Peng Gao

Peng Xu, Wenqi Shao, Kaipeng Zhang et al. · pku

Large Vision-Language Models (LVLMs) have recently played a dominant role in multimodal vision-language learning. Despite the great success, it lacks a holistic evaluation of their efficacy. This paper presents a comprehensive evaluation of publicly available large multimodal models by building a LVLM evaluation Hub (LVLM-eHub). Our LVLM-eHub consists of $8$ representative LVLMs such as InstructBLIP and MiniGPT-4, which are thoroughly evaluated by a quantitative capability evaluation and an online arena platform. The former evaluates $6$ categories of multimodal capabilities of LVLMs such as visual question answering and embodied artificial intelligence on $47$ standard text-related visual benchmarks, while the latter provides the user-level evaluation of LVLMs in an open-world question-answering scenario. The study reveals several innovative findings. First, instruction-tuned LVLM with massive in-domain data such as InstructBLIP heavily overfits many existing tasks, generalizing poorly in the open-world scenario. Second, instruction-tuned LVLM with moderate instruction-following data may result in object hallucination issues (i.e., generate objects that are inconsistent with target images in the descriptions). It either makes the current evaluation metric such as CIDEr for image captioning ineffective or generates wrong answers. Third, employing a multi-turn reasoning evaluation framework can mitigate the issue of object hallucination, shedding light on developing an effective pipeline for LVLM evaluation. The findings provide a foundational framework for the conception and assessment of innovative strategies aimed at enhancing zero-shot multimodal techniques. Our LVLM-eHub will be available at https://github.com/OpenGVLab/Multi-Modality-Arena

Mengzhao Chen, Wenqi Shao, Peng Xu et al.

Large language models (LLMs) are crucial in modern natural language processing and artificial intelligence. However, they face challenges in managing their significant memory requirements. Although quantization-aware training (QAT) offers a solution by reducing memory consumption through low-bit representations with minimal accuracy loss, it is impractical due to substantial training resources. To address this, we propose Efficient Quantization-Aware Training (EfficientQAT), a more feasible QAT algorithm. EfficientQAT involves two consecutive phases: Block-wise training of all parameters (Block-AP) and end-to-end training of quantization parameters (E2E-QP). To the best of our knowledge, Block-AP is the first method to enable direct training of all parameters in a block-wise manner, reducing accuracy loss in low-bit scenarios by enhancing the solution space during optimization. E2E-QP then trains only the quantization parameters (step sizes) end-to-end, further improving the performance of quantized models by considering interactions among all sub-modules. Extensive experiments demonstrate that EfficientQAT outperforms previous quantization methods across a range of models, including base LLMs, instruction-tuned LLMs, and multimodal LLMs, with scales from 7B to 70B parameters at various quantization bits. For instance, EfficientQAT obtains a 2-bit Llama-2-70B model on a single A100-80GB GPU in 41 hours, with less than 3 points accuracy degradation compared to the full precision (69.48 vs. 72.41). Code is available at https://github.com/OpenGVLab/EfficientQAT.

Wenqi Shao, Meng Lei, Yutao Hu et al. · pku

Recent advancements in Large Vision-Language Models (LVLMs) have demonstrated significant progress in tackling complex multimodal tasks. Among these cutting-edge developments, Google's Bard stands out for its remarkable multimodal capabilities, promoting comprehensive comprehension and reasoning across various domains. This work presents an early and holistic evaluation of LVLMs' multimodal abilities, with a particular focus on Bard, by proposing a lightweight variant of LVLM-eHub, named Tiny LVLM-eHub. In comparison to the vanilla version, Tiny LVLM-eHub possesses several appealing properties. Firstly, it provides a systematic assessment of six categories of multimodal capabilities, including visual perception, visual knowledge acquisition, visual reasoning, visual commonsense, object hallucination, and embodied intelligence, through quantitative evaluation of $42$ standard text-related visual benchmarks. Secondly, it conducts an in-depth analysis of LVLMs' predictions using the ChatGPT Ensemble Evaluation (CEE), which leads to a robust and accurate evaluation and exhibits improved alignment with human evaluation compared to the word matching approach. Thirdly, it comprises a mere $2.1$K image-text pairs, facilitating ease of use for practitioners to evaluate their own offline LVLMs. Through extensive experimental analysis, this study demonstrates that Bard outperforms previous LVLMs in most multimodal capabilities except object hallucination, to which Bard is still susceptible. Tiny LVLM-eHub serves as a baseline evaluation for various LVLMs and encourages innovative strategies aimed at advancing multimodal techniques. Our project is publicly available at \url{https://github.com/OpenGVLab/Multi-Modality-Arena}.

