Search

Token filtering to reduce irrelevant tokens prior to self-attention is a straightforward way to enable efficient vision Transformer. This is the first work to view token filtering from a feature selection perspective, where we weigh the importance of a token according to how much it can change the loss once masked. If the loss changes greatly after masking a token of interest, it means that such a token has a significant impact on the final decision and is thus relevant. Otherwise, the token is less important for the final decision, so it can be filtered out. After applying the token filtering module generalized from the whole training data, the token number fed to the self-attention module can be obviously reduced in the inference phase, leading to much fewer computations in all the subsequent self-attention layers. The token filter can be realized using a very simple network, where we utilize multi-layer perceptron. Except for the uniqueness of performing token filtering only once from the very beginning prior to self-attention, the other core feature making our method different from the other token filters lies in the predictability of token impact from a feature selection point of view. The experiments show that the proposed method provides an efficient way to approach a light weighted model after optimized with a backbone by means of fine tune, which is easy to be deployed in comparison with the existing methods based on training from scratch., Comment: 10 pages

Semantic image editing provides users with a flexible tool to modify a given image guided by a corresponding segmentation map. In this task, the features of the foreground objects and the backgrounds are quite different. However, all previous methods handle backgrounds and objects as a whole using a monolithic model. Consequently, they remain limited in processing content-rich images and suffer from generating unrealistic objects and texture-inconsistent backgrounds. To address this issue, we propose a novel paradigm, \textbf{S}emantic \textbf{I}mage \textbf{E}diting by \textbf{D}isentangling \textbf{O}bject and \textbf{B}ackground (\textbf{SIEDOB}), the core idea of which is to explicitly leverages several heterogeneous subnetworks for objects and backgrounds. First, SIEDOB disassembles the edited input into background regions and instance-level objects. Then, we feed them into the dedicated generators. Finally, all synthesized parts are embedded in their original locations and utilize a fusion network to obtain a harmonized result. Moreover, to produce high-quality edited images, we propose some innovative designs, including Semantic-Aware Self-Propagation Module, Boundary-Anchored Patch Discriminator, and Style-Diversity Object Generator, and integrate them into SIEDOB. We conduct extensive experiments on Cityscapes and ADE20K-Room datasets and exhibit that our method remarkably outperforms the baselines, especially in synthesizing realistic and diverse objects and texture-consistent backgrounds., Comment: CVPR 2023 highlight paper

Face inpainting aims at plausibly predicting missing pixels of face images within a corrupted region. Most existing methods rely on generative models learning a face image distribution from a big dataset, which produces uncontrollable results, especially with large-scale missing regions. To introduce strong control for face inpainting, we propose a novel reference-guided face inpainting method that fills the large-scale missing region with identity and texture control guided by a reference face image. However, generating high-quality results under imposing two control signals is challenging. To tackle such difficulty, we propose a dual control one-stage framework that decouples the reference image into two levels for flexible control: High-level identity information and low-level texture information, where the identity information figures out the shape of the face and the texture information depicts the component-aware texture. To synthesize high-quality results, we design two novel modules referred to as Half-AdaIN and Component-Wise Style Injector (CWSI) to inject the two kinds of control information into the inpainting processing. Our method produces realistic results with identity and texture control faithful to reference images. To the best of our knowledge, it is the first work to concurrently apply identity and component-level controls in face inpainting to promise more precise and controllable results. Code is available at https://github.com/WuyangLuo/RefFaceInpainting, Comment: accepted by IEEE Transactions on Circuits and Systems for Video Technology

Semantic image editing utilizes local semantic label maps to generate the desired content in the edited region. A recent work borrows SPADE block to achieve semantic image editing. However, it cannot produce pleasing results due to style discrepancy between the edited region and surrounding pixels. We attribute this to the fact that SPADE only uses an image-independent local semantic layout but ignores the image-specific styles included in the known pixels. To address this issue, we propose a style-preserved modulation (SPM) comprising two modulations processes: The first modulation incorporates the contextual style and semantic layout, and then generates two fused modulation parameters. The second modulation employs the fused parameters to modulate feature maps. By using such two modulations, SPM can inject the given semantic layout while preserving the image-specific context style. Moreover, we design a progressive architecture for generating the edited content in a coarse-to-fine manner. The proposed method can obtain context-consistent results and significantly alleviate the unpleasant boundary between the generated regions and the known pixels., Comment: ECCV 2022

