Yang Zhao

Xiaopei Wu, Yang Zhao, Liang Peng et al.

Current 3D object detection methods heavily rely on an enormous amount of annotations. Semi-supervised learning can be used to alleviate this issue. Previous semi-supervised 3D object detection methods directly follow the practice of fully-supervised methods to augment labeled and unlabeled data, which is sub-optimal. In this paper, we design a data augmentation method for semi-supervised learning, which we call Semi-Sampling. Specifically, we use ground truth labels and pseudo labels to crop gt samples and pseudo samples on labeled frames and unlabeled frames, respectively. Then we can generate a gt sample database and a pseudo sample database. When training a teacher-student semi-supervised framework, we randomly select gt samples and pseudo samples to both labeled frames and unlabeled frames, making a strong data augmentation for them. Our semi-sampling can be regarded as an extension of gt-sampling to semi-supervised learning. Our method is simple but effective. We consistently improve state-of-the-art methods on ScanNet, SUN-RGBD, and KITTI benchmarks by large margins. For example, when training using only 10% labeled data on ScanNet, we achieve 3.1 mAP and 6.4 mAP improvement upon 3DIoUMatch in terms of mAP@0.25 and mAP@0.5. When training using only 1% labeled data on KITTI, we boost 3DIoUMatch by 3.5 mAP, 6.7 mAP and 14.1 mAP on car, pedestrian and cyclist classes. Codes will be made publicly available at https://github.com/LittlePey/Semi-Sampling.

Yang Zhao, Jiaxi Yang, Wenbo Wang et al.

Industrial systems demand reliable predictive maintenance strategies to enhance operational efficiency and reduce downtime. This paper introduces an integrated framework that leverages the capabilities of the Transformer model-based neural networks and deep reinforcement learning (DRL) algorithms to optimize system maintenance actions. Our approach employs the Transformer model to effectively capture complex temporal patterns in sensor data, thereby accurately predicting the remaining useful life (RUL) of an equipment. Additionally, the DRL component of our framework provides cost-effective and timely maintenance recommendations. We validate the efficacy of our framework on the NASA C-MPASS dataset, where it demonstrates significant advancements in both RUL prediction accuracy and the optimization of maintenance actions, compared to the other prevalent machine learning-based methods. Our proposed approach provides an innovative data-driven framework for industry machine systems, accurately forecasting equipment lifespans and optimizing maintenance schedules, thereby reducing downtime and cutting costs.

Haoran You, Zhanyi Sun, Huihong Shi et al.

Vision Transformers (ViTs) have achieved state-of-the-art performance on various vision tasks. However, ViTs' self-attention module is still arguably a major bottleneck, limiting their achievable hardware efficiency. Meanwhile, existing accelerators dedicated to NLP Transformers are not optimal for ViTs. This is because there is a large difference between ViTs and NLP Transformers: ViTs have a relatively fixed number of input tokens, whose attention maps can be pruned by up to 90% even with fixed sparse patterns; while NLP Transformers need to handle input sequences of varying numbers of tokens and rely on on-the-fly predictions of dynamic sparse attention patterns for each input to achieve a decent sparsity (e.g., >=50%). To this end, we propose a dedicated algorithm and accelerator co-design framework dubbed ViTCoD for accelerating ViTs. Specifically, on the algorithm level, ViTCoD prunes and polarizes the attention maps to have either denser or sparser fixed patterns for regularizing two levels of workloads without hurting the accuracy, largely reducing the attention computations while leaving room for alleviating the remaining dominant data movements; on top of that, we further integrate a lightweight and learnable auto-encoder module to enable trading the dominant high-cost data movements for lower-cost computations. On the hardware level, we develop a dedicated accelerator to simultaneously coordinate the enforced denser/sparser workloads and encoder/decoder engines for boosted hardware utilization. Extensive experiments and ablation studies validate that ViTCoD largely reduces the dominant data movement costs, achieving speedups of up to 235.3x, 142.9x, 86.0x, 10.1x, and 6.8x over general computing platforms CPUs, EdgeGPUs, GPUs, and prior-art Transformer accelerators SpAtten and Sanger under an attention sparsity of 90%, respectively.