Weifeng Lin, Xinyu Wei, Renrui Zhang et al.

This paper presents a versatile image-to-image visual assistant, PixWizard, designed for image generation, manipulation, and translation based on free-from language instructions. To this end, we tackle a variety of vision tasks into a unified image-text-to-image generation framework and curate an Omni Pixel-to-Pixel Instruction-Tuning Dataset. By constructing detailed instruction templates in natural language, we comprehensively include a large set of diverse vision tasks such as text-to-image generation, image restoration, image grounding, dense image prediction, image editing, controllable generation, inpainting/outpainting, and more. Furthermore, we adopt Diffusion Transformers (DiT) as our foundation model and extend its capabilities with a flexible any resolution mechanism, enabling the model to dynamically process images based on the aspect ratio of the input, closely aligning with human perceptual processes. The model also incorporates structure-aware and semantic-aware guidance to facilitate effective fusion of information from the input image. Our experiments demonstrate that PixWizard not only shows impressive generative and understanding abilities for images with diverse resolutions but also exhibits promising generalization capabilities with unseen tasks and human instructions. The code and related resources are available at https://github.com/AFeng-x/PixWizard

Xiao Liu, Peng Gao, Tao Yu et al.

Deep learning, especially convolutional neural networks (CNNs) and Transformer architectures, have become the focus of extensive research in medical image segmentation, achieving impressive results. However, CNNs come with inductive biases that limit their effectiveness in more complex, varied segmentation scenarios. Conversely, while Transformer-based methods excel at capturing global and long-range semantic details, they suffer from high computational demands. In this study, we propose CSWin-UNet, a novel U-shaped segmentation method that incorporates the CSWin self-attention mechanism into the UNet to facilitate horizontal and vertical stripes self-attention. This method significantly enhances both computational efficiency and receptive field interactions. Additionally, our innovative decoder utilizes a content-aware reassembly operator that strategically reassembles features, guided by predicted kernels, for precise image resolution restoration. Our extensive empirical evaluations on diverse datasets, including synapse multi-organ CT, cardiac MRI, and skin lesions, demonstrate that CSWin-UNet maintains low model complexity while delivering high segmentation accuracy. Codes are available at https://github.com/eatbeanss/CSWin-UNet.

Rongyao Fang, Peng Gao, Aojun Zhou et al.

One-to-one matching is a crucial design in DETR-like object detection frameworks. It enables the DETR to perform end-to-end detection. However, it also faces challenges of lacking positive sample supervision and slow convergence speed. Several recent works proposed the one-to-many matching mechanism to accelerate training and boost detection performance. We revisit these methods and model them in a unified format of augmenting the object queries. In this paper, we propose two methods that realize one-to-many matching from a different perspective of augmenting images or image features. The first method is One-to-many Matching via Data Augmentation (denoted as DataAug-DETR). It spatially transforms the images and includes multiple augmented versions of each image in the same training batch. Such a simple augmentation strategy already achieves one-to-many matching and surprisingly improves DETR's performance. The second method is One-to-many matching via Feature Augmentation (denoted as FeatAug-DETR). Unlike DataAug-DETR, it augments the image features instead of the original images and includes multiple augmented features in the same batch to realize one-to-many matching. FeatAug-DETR significantly accelerates DETR training and boosts detection performance while keeping the inference speed unchanged. We conduct extensive experiments to evaluate the effectiveness of the proposed approach on DETR variants, including DAB-DETR, Deformable-DETR, and H-Deformable-DETR. Without extra training data, FeatAug-DETR shortens the training convergence periods of Deformable-DETR to 24 epochs and achieves 58.3 AP on COCO val2017 set with Swin-L as the backbone.

Xuexue Li, Wenhui Diao, Yongqiang Mao et al.