Non-contact facial video-based heart rate estimation using remote photoplethysmography (rPPG) has shown great potential in many applications (e.g., remote health care) and achieved creditable results in constrained scenarios. However, practical applications require results to be accurate even under complex environment with head movement and unstable illumination. Therefore, improving the performance of rPPG in complex environment has become a key challenge. In this paper, we propose a novel video embedding method that embeds each facial video sequence into a feature map referred to as Multi-scale Adaptive Spatial and Temporal Map with Overlap (MAST_Mop), which contains not only vital information but also surrounding information as reference, which acts as the mirror to figure out the homogeneous perturbations imposed on foreground and background simultaneously, such as illumination instability. Correspondingly, we propose a two-stream Transformer model to map the MAST_Mop into heart rate (HR), where one stream follows the pulse signal in the facial area while the other figures out the perturbation signal from the surrounding region such that the difference of the two channels leads to adaptive noise cancellation. Our approach significantly outperforms all current state-of-the-art methods on two public datasets MAHNOB-HCI and VIPL-HR. As far as we know, it is the first work with Transformer as backbone to capture the temporal dependencies in rPPGs and apply the two stream scheme to figure out the interference from backgrounds as mirror of the corresponding perturbation on foreground signals for noise tolerating.

Video anomaly detection is a challenging task because of diverse abnormal events. To this task, methods based on reconstruction and prediction are wildly used in recent works, which are built on the assumption that learning on normal data, anomalies cannot be reconstructed or predicated as good as normal patterns, namely the anomaly result with more errors. In this paper, we propose to discriminate anomalies from normal ones by the duality of normality-granted optical flow, which is conducive to predict normal frames but adverse to abnormal frames. The normality-granted optical flow is predicted from a single frame, to keep the motion knowledge focused on normal patterns. Meanwhile, We extend the appearance-motion correspondence scheme from frame reconstruction to prediction, which not only helps to learn the knowledge about object appearances and correlated motion, but also meets the fact that motion is the transformation between appearances. We also introduce a margin loss to enhance the learning of frame prediction. Experiments on standard benchmark datasets demonstrate the impressive performance of our approach.

Predicting risk map of traffic accidents is vital for accident prevention and early planning of emergency response. Here, the challenge lies in the multimodal nature of urban big data. We propose a compact neural ensemble model to alleviate overfitting in fusing multimodal features and develop some new features such as fractal measure of road complexity in satellite images, taxi flows, POIs, and road width and connectivity in OpenStreetMap. The solution is more promising in performance than the baseline methods and the single-modality data based solutions. After visualization from a micro view, the visual patterns of the scenes related to high and low risk are revealed, providing lessons for future road design. From city point of view, the predicted risk map is close to the ground truth, and can act as the base in optimizing spatial configuration of resources for emergency response, and alarming signs. To the best of our knowledge, it is the first work to fuse visual and spatio-temporal features in traffic accident prediction while advances to bridge the gap between data mining based urban computing and computer vision based urban perception.

In crowded scenes, detection and localization of abnormal behaviors is challenging in that high-density people make object segmentation and tracking extremely difficult. We associate the optical flows of multiple frames to capture short-term trajectories and introduce the histogram-based shape descriptor referred to as shape contexts to describe such short-term trajectories. Furthermore, we propose a K-NN similarity-based statistical model to detect anomalies over time and space, which is an unsupervised one-class learning algorithm requiring no clustering nor any prior assumption. Firstly, we retrieve the K-NN samples from the training set in regard to the testing sample, and then use the similarities between every pair of the K-NN samples to construct a Gaussian model. Finally, the probabilities of the similarities from the testing sample to the K-NN samples under the Gaussian model are calculated in the form of a joint probability. Abnormal events can be detected by judging whether the joint probability is below predefined thresholds in terms of time and space, separately. Such a scheme can adapt to the whole scene, since the probability computed as such is not affected by motion distortions arising from perspective distortion. We conduct experiments on real-world surveillance videos, and the results demonstrate that the proposed method can reliably detect and locate the abnormal events in the video sequences, outperforming the state-of-the-art approaches.

Recently, there is a rising interest in perceiving image aesthetics. The existing works deal with image aesthetics as a classification or regression problem. To extend the cognition from rating to reasoning, a deeper understanding of aesthetics should be based on revealing why a high- or low-aesthetic score should be assigned to an image. From such a point of view, we propose a model referred to as Neural Aesthetic Image Reviewer, which can not only give an aesthetic score for an image, but also generate a textual description explaining why the image leads to a plausible rating score. Specifically, we propose two multi-task architectures based on shared aesthetically semantic layers and task-specific embedding layers at a high level for performance improvement on different tasks. To facilitate researches on this problem, we collect the AVA-Reviews dataset, which contains 52,118 images and 312,708 comments in total. Through multi-task learning, the proposed models can rate aesthetic images as well as produce comments in an end-to-end manner. It is confirmed that the proposed models outperform the baselines according to the performance evaluation on the AVA-Reviews dataset. Moreover, we demonstrate experimentally that our model can generate textual reviews related to aesthetics, which are consistent with human perception., Comment: 8 pages, 13 figures