Stepwise Weighted Spike Coding for Deep Spiking Neural Networks

Spiking Neural Networks (SNNs) seek to mimic the spiking behavior of biological neurons and are expected to play a key role in the advancement of neural computing and artificial intelligence. The efficiency of SNNs is often determined by the neural coding schemes. Existing coding schemes either cause huge delays and energy consumption or necessitate intricate neuron models and training techniques. To address these issues, we propose a novel Stepwise Weighted Spike (SWS) coding scheme to enhance the encoding of information in spikes. This approach compresses the spikes by weighting the significance of the spike in each step of neural computation, achieving high performance and low energy consumption. A Ternary Self-Amplifying (TSA) neuron model with a silent period is proposed for supporting SWS-based computing, aimed at minimizing the residual error resulting from stepwise weighting in neural computation. Our experimental results show that the SWS coding scheme outperforms the existing neural coding schemes in very deep SNNs, and significantly reduces operations and latency.

Thermal Infrared Image Inpainting via Edge-Aware Guidance

Image inpainting has achieved fundamental advances with deep learning. However, almost all existing inpainting methods aim to process natural images, while few target Thermal Infrared (TIR) images, which have widespread applications. When applied to TIR images, conventional inpainting methods usually generate distorted or blurry content. In this paper, we propose a novel task -- Thermal Infrared Image Inpainting, which aims to reconstruct missing regions of TIR images. Crucially, we propose a novel deep-learning-based model TIR-Fill. We adopt the edge generator to complete the canny edges of broken TIR images. The completed edges are projected to the normalization weights and biases to enhance edge awareness of the model. In addition, a refinement network based on gated convolution is employed to improve TIR image consistency. The experiments demonstrate that our method outperforms state-of-the-art image inpainting approaches on FLIR thermal dataset.

FDA-GAN: Flow-based Dual Attention GAN for Human Pose Transfer

Human pose transfer aims at transferring the appearance of the source person to the target pose. Existing methods utilizing flow-based warping for non-rigid human image generation have achieved great success. However, they fail to preserve the appearance details in synthesized images since the spatial correlation between the source and target is not fully exploited. To this end, we propose the Flow-based Dual Attention GAN (FDA-GAN) to apply occlusion- and deformation-aware feature fusion for higher generation quality. Specifically, deformable local attention and flow similarity attention, constituting the dual attention mechanism, can derive the output features responsible for deformable- and occlusion-aware fusion, respectively. Besides, to maintain the pose and global position consistency in transferring, we design a pose normalization network for learning adaptive normalization from the target pose to the source person. Both qualitative and quantitative results show that our method outperforms state-of-the-art models in public iPER and DeepFashion datasets.

GLocal: Global Graph Reasoning and Local Structure Transfer for Person Image Generation

In this paper, we focus on person image generation, namely, generating person image under various conditions, e.g., corrupted texture or different pose. To address texture occlusion and large pose misalignment in this task, previous works just use the corresponding region's style to infer the occluded area and rely on point-wise alignment to reorganize the context texture information, lacking the ability to globally correlate the region-wise style codes and preserve the local structure of the source. To tackle these problems, we present a GLocal framework to improve the occlusion-aware texture estimation by globally reasoning the style inter-correlations among different semantic regions, which can also be employed to recover the corrupted images in texture inpainting. For local structural information preservation, we further extract the local structure of the source image and regain it in the generated image via local structure transfer. We benchmark our method to fully characterize its performance on DeepFashion dataset and present extensive ablation studies that highlight the novelty of our method.

An Ultra Fast Low Power Convolutional Neural Network Image Sensor with Pixel-level Computing

The separation of the data capture and analysis in modern vision systems has led to a massive amount of data transfer between the end devices and cloud computers, resulting in long latency, slow response, and high power consumption. Efficient hardware architectures are under focused development to enable Artificial Intelligence (AI) at the resource-limited end sensing devices. This paper proposes a Processing-In-Pixel (PIP) CMOS sensor architecture, which allows convolution operation before the column readout circuit to significantly improve the image reading speed with much lower power consumption. The simulation results show that the proposed architecture enables convolution operation (kernel size=3*3, stride=2, input channel=3, output channel=64) in a 1080P image sensor array with only 22.62 mW power consumption. In other words, the computational efficiency is 4.75 TOPS/w, which is about 3.6 times as higher as the state-of-the-art.