Yang Zhao, Yanwu Xu, Zhisheng Xiao et al.

The deployment of large-scale text-to-image diffusion models on mobile devices is impeded by their substantial model size and slow inference speed. In this paper, we propose \textbf{MobileDiffusion}, a highly efficient text-to-image diffusion model obtained through extensive optimizations in both architecture and sampling techniques. We conduct a comprehensive examination of model architecture design to reduce redundancy, enhance computational efficiency, and minimize model's parameter count, while preserving image generation quality. Additionally, we employ distillation and diffusion-GAN finetuning techniques on MobileDiffusion to achieve 8-step and 1-step inference respectively. Empirical studies, conducted both quantitatively and qualitatively, demonstrate the effectiveness of our proposed techniques. MobileDiffusion achieves a remarkable \textbf{sub-second} inference speed for generating a $512\times512$ image on mobile devices, establishing a new state of the art.

Zhichao Zuo, Zhao Zhang, Yan Luo et al.

This paper presents a novel framework termed Cut-and-Paste for real-word semantic video editing under the guidance of text prompt and additional reference image. While the text-driven video editing has demonstrated remarkable ability to generate highly diverse videos following given text prompts, the fine-grained semantic edits are hard to control by plain textual prompt only in terms of object details and edited region, and cumbersome long text descriptions are usually needed for the task. We therefore investigate subject-driven video editing for more precise control of both edited regions and background preservation, and fine-grained semantic generation. We achieve this goal by introducing an reference image as supplementary input to the text-driven video editing, which avoids racking your brain to come up with a cumbersome text prompt describing the detailed appearance of the object. To limit the editing area, we refer to a method of cross attention control in image editing and successfully extend it to video editing by fusing the attention map of adjacent frames, which strikes a balance between maintaining video background and spatio-temporal consistency. Compared with current methods, the whole process of our method is like ``cut" the source object to be edited and then ``paste" the target object provided by reference image. We demonstrate that our method performs favorably over prior arts for video editing under the guidance of text prompt and extra reference image, as measured by both quantitative and subjective evaluations.

Yang Zhao, Xuan Lin, Wenqiang Xu et al.

In recent days, streaming technology has greatly promoted the development in the field of livestream. Due to the excessive length of livestream records, it's quite essential to extract highlight segments with the aim of effective reproduction and redistribution. Although there are lots of approaches proven to be effective in the highlight detection for other modals, the challenges existing in livestream processing, such as the extreme durations, large topic shifts, much irrelevant information and so forth, heavily hamper the adaptation and compatibility of these methods. In this paper, we formulate a new task Livestream Highlight Detection, discuss and analyze the difficulties listed above and propose a novel architecture AntPivot to solve this problem. Concretely, we first encode the original data into multiple views and model their temporal relations to capture clues in a hierarchical attention mechanism. Afterwards, we try to convert the detection of highlight clips into the search for optimal decision sequences and use the fully integrated representations to predict the final results in a dynamic-programming mechanism. Furthermore, we construct a fully-annotated dataset AntHighlight to instantiate this task and evaluate the performance of our model. The extensive experiments indicate the effectiveness and validity of our proposed method.

Luting Wang, Yang Zhao, Zijian Zhang et al.

Abstract Modern image generation (IG) models have been shown to capture rich semantics valuable for image understanding (IU) tasks. However, the potential of IU models to improve IG performance remains uncharted. We address this issue using a token-based IG framework, which relies on effective tokenizers to project images into token sequences. Currently, pixel reconstruction (e.g., VQGAN) dominates the training objective for image tokenizers. In contrast, our approach adopts the feature reconstruction objective, where tokenizers are trained by distilling knowledge from pretrained IU encoders. Comprehensive comparisons indicate that tokenizers with strong IU capabilities achieve superior IG performance across a variety of metrics, datasets, tasks, and proposal networks. Notably, VQ-KD CLIP achieves $4.10$ FID on ImageNet-1k (IN-1k). Visualization suggests that the superiority of VQ-KD can be partly attributed to the rich semantics within the VQ-KD codebook. We further introduce a straightforward pipeline to directly transform IU encoders into tokenizers, demonstrating exceptional effectiveness for IG tasks. These discoveries may energize further exploration into image tokenizer research and inspire the community to reassess the relationship between IU and IG. The code is released at https://github.com/magic-research/vector_quantization.