Occlusion between objects is one of the overlooked challenges for object detection in UAV images. Due to the variable altitude and angle of UAVs, occlusion in UAV images happens more frequently than that in natural scenes. Compared to occlusion in natural scene images, occlusion in UAV images happens with feature confusion problem and local aggregation characteristic. And we found that extracting or localizing occlusion between objects is beneficial for the detector to address this challenge. According to this finding, the occlusion localization task is introduced, which together with the object detection task constitutes our occlusion-guided multi-task network (OGMN). The OGMN contains the localization of occlusion and two occlusion-guided multi-task interactions. In detail, an occlusion estimation module (OEM) is proposed to precisely localize occlusion. Then the OGMN utilizes the occlusion localization results to implement occlusion-guided detection with two multi-task interactions. One interaction for the guide is between two task decoders to address the feature confusion problem, and an occlusion decoupling head (ODH) is proposed to replace the general detection head. Another interaction for guide is designed in the detection process according to local aggregation characteristic, and a two-phase progressive refinement process (TPP) is proposed to optimize the detection process. Extensive experiments demonstrate the effectiveness of our OGMN on the Visdrone and UAVDT datasets. In particular, our OGMN achieves 35.0% mAP on the Visdrone dataset and outperforms the baseline by 5.3%. And our OGMN provides a new insight for accurate occlusion localization and achieves competitive detection performance.

Sheng Xu, Yanjing Li, Mingbao Lin et al.

The recent detection transformer (DETR) has advanced object detection, but its application on resource-constrained devices requires massive computation and memory resources. Quantization stands out as a solution by representing the network in low-bit parameters and operations. However, there is a significant performance drop when performing low-bit quantized DETR (Q-DETR) with existing quantization methods. We find that the bottlenecks of Q-DETR come from the query information distortion through our empirical analyses. This paper addresses this problem based on a distribution rectification distillation (DRD). We formulate our DRD as a bi-level optimization problem, which can be derived by generalizing the information bottleneck (IB) principle to the learning of Q-DETR. At the inner level, we conduct a distribution alignment for the queries to maximize the self-information entropy. At the upper level, we introduce a new foreground-aware query matching scheme to effectively transfer the teacher information to distillation-desired features to minimize the conditional information entropy. Extensive experimental results show that our method performs much better than prior arts. For example, the 4-bit Q-DETR can theoretically accelerate DETR with ResNet-50 backbone by 6.6x and achieve 39.4% AP, with only 2.6% performance gaps than its real-valued counterpart on the COCO dataset.

Weijie Xia, Gao Peng, Chenguang Wang et al.

Electricity Consumption Profiles (ECPs) are crucial for operating and planning power distribution systems, especially with the increasing numbers of various low-carbon technologies such as solar panels and electric vehicles. Traditional ECP modeling methods typically assume the availability of sufficient ECP data. However, in practice, the accessibility of ECP data is limited due to privacy issues or the absence of metering devices. Few-shot learning (FSL) has emerged as a promising solution for ECP modeling in data-scarce scenarios. Nevertheless, standard FSL methods, such as those used for images, are unsuitable for ECP modeling because (1) these methods usually assume several source domains with sufficient data and several target domains. However, in the context of ECP modeling, there may be thousands of source domains with a moderate amount of data and thousands of target domains. (2) Standard FSL methods usually involve cumbersome knowledge transfer mechanisms, such as pre-training and fine-tuning, whereas ECP modeling requires more lightweight methods. (3) Deep learning models often lack explainability, hindering their application in industry. This paper proposes a novel FSL method that exploits Transformers and Gaussian Mixture Models (GMMs) for ECP modeling to address the above-described issues. Results show that our method can accurately restore the complex ECP distribution with a minimal amount of ECP data (e.g., only 1.6\% of the complete domain dataset) while it outperforms state-of-the-art time series modeling methods, maintaining the advantages of being both lightweight and interpretable. The project is open-sourced at https://github.com/xiaweijie1996/TransformerEM-GMM.git.

Tao Yu, Peng Gao, Fei Wang et al.

Due to the increasing complexity of chip design, existing placement methods still have many shortcomings in dealing with macro cells coverage and optimization efficiency. Aiming at the problems of layout overlap, inferior performance, and low optimization efficiency in existing chip design methods, this paper proposes an end-to-end placement method, SRLPlacer, based on reinforcement learning. First, the placement problem is transformed into a Markov decision process by establishing the coupling relationship graph model between macro cells to learn the strategy for optimizing layouts. Secondly, the whole placement process is optimized after integrating the standard cell layout. By assessing on the public benchmark ISPD2005, the proposed SRLPlacer can effectively solve the overlap problem between macro cells while considering routing congestion and shortening the total wire length to ensure routability. Codes are available at https://github.com/zhouyusd/SRLPlacer.

Saimon Amanuel Tsegai, Xinyu Yang, Haoyuan Liu et al.

