Flexible laryngoscopy is commonly performed by otolaryngologists to detect laryngeal diseases and to recognize potentially malignant lesions. Recently, researchers have introduced machine learning techniques to facilitate automated diagnosis using laryngeal images and achieved promising results. Diagnostic performance can be improved when patients' demographic information is incorporated into models. However, manual entry of patient data is time consuming for clinicians. In this study, we made the first endeavor to employ deep learning models to predict patient demographic information to improve detector model performance. The overall accuracy for gender, smoking history, and age was 85.5%, 65.2%, and 75.9%, respectively. We also created a new laryngoscopic image set for machine learning study and benchmarked the performance of 8 classical deep learning models based on CNNs and Transformers. The results can be integrated into current learning models to improve their performance by incorporating the patient's demographic information.
Image steganography is the process of concealing secret information in images through imperceptible changes. Recent work has formulated this task as a classic constrained optimization problem. In this paper, we argue that image steganography is inherently performed on the (elusive) manifold of natural images, and propose an iterative neural network trained to perform the optimization steps. In contrast to classical optimization methods like L-BFGS or projected gradient descent, we train the neural network to also stay close to the manifold of natural images throughout the optimization. We show that our learned neural optimization is faster and more reliable than classical optimization approaches. In comparison to previous state-of-the-art encoder-decoder-based steganography methods, it reduces the recovery error rate by multiple orders of magnitude and achieves zero error up to 3 bits per pixel (bpp) without the need for error-correcting codes.
For grasp network algorithms, generating grasp datasets for a large number of 3D objects is a crucial task. However, generating grasp datasets for hundreds of objects can be very slow and consume a lot of storage resources, which hinders algorithm iteration and promotion. For point cloud grasp network algorithms, the network input is essentially the internal point cloud of the grasp area that intersects with the object in the gripper coordinate system. Due to the existence of a large number of completely consistent gripper area point clouds based on the gripper coordinate system in the grasp dataset generated for hundreds of objects, it is possible to remove the consistent gripper area point clouds from many objects and assemble them into a single object to generate the grasp dataset, thus replacing the enormous workload of generating grasp datasets for hundreds of objects. We propose a new approach to map the repetitive features of a large number of objects onto a finite set.To this end, we propose a method for extracting the gripper area point cloud that intersects with the object from the simulator and design a gripper feature filter to remove the shape-repeated gripper space area point clouds, and then assemble them into a single object. The experimental results show that the time required to generate the new object grasp dataset is greatly reduced compared to generating the grasp dataset for hundreds of objects, and it performs well in real machine grasping experiments. We will release the data and tools after the paper is accepted.
Vision Transformers have attracted a lot of attention recently since the successful implementation of Vision Transformer (ViT) on vision tasks. With vision Transformers, specifically the multi-head self-attention modules, networks can capture long-term dependencies inherently. However, these attention modules normally need to be trained on large datasets, and vision Transformers show inferior performance on small datasets when training from scratch compared with widely dominant backbones like ResNets. Note that the Transformer model was first proposed for natural language processing, which carries denser information than natural images. To boost the performance of vision Transformers on small datasets, this paper proposes to explicitly increase the input information density in the frequency domain. Specifically, we introduce selecting channels by calculating the channel-wise heatmaps in the frequency domain using Discrete Cosine Transform (DCT), reducing the size of input while keeping most information and hence increasing the information density. As a result, 25% fewer channels are kept while better performance is achieved compared with previous work. Extensive experiments demonstrate the effectiveness of the proposed approach on five small-scale datasets, including CIFAR-10/100, SVHN, Flowers-102, and Tiny ImageNet. The accuracy has been boosted up to 17.05% with Swin and Focal Transformers. Codes are available at https://github.com/xiangyu8/DenseVT.
Gradient inversion attack enables recovery of training samples from model updates in federated learning (FL) and constitutes a serious threat to data privacy. To mitigate this vulnerability, prior work proposed both principled defenses based on differential privacy, as well as heuristic defenses based on gradient compression as countermeasures. These defenses have so far been very effective, in particular those based on gradient compression that allow the model to maintain high accuracy while greatly reducing the attack's effectiveness. In this work, we argue that such findings do not accurately reflect the privacy risk in FL, and show that existing defenses can be broken by a simple adaptive attack that trains a model using auxiliary data to learn how to invert gradients on both vision and language tasks.