C2F-FWN: Coarse-to-Fine Flow Warping Network for Spatial-Temporal Consistent Motion Transfer

Human video motion transfer (HVMT) aims to synthesize videos that one person imitates other persons' actions. Although existing GAN-based HVMT methods have achieved great success, they either fail to preserve appearance details due to the loss of spatial consistency between synthesized and exemplary images, or generate incoherent video results due to the lack of temporal consistency among video frames. In this paper, we propose Coarse-to-Fine Flow Warping Network (C2F-FWN) for spatial-temporal consistent HVMT. Particularly, C2F-FWN utilizes coarse-to-fine flow warping and Layout-Constrained Deformable Convolution (LC-DConv) to improve spatial consistency, and employs Flow Temporal Consistency (FTC) Loss to enhance temporal consistency. In addition, provided with multi-source appearance inputs, C2F-FWN can support appearance attribute editing with great flexibility and efficiency. Besides public datasets, we also collected a large-scale HVMT dataset named SoloDance for evaluation. Extensive experiments conducted on our SoloDance dataset and the iPER dataset show that our approach outperforms state-of-art HVMT methods in terms of both spatial and temporal consistency. Source code and the SoloDance dataset are available at https://github.com/wswdx/C2F-FWN.

A Foreground-background Parallel Compression with Residual Encoding for Surveillance Video

The data storage has been one of the bottlenecks in surveillance systems. The conventional video compression algorithms such as H.264 and H.265 do not fully utilize the low information density characteristic of the surveillance video. In this paper, we propose a video compression method that extracts and compresses the foreground and background of the video separately. The compression ratio is greatly improved by sharing background information among multiple adjacent frames through an adaptive background updating and interpolation module. Besides, we present two different schemes to compress the foreground and compare their performance in the ablation study to show the importance of temporal information for video compression. In the decoding end, a coarse-to-fine two-stage module is applied to achieve the composition of the foreground and background and the enhancements of frame quality. Furthermore, an adaptive sampling method for surveillance cameras is proposed, and we have shown its effects through software simulation. The experimental results show that our proposed method requires 69.5% less bpp (bits per pixel) than the conventional algorithm H.265 to achieve the same PSNR (36 dB) on the HECV dataset.

A GAN-based Tunable Image Compression System

The method of importance map has been widely adopted in DNN-based lossy image compression to achieve bit allocation according to the importance of image contents. However, insufficient allocation of bits in non-important regions often leads to severe distortion at low bpp (bits per pixel), which hampers the development of efficient content-weighted image compression systems. This paper rethinks content-based compression by using Generative Adversarial Network (GAN) to reconstruct the non-important regions. Moreover, multiscale pyramid decomposition is applied to both the encoder and the discriminator to achieve global compression of high-resolution images. A tunable compression scheme is also proposed in this paper to compress an image to any specific compression ratio without retraining the model. The experimental results show that our proposed method improves MS-SSIM by more than 10.3% compared to the recently reported GAN-based method to achieve the same low bpp (0.05) on the Kodak dataset.

Appearance Composing GAN: A General Method for Appearance-Controllable Human Video Motion Transfer

Due to the rapid development of GANs, there has been significant progress in the field of human video motion transfer which has a wide range of applications in computer vision and graphics. However, existing works only support motion-controllable video synthesis while appearances of different video components are bound together and uncontrollable, which means one person can only appear with the same clothing and background. Besides, most of these works are person-specific and require to train an individual model for each person, which is inflexible and inefficient. Therefore, we propose appearance composing GAN: a general method enabling control over not only human motions but also video appearances for arbitrary human subjects within only one model. The key idea is to exert layout-level appearance control on different video components and fuse them to compose the desired full video scene. Specifically, we achieve such appearance control by providing our model with optimal appearance conditioning inputs obtained separately for each component, allowing controllable component appearance synthesis for different people by changing the input appearance conditions accordingly. In terms of synthesis, a two-stage GAN framework is proposed to sequentially generate the desired body semantic layouts and component appearances, both are consistent with the input human motions and appearance conditions. Coupled with our ACGAN loss and background modulation block, the proposed method can achieve general and appearance-controllable human video motion transfer. Moreover, we build a dataset containing a large number of dance videos for training and evaluation. Experimental results show that, when applied to motion transfer tasks involving a variety of human subjects, our proposed method achieves appearance-controllable synthesis with higher video quality than state-of-arts based on only one-time training.