System auditing is a vital technique for collecting system call events as system provenance and investigating complex multi-step attacks such as Advanced Persistent Threats. However, existing attack investigation methods struggle to uncover long attack sequences due to the massive volume of system provenance data and their inability to focus on attack-relevant parts. In this paper, we present Provexa, a defense system that enables human analysts to effectively analyze large-scale system provenance to reveal multi-step attack sequences. Provexa introduces an expressive domain-specific language, ProvQL, that offers essential primitives for various types of attack analyses (e.g., attack pattern search, attack dependency tracking) with user-defined constraints, enabling analysts to focus on attack-relevant parts and iteratively sift through the large provenance data. Moreover, Provexa provides an optimized execution engine for efficient language execution. Our extensive evaluations on a wide range of attack scenarios demonstrate the practical effectiveness of Provexa in facilitating timely attack investigation.

Yi Xin, Juncheng Yan, Qi Qin et al.

We present Lumina-mGPT 2.0, a stand-alone, decoder-only autoregressive model that revisits and revitalizes the autoregressive paradigm for high-quality image generation and beyond. Unlike existing approaches that rely on pretrained components or hybrid architectures, Lumina-mGPT 2.0 is trained entirely from scratch, enabling unrestricted architectural design and licensing freedom. It achieves generation quality on par with state-of-the-art diffusion models such as DALL-E 3 and SANA, while preserving the inherent flexibility and compositionality of autoregressive modeling. Our unified tokenization scheme allows the model to seamlessly handle a wide spectrum of tasks-including subject-driven generation, image editing, controllable synthesis, and dense prediction-within a single generative framework. To further boost usability, we incorporate efficient decoding strategies like inference-time scaling and speculative Jacobi sampling to improve quality and speed, respectively. Extensive evaluations on standard text-to-image benchmarks (e.g., GenEval, DPG) demonstrate that Lumina-mGPT 2.0 not only matches but in some cases surpasses diffusion-based models. Moreover, we confirm its multi-task capabilities on the Graph200K benchmark, with the native Lumina-mGPT 2.0 performing exceptionally well. These results position Lumina-mGPT 2.0 as a strong, flexible foundation model for unified multimodal generation. We have released our training details, code, and models at https://github.com/Alpha-VLLM/Lumina-mGPT-2.0.

Dongyang Liu, Shicheng Li, Yutong Liu et al.

Recent advancements have established Diffusion Transformers (DiTs) as a dominant framework in generative modeling. Building on this success, Lumina-Next achieves exceptional performance in the generation of photorealistic images with Next-DiT. However, its potential for video generation remains largely untapped, with significant challenges in modeling the spatiotemporal complexity inherent to video data. To address this, we introduce Lumina-Video, a framework that leverages the strengths of Next-DiT while introducing tailored solutions for video synthesis. Lumina-Video incorporates a Multi-scale Next-DiT architecture, which jointly learns multiple patchifications to enhance both efficiency and flexibility. By incorporating the motion score as an explicit condition, Lumina-Video also enables direct control of generated videos' dynamic degree. Combined with a progressive training scheme with increasingly higher resolution and FPS, and a multi-source training scheme with mixed natural and synthetic data, Lumina-Video achieves remarkable aesthetic quality and motion smoothness at high training and inference efficiency. We additionally propose Lumina-V2A, a video-to-audio model based on Next-DiT, to create synchronized sounds for generated videos. Codes are released at https://www.github.com/Alpha-VLLM/Lumina-Video.

Xudong Lu, Aojun Zhou, Ziyi Lin et al. · salesforce

Recent developments in large-scale pre-trained text-to-image diffusion models have significantly improved the generation of high-fidelity images, particularly with the emergence of diffusion transformer models (DiTs). Among diffusion models, diffusion transformers have demonstrated superior image-generation capabilities, boosting lower FID scores and higher scalability. However, deploying large-scale DiT models can be expensive due to their excessive parameter numbers. Although existing research has explored efficient deployment techniques for diffusion models, such as model quantization, there is still little work concerning DiT-based models. To tackle this research gap, we propose TerDiT, the first quantization-aware training (QAT) and efficient deployment scheme for extremely low-bit diffusion transformer models. We focus on the ternarization of DiT networks, with model sizes ranging from 600M to 4.2B, and image resolution from 256$\times$256 to 512$\times$512. Our work contributes to the exploration of efficient deployment of large-scale DiT models, demonstrating the feasibility of training extremely low-bit DiT models from scratch while maintaining competitive image generation capacities compared to full-precision models. Our code and pre-trained TerDiT checkpoints have been released at https://github.com/Lucky-Lance/TerDiT.

