Jiale Zhang

Jiale Zhang, Yulun Zhang, Jinjin Gu et al. · eth-zurich

Recently, Transformer-based image restoration networks have achieved promising improvements over convolutional neural networks due to parameter-independent global interactions. To lower computational cost, existing works generally limit self-attention computation within non-overlapping windows. However, each group of tokens are always from a dense area of the image. This is considered as a dense attention strategy since the interactions of tokens are restrained in dense regions. Obviously, this strategy could result in restricted receptive fields. To address this issue, we propose Attention Retractable Transformer (ART) for image restoration, which presents both dense and sparse attention modules in the network. The sparse attention module allows tokens from sparse areas to interact and thus provides a wider receptive field. Furthermore, the alternating application of dense and sparse attention modules greatly enhances representation ability of Transformer while providing retractable attention on the input image.We conduct extensive experiments on image super-resolution, denoising, and JPEG compression artifact reduction tasks. Experimental results validate that our proposed ART outperforms state-of-the-art methods on various benchmark datasets both quantitatively and visually. We also provide code and models at https://github.com/gladzhang/ART.

Jiale Zhang, Yulun Zhang, Jinjin Gu et al. · eth-zurich

In this paper, we present a hybrid X-shaped vision Transformer, named Xformer, which performs notably on image denoising tasks. We explore strengthening the global representation of tokens from different scopes. In detail, we adopt two types of Transformer blocks. The spatial-wise Transformer block performs fine-grained local patches interactions across tokens defined by spatial dimension. The channel-wise Transformer block performs direct global context interactions across tokens defined by channel dimension. Based on the concurrent network structure, we design two branches to conduct these two interaction fashions. Within each branch, we employ an encoder-decoder architecture to capture multi-scale features. Besides, we propose the Bidirectional Connection Unit (BCU) to couple the learned representations from these two branches while providing enhanced information fusion. The joint designs make our Xformer powerful to conduct global information modeling in both spatial and channel dimensions. Extensive experiments show that Xformer, under the comparable model complexity, achieves state-of-the-art performance on the synthetic and real-world image denoising tasks. We also provide code and models at https://github.com/gladzhang/Xformer.

Zhiyu Pan, Yinpeng Chen, Jiale Zhang et al.

Automatic image cropping algorithms aim to recompose images like human-being photographers by generating the cropping boxes with improved composition quality. Cropping box regression approaches learn the beauty of composition from annotated cropping boxes. However, the bias of annotations leads to quasi-trivial recomposing results, which has an obvious tendency to the average location of training samples. The crux of this predicament is that the task is naively treated as a box regression problem, where rare samples might be dominated by normal samples, and the composition patterns of rare samples are not well exploited. Observing that similar composition patterns tend to be shared by the cropping boundaries annotated nearly, we argue to find the beauty of composition from the rare samples by clustering the samples with similar cropping boundary annotations, ie, similar composition patterns. We propose a novel Contrastive Composition Clustering (C2C) to regularize the composition features by contrasting dynamically established similar and dissimilar pairs. In this way, common composition patterns of multiple images can be better summarized, which especially benefits the rare samples and endows our model with better generalizability to render nontrivial results. Extensive experimental results show the superiority of our model compared with prior arts. We also illustrate the philosophy of our design with an interesting analytical visualization.

Jiale Zhang, Wenfeng Huang, Xiangyun Liao et al.

Laparoscopic surgery offers minimally invasive procedures with better patient outcomes, but smoke presence challenges visibility and safety. Existing learning-based methods demand large datasets and high computational resources. We propose the Progressive Frequency-Aware Network (PFAN), a lightweight GAN framework for laparoscopic image desmoking, combining the strengths of CNN and Transformer for progressive information extraction in the frequency domain. PFAN features CNN-based Multi-scale Bottleneck-Inverting (MBI) Blocks for capturing local high-frequency information and Locally-Enhanced Axial Attention Transformers (LAT) for efficiently handling global low-frequency information. PFAN efficiently desmokes laparoscopic images even with limited training data. Our method outperforms state-of-the-art approaches in PSNR, SSIM, CIEDE2000, and visual quality on the Cholec80 dataset and retains only 629K parameters. Our code and models are made publicly available at: https://github.com/jlzcode/PFAN.

Hao Sui, Bing Chen, Jiale Zhang et al.