Yang Zhao, Hao Zhang, Xiuyuan Hu

How to train deep neural networks (DNNs) to generalize well is a central concern in deep learning, especially for severely overparameterized networks nowadays. In this paper, we propose an effective method to improve the model generalization by additionally penalizing the gradient norm of loss function during optimization. We demonstrate that confining the gradient norm of loss function could help lead the optimizers towards finding flat minima. We leverage the first-order approximation to efficiently implement the corresponding gradient to fit well in the gradient descent framework. In our experiments, we confirm that when using our methods, generalization performance of various models could be improved on different datasets. Also, we show that the recent sharpness-aware minimization method (Foret et al., 2021) is a special, but not the best, case of our method, where the best case of our method could give new state-of-art performance on these tasks. Code is available at {https://github.com/zhaoyang-0204/gnp}.

Kelvin C. K. Chan, Yang Zhao, Xuhui Jia et al.

In subject-driven text-to-image synthesis, the synthesis process tends to be heavily influenced by the reference images provided by users, often overlooking crucial attributes detailed in the text prompt. In this work, we propose Subject-Agnostic Guidance (SAG), a simple yet effective solution to remedy the problem. We show that through constructing a subject-agnostic condition and applying our proposed dual classifier-free guidance, one could obtain outputs consistent with both the given subject and input text prompts. We validate the efficacy of our approach through both optimization-based and encoder-based methods. Additionally, we demonstrate its applicability in second-order customization methods, where an encoder-based model is fine-tuned with DreamBooth. Our approach is conceptually simple and requires only minimal code modifications, but leads to substantial quality improvements, as evidenced by our evaluations and user studies.

Huaiyuan Ying, Hongyi Yuan, Jinsen Lu et al.

Electronic Health Records (EHRs) hold immense potential for advancing healthcare, offering rich, longitudinal data that combines structured information with valuable insights from unstructured clinical notes. However, the unstructured nature of clinical text poses significant challenges for secondary applications. Traditional methods for structuring EHR free-text data, such as rule-based systems and multi-stage pipelines, are often limited by their time-consuming configurations and inability to adapt across clinical notes from diverse healthcare settings. Few systems provide a comprehensive attribute extraction for terminologies. While giant large language models (LLMs) like GPT-4 and LLaMA 405B excel at structuring tasks, they are slow, costly, and impractical for large-scale use. To overcome these limitations, we introduce GENIE, a Generative Note Information Extraction system that leverages LLMs to streamline the structuring of unstructured clinical text into usable data with standardized format. GENIE processes entire paragraphs in a single pass, extracting entities, assertion statuses, locations, modifiers, values, and purposes with high accuracy. Its unified, end-to-end approach simplifies workflows, reduces errors, and eliminates the need for extensive manual intervention. Using a robust data preparation pipeline and fine-tuned small scale LLMs, GENIE achieves competitive performance across multiple information extraction tasks, outperforming traditional tools like cTAKES and MetaMap and can handle extra attributes to be extracted. GENIE strongly enhances real-world applicability and scalability in healthcare systems. By open-sourcing the model and test data, we aim to encourage collaboration and drive further advancements in EHR structurization.

Haifeng Huang, Yang Zhao, Zehan Wang et al.

Temporal Video Grounding (TVG) aims to localize the temporal boundary of a specific segment in an untrimmed video based on a given language query. Since datasets in this domain are often gathered from limited video scenes, models tend to overfit to scene-specific factors, which leads to suboptimal performance when encountering new scenes in real-world applications. In a new scene, the fine-grained annotations are often insufficient due to the expensive labor cost, while the coarse-grained video-query pairs are easier to obtain. Thus, to address this issue and enhance model performance on new scenes, we explore the TVG task in an unsupervised domain adaptation (UDA) setting across scenes for the first time, where the video-query pairs in the source scene (domain) are labeled with temporal boundaries, while those in the target scene are not. Under the UDA setting, we introduce a novel Adversarial Multi-modal Domain Adaptation (AMDA) method to adaptively adjust the model's scene-related knowledge by incorporating insights from the target data. Specifically, we tackle the domain gap by utilizing domain discriminators, which help identify valuable scene-related features effective across both domains. Concurrently, we mitigate the semantic gap between different modalities by aligning video-query pairs with related semantics. Furthermore, we employ a mask-reconstruction approach to enhance the understanding of temporal semantics within a scene. Extensive experiments on Charades-STA, ActivityNet Captions, and YouCook2 demonstrate the effectiveness of our proposed method.

