In recent years, deep learning approaches have been proved good performance in traffic flow prediction, many complex models have been proposed to make traffic flow prediction more accurate. However, lacking transparency limits the domain experts on understanding when and where the input data mainly impact the results. Most urban experts and planners can only adjust traffic based on their own experience and can not react effectively toward the potential traffic jam. To tackle this problem, we adapt Shapley value and present a visualization analysis system , which can provide experts with the interpretation of traffic flow prediction. TrafPS consists of three layers, from data process to results computation and visualization. We design three visualization views in TrafPS to support the prediction analysis process. One demonstration shows that the TrafPS supports an effective analytical pipeline on interpreting the prediction flow to users and provides an intuitive visualization for decision making.
The transformer architectures with attention mechanisms have obtained success in Nature Language Processing (NLP), and Vision Transformers (ViTs) have recently extended the application domains to various vision tasks. While achieving high performance, ViTs suffer from large model size and high computation complexity that hinders the deployment of them on edge devices. To achieve high throughput on hardware and preserve the model accuracy simultaneously, we propose VAQF, a framework that builds inference accelerators on FPGA platforms for quantized ViTs with binary weights and low-precision activations. Given the model structure and the desired frame rate, VAQF will automatically output the required quantization precision for activations as well as the optimized parameter settings of the accelerator that fulfill the hardware requirements. The implementations are developed with Vivado High-Level Synthesis (HLS) on the Xilinx ZCU102 FPGA board, and the evaluation results with the DeiT-base model indicate that a frame rate requirement of 24 frames per second (FPS) is satisfied with 8-bit activation quantization, and a target of 30 FPS is met with 6-bit activation quantization. To the best of our knowledge, this is the first time quantization has been incorporated into ViT acceleration on FPGAs with the help of a fully automatic framework to guide the quantization strategy on the software side and the accelerator implementations on the hardware side given the target frame rate. Very small compilation time cost is incurred compared with quantization training, and the generated accelerators show the capability of achieving real-time execution for state-of-the-art ViT models on FPGAs.
Many image processing networks apply a single set of static convolutional kernels across the entire input image, which is sub-optimal for natural images, as they often consist of heterogeneous visual patterns. Recent works in classification, segmentation, and image restoration have demonstrated that dynamic kernels outperform static kernels at modeling local image statistics. However, these works often adopt per-pixel convolution kernels, which introduce high memory and computation costs. To achieve spatial-varying processing without significant overhead, we present Malleable Convolution (MalleConv), as an efficient variant of dynamic convolution. The weights of MalleConv are dynamically produced by an efficient predictor network capable of generating content-dependent outputs at specific spatial locations. Unlike previous works, MalleConv generates a much smaller set of spatially-varying kernels from input, which enlarges the network's receptive field and significantly reduces computational and memory costs. These kernels are then applied to a full-resolution feature map through an efficient slice-and-conv operator with minimum memory overhead. We further build an efficient denoising network using MalleConv, coined as MalleNet. It achieves high quality results without very deep architecture, e.g., reaching 8.91x faster speed compared to the best performed denoising algorithms (SwinIR), while maintaining similar performance. We also show that a single MalleConv added to a standard convolution-based backbone can contribute significantly to reducing the computational cost or boosting image quality at a similar cost. Project page: https://yifanjiang.net/MalleConv.html
Efficient video architecture is the key to deploying video recognition systems on devices with limited computing resources. Unfortunately, existing video architectures are often computationally intensive and not suitable for such applications. The recent X3D work presents a new family of efficient video models by expanding a hand-crafted image architecture along multiple axes, such as space, time, width, and depth. Although operating in a conceptually large space, X3D searches one axis at a time, and merely explored a small set of 30 architectures in total, which does not sufficiently explore the space. This paper bypasses existing 2D architectures, and directly searched for 3D architectures in a fine-grained space, where block type, filter number, expansion ratio and attention block are jointly searched. A probabilistic neural architecture search method is adopted to efficiently search in such a large space. Evaluations on Kinetics and Something-Something-V2 benchmarks confirm our AutoX3D models outperform existing ones in accuracy up to 1.3% under similar FLOPs, and reduce the computational cost up to x1.74 when reaching similar performance.