Recent studies have revealed that GNNs are highly susceptible to multiple adversarial attacks. Among these, graph backdoor attacks pose one of the most prominent threats, where attackers cause models to misclassify by learning the backdoored features with injected triggers and modified target labels during the training phase. Based on the features of the triggers, these attacks can be categorized into out-of-distribution (OOD) and in-distribution (ID) graph backdoor attacks, triggers with notable differences from the clean sample feature distributions constitute OOD backdoor attacks, whereas the triggers in ID backdoor attacks are nearly identical to the clean sample feature distributions. Existing methods can successfully defend against OOD backdoor attacks by comparing the feature distribution of triggers and clean samples but fail to mitigate stealthy ID backdoor attacks. Due to the lack of proper supervision signals, the main task accuracy is negatively affected in defending against ID backdoor attacks. To bridge this gap, we propose DMGNN against OOD and ID graph backdoor attacks that can powerfully eliminate stealthiness to guarantee defense effectiveness and improve the model performance. Specifically, DMGNN can easily identify the hidden ID and OOD triggers via predicting label transitions based on counterfactual explanation. To further filter the diversity of generated explainable graphs and erase the influence of the trigger features, we present a reverse sampling pruning method to screen and discard the triggers directly on the data level. Extensive experimental evaluations on open graph datasets demonstrate that DMGNN far outperforms the state-of-the-art (SOTA) defense methods, reducing the attack success rate to 5% with almost negligible degradation in model performance (within 3.5%).

Jiale Zhang, Qianxi Jia, Yang Liu et al.

Stereo video conversion aims to transform monocular videos into immersive stereo format. Despite the advancements in novel view synthesis, it still remains two major challenges: i) difficulty of achieving high-fidelity and stable results, and ii) insufficiency of high-quality stereo video data. In this paper, we introduce SpatialMe, a novel stereo video conversion framework based on depth-warping and blend-inpainting. Specifically, we propose a mask-based hierarchy feature update (MHFU) refiner, which integrate and refine the outputs from designed multi-branch inpainting module, using feature update unit (FUU) and mask mechanism. We also propose a disparity expansion strategy to address the problem of foreground bleeding. Furthermore, we conduct a high-quality real-world stereo video dataset -- StereoV1K, to alleviate the data shortage. It contains 1000 stereo videos captured in real-world at a resolution of 1180 x 1180, covering various indoor and outdoor scenes. Extensive experiments demonstrate the superiority of our approach in generating stereo videos over state-of-the-art methods.

David Wang, Derek Goh, Jiale Zhang

Cashierless stores rely on computer vision and RFID tags to associate shoppers with items, but concealed items placed in backpacks, pockets, or bags create challenges for theft prevention. We introduce a system that turns existing RFID tagged items into material sensors by exploiting how different containers attenuate and scatter RF signals. Using RSSI and phase angle, we trained a neural network to classify seven common containers. In a simulated retail environment, the model achieves 89% accuracy with one second samples and 74% accuracy from single reads. Incorporating distance measurements, our system achieves 82% accuracy across 0.3-2m tag to reader separations. When deployed at aisle or doorway choke points, the system can flag suspicious events in real time, prompting camera screening or staff intervention. By combining material identification with computer vision tracking, our system provides proactive loss prevention for cashierless retail while utilizing existing infrastructure.

Yen Cheng Chang, Jesse Codling, Yiwen Dong et al.

Crowd monitoring in sports stadiums is important to enhance public safety and improve the audience experience. Existing approaches mainly rely on cameras and microphones, which can cause significant disturbances and often raise privacy concerns. In this paper, we sense floor vibration, which provides a less disruptive and more non-intrusive way of crowd sensing, to predict crowd behavior. However, since the vibration-based crowd monitoring approach is newly developed, one main challenge is the lack of training data due to sports stadiums being large public spaces with complex physical activities. In this paper, we present ViLA (Vibration Leverage Audio), a vibration-based method that reduces the dependency on labeled data by pre-training with unlabeled cross-modality data. ViLA is first pre-trained on audio data in an unsupervised manner and then fine-tuned with a minimal amount of in-domain vibration data. By leveraging publicly available audio datasets, ViLA learns the wave behaviors from audio and then adapts the representation to vibration, reducing the reliance on domain-specific vibration data. Our real-world experiments demonstrate that pre-training the vibration model using publicly available audio data (YouTube8M) achieved up to a 5.8x error reduction compared to the model without audio pre-training.