Yang Zhao, Yan Zhang, Xubo Yang

Existing human motion generation methods with trajectory and pose inputs operate global processing on both modalities, leading to suboptimal outputs. In this paper, we propose IKMo, an image-keyframed motion generation method based on the diffusion model with trajectory and pose being decoupled. The trajectory and pose inputs go through a two-stage conditioning framework. In the first stage, the dedicated optimization module is applied to refine inputs. In the second stage, trajectory and pose are encoded via a Trajectory Encoder and a Pose Encoder in parallel. Then, motion with high spatial and semantic fidelity is guided by a motion ControlNet, which processes the fused trajectory and pose data. Experiment results based on HumanML3D and KIT-ML datasets demonstrate that the proposed method outperforms state-of-the-art on all metrics under trajectory-keyframe constraints. In addition, MLLM-based agents are implemented to pre-process model inputs. Given texts and keyframe images from users, the agents extract motion descriptions, keyframe poses, and trajectories as the optimized inputs into the motion generation model. We conducts a user study with 10 participants. The experiment results prove that the MLLM-based agents pre-processing makes generated motion more in line with users' expectation. We believe that the proposed method improves both the fidelity and controllability of motion generation by the diffusion model.

Shanding Diao, Yang Zhao, Yuan Chen et al.

With the rapid development of stereoscopic display technologies, especially glasses-free 3D screens, and virtual reality devices, stereoscopic conversion has become an important task to address the lack of high-quality stereoscopic image and video resources. Current stereoscopic conversion algorithms typically struggle to balance reconstruction performance and inference efficiency. This paper proposes a planar video real-time stereoscopic conversion network based on multi-plane images (MPI), which consists of a detail branch for generating MPI and a depth-semantic branch for perceiving depth information. Unlike models that depend on explicit depth map inputs, the proposed method employs a lightweight depth-semantic branch to extract depth-aware features implicitly. To optimize the lightweight branch, a heavy training but light inference strategy is adopted, which involves designing a coarse-to-fine auxiliary branch that is only used during the training stage. In addition, the proposed method simplifies the MPI rendering process for stereoscopic conversion scenarios to further accelerate the inference. Experimental results demonstrate that the proposed method can achieve comparable performance to some state-of-the-art (SOTA) models and support real-time inference at 2K resolution. Compared to the SOTA TMPI algorithm, the proposed method obtains similar subjective quality while achieving over $40\times$ inference acceleration.

Pengcheng Zhao, Yanxiang Chen, Yang Zhao et al.

Automatic image colorization is inherently an ill-posed problem with uncertainty, which requires an accurate semantic understanding of scenes to estimate reasonable colors for grayscale images. Although recent interaction-based methods have achieved impressive performance, it is still a very difficult task to infer realistic and accurate colors for automatic colorization. To reduce the difficulty of semantic understanding of grayscale scenes, this paper tries to utilize corresponding audio, which naturally contains extra semantic information about the same scene. Specifically, a novel and pluggable audio-infused automatic image colorization (AIAIC) method is proposed, which consists of three stages. First, we take color image semantics as a bridge and pretrain a colorization network guided by color image semantics. Second, the natural co-occurrence of audio and video is utilized to learn the color semantic correlations between audio and visual scenes. Third, the implicit audio semantic representation is fed into the pretrained network to finally realize the audio-guided colorization. The whole process is trained in a self-supervised manner without human annotation. Experiments demonstrate that audio guidance can effectively improve the performance of automatic colorization, especially for some scenes that are difficult to understand only from visual modality.

Di Xu, Yang Zhao, Xiang Hao et al.