Due to the fast processing-speed and robustness it can achieve, skeleton-based action recognition has recently received the attention of the computer vision community. The recent Convolutional Neural Network (CNN)-based methods have shown commendable performance in learning spatio-temporal representations for skeleton sequence, which use skeleton image as input to a CNN. Since the CNN-based methods mainly encoding the temporal and skeleton joints simply as rows and columns, respectively, the latent correlation related to all joints may be lost caused by the 2D convolution. To solve this problem, we propose a novel CNN-based method with adversarial training for action recognition. We introduce a two-level domain adversarial learning to align the features of skeleton images from different view angles or subjects, respectively, thus further improve the generalization. We evaluated our proposed method on NTU RGB+D. It achieves competitive results compared with state-of-the-art methods and 2.4$\%$, 1.9$\%$ accuracy gain than the baseline for cross-subject and cross-view.
Automatic segmentation of infected regions in computed tomography (CT) images is necessary for the initial diagnosis of COVID-19. Deep-learning-based methods have the potential to automate this task but require a large amount of data with pixel-level annotations. Training a deep network with annotated lung cancer CT images, which are easier to obtain, can alleviate this problem to some extent. However, this approach may suffer from a reduction in performance when applied to unseen COVID-19 images during the testing phase due to the domain shift. In this paper, we propose a novel unsupervised method for COVID-19 infection segmentation that aims to learn the domain-invariant features from lung cancer and COVID-19 images to improve the generalization ability of the segmentation network for use with COVID-19 CT images. To overcome the intensity shift, our method first transforms annotated lung cancer data into the style of unlabeled COVID-19 data using an effective augmentation approach via a Fourier transform. Furthermore, to reduce the distribution shift, we design a teacher-student network to learn rotation-invariant features for segmentation. Experiments demonstrate that even without getting access to the annotations of COVID-19 CT during training, the proposed network can achieve a state-of-the-art segmentation performance on COVID-19 images.
Image harmonization aims to improve the quality of image compositing by matching the "appearance" (\eg, color tone, brightness and contrast) between foreground and background images. However, collecting large-scale annotated datasets for this task requires complex professional retouching. Instead, we propose a novel Self-Supervised Harmonization framework (SSH) that can be trained using just "free" natural images without being edited. We reformulate the image harmonization problem from a representation fusion perspective, which separately processes the foreground and background examples, to address the background occlusion issue. This framework design allows for a dual data augmentation method, where diverse [foreground, background, pseudo GT] triplets can be generated by cropping an image with perturbations using 3D color lookup tables (LUTs). In addition, we build a real-world harmonization dataset as carefully created by expert users, for evaluation and benchmarking purposes. Our results show that the proposed self-supervised method outperforms previous state-of-the-art methods in terms of reference metrics, visual quality, and subject user study. Code and dataset are available at \url{https://github.com/VITA-Group/SSHarmonization}.
Low-light images captured in the real world are inevitably corrupted by sensor noise. Such noise is spatially variant and highly dependent on the underlying pixel intensity, deviating from the oversimplified assumptions in conventional denoising. Existing light enhancement methods either overlook the important impact of real-world noise during enhancement, or treat noise removal as a separate pre- or post-processing step. We present Coordinated Enhancement for Real-world Low-light Noisy Images (CERL), that seamlessly integrates light enhancement and noise suppression parts into a unified and physics-grounded optimization framework. For the real low-light noise removal part, we customize a self-supervised denoising model that can easily be adapted without referring to clean ground-truth images. For the light enhancement part, we also improve the design of a state-of-the-art backbone. The two parts are then joint formulated into one principled plug-and-play optimization. Our approach is compared against state-of-the-art low-light enhancement methods both qualitatively and quantitatively. Besides standard benchmarks, we further collect and test on a new realistic low-light mobile photography dataset (RLMP), whose mobile-captured photos display heavier realistic noise than those taken by high-quality cameras. CERL consistently produces the most visually pleasing and artifact-free results across all experiments. Our RLMP dataset and codes are available at: https://github.com/VITA-Group/CERL.