Text-conditioned image editing is a recently emerged and highly practical task, and its potential is immeasurable. However, most of the concurrent methods are unable to perform action editing, i.e. they can not produc...
详细信息
Learning-based methods have attracted a lot of research attention and led to significant improvements in low-light image enhancement. However, most of them still suffer from two main problems: expensive computational ...
详细信息
In recent years, face recognition systems have faced increasingly security threats, making it essential to employ Face Anti-spoofing (FAS) to protect against various types of attacks in traditional scenarios like phon...
In recent years, face recognition systems have faced increasingly security threats, making it essential to employ Face Anti-spoofing (FAS) to protect against various types of attacks in traditional scenarios like phone unlocking, face payment and self-service security inspection. However, further exploration is required to fully secure FAS in long-distance settings. In this paper, we propose two contributions to enhance the security of face recognition systems: Dynamic Feature Queue (DFQ) and Progressive Training Strategy (PTS). DFQ converts the conventional binary classification task into a multi-classification task. It treats live samples as a closed set and attack samples as an open set by using a dynamic queue that stores the features of spoofing samples and updates them. On the other hand, PTS targets difficult samples and iteratively adds them in batches for training. The proposed PTS divides the entire training set into blocks, trains only a small portion of the data, and gradually increases the training data with each stage while also incorporating low-scoring positive samples and high-scoring spoof samples from the test set. These two contributions complement each other by enhancing the model’s ability to generalize and defend against various types of attacks, making the face recognition system more secure and reliable. Our proposed methods have achieved top performance on ACER metric with 4.73% on the SuHiFiMask dataset [11] and won the first prize in Surveillance Face Anti-spoofing track of the Challenge@CVPR 2023.
It is a challenging task to learn rich and multi-scale spatiotemporal semantics from high-dimensional videos, due to large local redundancy and complex global dependency between video frames. The recent advances in th...
详细信息
Photomosaic images are composite images composed of many small images called *** its overall visual effect,a photomosaic image is similar to the target image,and photomosaics are also called“montage art”.Noisy block...
详细信息
Photomosaic images are composite images composed of many small images called *** its overall visual effect,a photomosaic image is similar to the target image,and photomosaics are also called“montage art”.Noisy blocks and the loss of local information are the major obstacles in most methods or programs that create photomosaic *** solve these problems and generate a photomosaic image in this study,we propose a tile selection method based on error minimization.A photomosaic image can be generated by partitioning the target image in a rectangular pattern,selecting appropriate tile images,and then adding them with a weight *** on the principles of montage art,the quality of the generated photomosaic image can be evaluated by both global and local *** the proposed framework,via an error function analysis,the results show that selecting a tile image using a global minimum distance minimizes both the global error and the local error ***,the weight coefficient of the image superposition can be used to adjust the ratio of the global and local ***,to verify the proposed method,we built a new photomosaic creation dataset during this *** experimental results show that the proposed method achieves a low mean absolute error and that the generated photomosaic images have a more artistic effect than do the existing approaches.
Self-supervised pretraining has achieved remarkable success in high-level vision, but its application in low-level vision remains ambiguous and not well-established. What is the primitive intention of pretraining? Wha...
Self-supervised pretraining has achieved remarkable success in high-level vision, but its application in low-level vision remains ambiguous and not well-established. What is the primitive intention of pretraining? What is the core problem of pretraining in low-level vision? In this paper, we aim to answer these essential questions and establish a new pretraining scheme for low-level vision. Specifically, we examine previous pretraining methods in both high-level and low-level vision, and categorize current low-level vision tasks into two groups based on the difficulty of data acqui-sition: low-cost and high-cost tasks. Existing literature has mainly focused on pretraining for low-cost tasks, where the observed performance improvement is often limited. However, we argue that pretraining is more significant for high-cost tasks, where data acquisition is more challenging. To learn a general low-level vision representation that can improve the performance of various tasks, we propose a new pretraining paradigm called degradation autoencoder (De-gAE). DegAE follows the philosophy of designing pretext task for self-supervised pretraining and is elaborately tai-lored to low-level vision. With DegAE pretraining, SwinIR achieves a 6.88dB performance gain on image dehaze task, while Uformer obtains 3.22dB and 0.54dB improvement on dehaze and derain tasks, respectively.
Remote photoplethysmography (rPPG) aims to measure non-contact physiological signals from facial videos, which has shown great potential in many applications. Most existing methods directly extract video-based rPPG fe...
详细信息
Transformer-based methods have shown impressive performance in low-level vision tasks, such as image super-resolution. However, we find that these networks can only utilize a limited spatial range of input information...
Transformer-based methods have shown impressive performance in low-level vision tasks, such as image super-resolution. However, we find that these networks can only utilize a limited spatial range of input information through attribution analysis. This implies that the potential of Transformer is still not fully exploited in existing networks. In order to activate more input pixels for better reconstruction, we propose a novel Hybrid Attention Transformer (HAT). It combines both channel attention and window-based self-attention schemes, thus making use of their complementary advantages of being able to utilize global statistics and strong local fitting capability. Moreover, to better aggregate the cross-window information, we introduce an overlapping cross-attention module to enhance the interaction between neighboring window features. In the training stage, we additionally adopt a same-task pre-training strategy to exploit the potential of the model for further improvement. Extensive experiments show the effectiveness of the proposed modules, and we further scale up the model to demonstrate that the performance of this task can be greatly improved. Our overall method significantly outperforms the state-of-the-art methods by more than 1dB.
Latest diffusion-based methods for many image restoration tasks outperform traditional models, but they encounter the long-time inference problem. To tackle it, this paper proposes a Wavelet-Based Diffusion Model (Wav...
详细信息
Despite recent advancements in text-to-image generation, most existing methods struggle to create images with multiple objects and complex spatial relationships in the 3D world. To tackle this limitation, we introduce...
详细信息
暂无评论