We introduce a novel dataset consisting of images depicting pink eggs that have been identified as Pomacea canaliculata eggs, accompanied by corresponding bounding box annotations. The purpose of this dataset is to aid researchers in the analysis of the spread of Pomacea canaliculata species by utilizing deep learning techniques, as well as supporting other investigative pursuits that require visual data pertaining to the eggs of Pomacea canaliculata. It is worth noting, however, that the identity of the eggs in question is not definitively established, as other species within the same taxonomic family have been observed to lay similar-looking eggs in regions of the Americas. Therefore, a crucial prerequisite to any decision regarding the elimination of these eggs would be to establish with certainty whether they are exclusively attributable to invasive Pomacea canaliculata or if other species are also involved. The dataset is available at https://www.kaggle.com/datasets/deeshenzhen/pinkeggs

Yang Zhao, Yanbo Ma, Yuan Chen et al.

Early interlaced videos usually contain multiple and interlacing and complex compression artifacts, which significantly reduce the visual quality. Although the high-definition reconstruction technology for early videos has made great progress in recent years, related research on deinterlacing is still lacking. Traditional methods mainly focus on simple interlacing mechanism, and cannot deal with the complex artifacts in real-world early videos. Recent interlaced video reconstruction deep deinterlacing models only focus on single frame, while neglecting important temporal information. Therefore, this paper proposes a multiframe deinterlacing network joint enhancement network for early interlaced videos that consists of three modules, i.e., spatial vertical interpolation module, temporal alignment and fusion module, and final refinement module. The proposed method can effectively remove the complex artifacts in early videos by using temporal redundancy of multi-fields. Experimental results demonstrate that the proposed method can recover high quality results for both synthetic dataset and real-world early interlaced videos.

Yang Zhao, Hao Zhang

Identifying the status of individual network units is critical for understanding the mechanism of convolutional neural networks (CNNs). However, it is still challenging to reliably give a general indication of unit status, especially for units in different network models. To this end, we propose a novel method for quantitatively clarifying the status of single unit in CNN using algebraic topological tools. Unit status is indicated via the calculation of a defined topological-based entropy, called feature entropy, which measures the degree of chaos of the global spatial pattern hidden in the unit for a category. In this way, feature entropy could provide an accurate indication of status for units in different networks with diverse situations like weight-rescaling operation. Further, we show that feature entropy decreases as the layer goes deeper and shares almost simultaneous trend with loss during training. We show that by investigating the feature entropy of units on only training data, it could give discrimination between networks with different generalization ability from the view of the effectiveness of feature representations.

Yang Zhao, Guoqing Li, Wenjun Xie et al.

In this paper, an efficient super-resolution (SR) method based on deep convolutional neural network (CNN) is proposed, namely Gradual Upsampling Network (GUN). Recent CNN based SR methods often preliminarily magnify the low resolution (LR) input to high resolution (HR) and then reconstruct the HR input, or directly reconstruct the LR input and then recover the HR result at the last layer. The proposed GUN utilizes a gradual process instead of these two commonly used frameworks. The GUN consists of an input layer, multiple upsampling and convolutional layers, and an output layer. By means of the gradual process, the proposed network can simplify the direct SR problem to multistep easier upsampling tasks with very small magnification factor in each step. Furthermore, a gradual training strategy is presented for the GUN. In the proposed training process, an initial network can be easily trained with edge-like samples, and then the weights are gradually tuned with more complex samples. The GUN can recover fine and vivid results, and is easy to be trained. The experimental results on several image sets demonstrate the effectiveness of the proposed network.

Yang Zhao, Ronggang Wang, Wei Jia et al.

Recent learning-based super-resolution (SR) methods often focus on dictionary learning or network training. In this paper, we discuss in detail a new SR method based on local patch encoding (LPE) instead of traditional dictionary learning. The proposed method consists of a learning stage and a reconstructing stage. In the learning stage, image patches are classified into different classes by means of the proposed LPE, and then a projection matrix is computed for each class by utilizing a simple constraint. In the reconstructing stage, an input LR patch can be simply reconstructed by computing its LPE code and then multiplying the corresponding projection matrix. Furthermore, we discuss the relationship between the proposed method and the anchored neighborhood regression methods; we also analyze the extendibility of the proposed method. The experimental results on several image sets demonstrate the effectiveness of the LPE-based methods.