22 June 2022 in IEEE Transactions on Neural Networks and Learning Systems
Backdoor attack intends to embed hidden backdoors into deep neural networks (DNNs), so that the attacked models perform well on benign samples, whereas their predictions will be maliciously changed if the hidden backdoor is activated by attacker-specified triggers. This threat could happen when the training process is not fully controlled, such as training on third-party datasets or adopting third-party models, which poses a new and realistic threat. Although backdoor learning is an emerging and rapidly growing research area, there is still no comprehensive and timely review of it. In this article, we present the first comprehensive survey of this realm. We summarize and categorize existing backdoor attacks and defenses based on their characteristics, and provide a unified framework for analyzing poisoning-based backdoor attacks. Besides, we also analyze the relation between backdoor attacks and relevant fields (i.e., adversarial attacks and data poisoning), and summarize widely adopted benchmark datasets. Finally, we briefly outline certain future research directions relying upon reviewed works. A curated list of backdoor-related resources is also available at https://github.com/THUYimingLi/backdoor-learning-resources.
8 March 2022 in IEEE Transactions on Image Processing
Image inpainting has made remarkable progress with recent advances in deep learning. Popular networks mainly follow an encoder-decoder architecture (sometimes with skip connections) and possess sufficiently large receptive field, i.e. , larger than the image resolution. The receptive field refers to the set of input pixels that are path-connected to a neuron. For image inpainting task, however, the size of surrounding areas needed to repair different kinds of missing regions are different, and the very large receptive field is not always optimal, especially for the local structures and textures. In addition, a large receptive field tends to involve more undesired completion results, which will disturb the inpainting process. Based on these insights, we rethink the process of image inpainting from a different perspective of receptive field, and propose a novel three-stage inpainting framework with local and global refinement. Specifically, we first utilize an encoder-decoder network with skip connection to achieve coarse initial results. Then, we introduce a shallow deep model with small receptive field to conduct the local refinement, which can also weaken the influence of distant undesired completion results. Finally, we propose an attention-based encoder-decoder network with large receptive field to conduct the global refinement. Experimental results demonstrate that our method outperforms the state of the arts on three popular publicly available datasets for image inpainting. Our local and global refinement network can be directly inserted into the end of any existing networks to further improve their inpainting performance. Code is available at https://github.com/weizequan/LGNet.git .
26 July 2021 in IEEE Transactions on Pattern Analysis and Machine Intelligence
With the recent advancement of deep convolutional neural networks, significant progress has been made in general face recognition. However, the state-of-the-art general face recognition models do not generalize well to occluded face images, which are exactly the common cases in real-world scenarios. The potential reasons are the absences of large-scale occluded face data for training and specific designs for tackling corrupted features brought by occlusions. This paper presents a novel face recognition method that is robust to occlusions based on a single end-to-end deep neural network. Our approach, named FROM (Face Recognition with Occlusion Masks), learns to discover the corrupted features from the deep convolutional neural networks, and clean them by the dynamically learned masks. In addition, we construct massive occluded face images to train FROM effectively and efficiently. FROM is simple yet powerful compared to the existing methods that either rely on external detectors to discover the occlusions or employ shallow models which are less discriminative. Experimental results on the LFW, Megaface challenge 1, RMF2, AR dataset and other simulated occluded/masked datasets confirm that FROM dramatically improves the accuracy under occlusions, and generalizes well on general face recognition.
10 January 2017 in IEEE Transactions on Image Processing
Heterogeneous face recognition is an important, yet challenging problem in face recognition community. It refers to matching a probe face image to a gallery of face images taken from alternate imaging modality. The major challenge of heterogeneous face recognition lies in the great discrepancies between different image modalities. Conventional face feature descriptors, e.g., local binary patterns, histogram of oriented gradients, and scale-invariant feature transform, are mostly designed in a handcrafted way and thus generally fail to extract the common discriminant information from the heterogeneous face images. In this paper, we propose a new feature descriptor called common encoding model for heterogeneous face recognition, which is able to capture common discriminant information, such that the large modality gap can be significantly reduced at the feature extraction stage. Specifically, we turn a face image into an encoded one with the encoding model learned from the training data, where the difference of the encoded heterogeneous face images of the same person can be minimized. Based on the encoded face images, we further develop a discriminant matching method to infer the hidden identity information of the cross-modality face images for enhanced recognition performance. The effectiveness of the proposed approach is demonstrated (on several public-domain face datasets) in two typical heterogeneous face recognition scenarios: matching NIR faces to VIS faces and matching sketches to photographs.