we present a novel shallow neural network (SNN) in which features are extracted from the channel state information (CSI) corresponding to WiFi subcarriers received on different antennas and used to train the model. The single-layer architecture of this localisation neural network makes it lightweight and easy-to-deploy on devices with stringent constraints on computational resources. We further investigate for localisation the use of deep learning models and design novel architectures for convolutional neural network (CNN) and long-short term memory (LSTM). We extensively evaluate these localisation algorithms for continuous tracking in indoor environments. Experimental results prove that even an SNN model, after a careful handcrafted feature extraction, can achieve accurate localisation. Meanwhile, using a well-organised architecture, the neural network models can be trained directly with raw data from the CSI and localisation features can be automatically extracted to achieve accurate position estimates. We also found that the performance of neural network-based methods are directly affected by the number of anchor access points (APs) regardless of their structure. With three APs, all neural network models proposed in this paper can obtain localisation accuracy of around 0.5 metres. In addition the proposed deep NN architecture reduces the data pre-processing time by 6.5 hours compared with a shallow NN using the data collected in our testbed. In the deployment phase, the inference time is also significantly reduced to 0.1 ms per sample. We also demonstrate the generalisation capability of the proposed method by evaluating models using different target movement characteristics to the ones in which they were trained., Comment: Accepted for presentation at the 25th International Conference on Pattern Recognition (ICPR), IEEE, 2020

Recent research on reinforcement learning (RL) has suggested that trained agents are vulnerable to maliciously crafted adversarial samples. In this work, we show how such samples can be generalised from White-box and Grey-box attacks to a strong Black-box case, where the attacker has no knowledge of the agents, their training parameters and their training methods. We use sequence-to-sequence models to predict a single action or a sequence of future actions that a trained agent will make. First, we show our approximation model, based on time-series information from the agent, consistently predicts RL agents' future actions with high accuracy in a Black-box setup on a wide range of games and RL algorithms. Second, we find that although adversarial samples are transferable from the target model to our RL agents, they often outperform random Gaussian noise only marginally. This highlights a serious methodological deficiency in previous work on such agents; random jamming should have been taken as the baseline for evaluation. Third, we propose a novel use for adversarial samplesin Black-box attacks of RL agents: they can be used to trigger a trained agent to misbehave after a specific time delay. This appears to be a genuinely new type of attack. It potentially enables an attacker to use devices controlled by RL agents as time bombs.