The attention mechanism plays a pivotal role in designing advanced super-resolution (SR) networks. In this work, we design an efficient SR network by improving the attention mechanism. We start from a simple pixel attention module and gradually modify it to achieve better super-resolution performance with reduced parameters. The specific approaches include: (1) increasing the receptive field of the attention branch, (2) replacing large dense convolution kernels with depth-wise separable convolutions, and (3) introducing pixel normalization. These approaches paint a clear evolutionary roadmap for the design of attention mechanisms. Based on these observations, we propose VapSR, the VAst-receptive-field Pixel attention network. Experiments demonstrate the superior performance of VapSR. VapSR outperforms the present lightweight networks with even fewer parameters. And the light version of VapSR can use only 21.68% and 28.18% parameters of IMDB and RFDN to achieve similar performances to those networks. The code and models are available at url{https://github.com/zhoumumu/VapSR.
Under-Display Camera (UDC) has been widely exploited to help smartphones realize full screen display. However, as the screen could inevitably affect the light propagation process, the images captured by the UDC system usually contain flare, haze, blur, and noise. Particularly, flare and blur in UDC images could severely deteriorate the user experience in high dynamic range (HDR) scenes. In this paper, we propose a new deep model, namely UDC-UNet, to address the UDC image restoration problem with the known Point Spread Function (PSF) in HDR scenes. On the premise that Point Spread Function (PSF) of the UDC system is known, we treat UDC image restoration as a non-blind image restoration problem and propose a novel learning-based approach. Our network consists of three parts, including a U-shape base network to utilize multi-scale information, a condition branch to perform spatially variant modulation, and a kernel branch to provide the prior knowledge of the given PSF. According to the characteristics of HDR data, we additionally design a tone mapping loss to stabilize network optimization and achieve better visual quality. Experimental results show that the proposed UDC-UNet outperforms the state-of-the-art methods in quantitative and qualitative comparisons. Our approach won the second place in the UDC image restoration track of MIPI challenge. Codes will be publicly available.
Conventional neural structures tend to communicate through analog quantities such as currents or voltages, however, as CMOS devices shrink and supply voltages decrease, the dynamic range of voltage/current-domain analog circuits becomes narrower, the available margin becomes smaller, and noise immunity decreases. More than that, the use of operational amplifiers (op-amps) and clocked or asynchronous comparators in conventional designs leads to high energy consumption and large chip area, which would be detrimental to building spiking neural networks. In view of this, we propose a neural structure for generating and transmitting time-domain signals, including a neuron module, a synapse module, and two weight modules. The proposed neural structure is driven by leakage currents in the transistor triode region and does not use op-amps and comparators, thus providing higher energy and area efficiency compared to conventional designs. In addition, the structure provides greater noise immunity due to internal communication via time-domain signals, which simplifies the wiring between the modules. The proposed neural structure is fabricated using TSMC 65 nm CMOS technology. The proposed neuron and synapse occupy an area of 127 um2 and 231 um2, respectively, while achieving millisecond time constants. Actual chip measurements show that the proposed structure successfully implements the temporal signal communication function with millisecond time constants, which is a critical step toward hardware reservoir computing for human-computer interaction.
Low-light video enhancement (LLVE) is an important yet challenging task with many applications such as photographing and autonomous driving. Unlike single image low-light enhancement, most LLVE methods utilize temporal information from adjacent frames to restore the color and remove the noise of the target frame. However, these algorithms, based on the framework of multi-frame alignment and enhancement, may produce multi-frame fusion artifacts when encountering extreme low light or fast motion. In this paper, inspired by the low latency and high dynamic range of events, we use synthetic events from multiple frames to guide the enhancement and restoration of low-light videos. Our method contains three stages: 1) event synthesis and enhancement, 2) event and image fusion, and 3) low-light enhancement. In this framework, we design two novel modules (event-image fusion transform and event-guided dual branch) for the second and third stages, respectively. Extensive experiments show that our method outperforms existing low-light video or single image enhancement approaches on both synthetic and real LLVE datasets.
Advances in perception for self-driving cars have accelerated in recent years due to the availability of large-scale datasets, typically collected at specific locations and under nice weather conditions. Yet, to achieve the high safety requirement, these perceptual systems must operate robustly under a wide variety of weather conditions including snow and rain. In this paper, we present a new dataset to enable robust autonomous driving via a novel data collection process - data is repeatedly recorded along a 15 km route under diverse scene (urban, highway, rural, campus), weather (snow, rain, sun), time (day/night), and traffic conditions (pedestrians, cyclists and cars). The dataset includes images and point clouds from cameras and LiDAR sensors, along with high-precision GPS/INS to establish correspondence across routes. The dataset includes road and object annotations using amodal masks to capture partial occlusions and 3D bounding boxes. We demonstrate the uniqueness of this dataset by analyzing the performance of baselines in amodal segmentation of road and objects, depth estimation, and 3D object detection. The repeated routes opens new research directions in object discovery, continual learning, and anomaly detection. Link to Ithaca365: https://ithaca365.mae.cornell.edu/