Long Xu, Peng Gao, Wen-Jia Tang et al.

Although deep learning-based visual tracking methods have made significant progress, they exhibit vulnerabilities when facing carefully designed adversarial attacks, which can lead to a sharp decline in tracking performance. To address this issue, this paper proposes for the first time a novel adversarial defense method based on denoise diffusion probabilistic models, termed DiffDf, aimed at effectively improving the robustness of existing visual tracking methods against adversarial attacks. DiffDf establishes a multi-scale defense mechanism by combining pixel-level reconstruction loss, semantic consistency loss, and structural similarity loss, effectively suppressing adversarial perturbations through a gradual denoising process. Extensive experimental results on several mainstream datasets show that the DiffDf method demonstrates excellent generalization performance for trackers with different architectures, significantly improving various evaluation metrics while achieving real-time inference speeds of over 30 FPS, showcasing outstanding defense performance and efficiency. Codes are available at https://github.com/pgao-lab/DiffDf.

Shitian Zhao, Qilong Wu, Xinyue Li et al.

We introduce LeX-Art, a comprehensive suite for high-quality text-image synthesis that systematically bridges the gap between prompt expressiveness and text rendering fidelity. Our approach follows a data-centric paradigm, constructing a high-quality data synthesis pipeline based on Deepseek-R1 to curate LeX-10K, a dataset of 10K high-resolution, aesthetically refined 1024$\times$1024 images. Beyond dataset construction, we develop LeX-Enhancer, a robust prompt enrichment model, and train two text-to-image models, LeX-FLUX and LeX-Lumina, achieving state-of-the-art text rendering performance. To systematically evaluate visual text generation, we introduce LeX-Bench, a benchmark that assesses fidelity, aesthetics, and alignment, complemented by Pairwise Normalized Edit Distance (PNED), a novel metric for robust text accuracy evaluation. Experiments demonstrate significant improvements, with LeX-Lumina achieving a 79.81% PNED gain on CreateBench, and LeX-FLUX outperforming baselines in color (+3.18%), positional (+4.45%), and font accuracy (+3.81%). Our codes, models, datasets, and demo are publicly available.

Wei-Long Tian, Peng Gao, Xiao Liu et al.

In recent years, visual tracking methods based on convolutional neural networks and Transformers have achieved remarkable performance and have been successfully applied in fields such as autonomous driving. However, the numerous security issues exposed by deep learning models have gradually affected the reliable application of visual tracking methods in real-world scenarios. Therefore, how to reveal the security vulnerabilities of existing visual trackers through effective adversarial attacks has become a critical problem that needs to be addressed. To this end, we propose an adaptive meta-gradient adversarial attack (AMGA) method for visual tracking. This method integrates multi-model ensembles and meta-learning strategies, combining momentum mechanisms and Gaussian smoothing, which can significantly enhance the transferability and attack effectiveness of adversarial examples. AMGA randomly selects models from a large model repository, constructs diverse tracking scenarios, and iteratively performs both white- and black-box adversarial attacks in each scenario, optimizing the gradient directions of each model. This paradigm minimizes the gap between white- and black-box adversarial attacks, thus achieving excellent attack performance in black-box scenarios. Extensive experimental results on large-scale datasets such as OTB2015, LaSOT, and GOT-10k demonstrate that AMGA significantly improves the attack performance, transferability, and deception of adversarial examples. Codes and data are available at https://github.com/pgao-lab/AMGA.

Ziyu Guo, Renrui Zhang, Xiangyang Zhu et al.

We introduce Point-Bind, a 3D multi-modality model aligning point clouds with 2D image, language, audio, and video. Guided by ImageBind, we construct a joint embedding space between 3D and multi-modalities, enabling many promising applications, e.g., any-to-3D generation, 3D embedding arithmetic, and 3D open-world understanding. On top of this, we further present Point-LLM, the first 3D large language model (LLM) following 3D multi-modal instructions. By parameter-efficient fine-tuning techniques, Point-LLM injects the semantics of Point-Bind into pre-trained LLMs, e.g., LLaMA, which requires no 3D instruction data, but exhibits superior 3D and multi-modal question-answering capacity. We hope our work may cast a light on the community for extending 3D point clouds to multi-modality applications. Code is available at https://github.com/ZiyuGuo99/Point-Bind_Point-LLM.

Renrui Zhang, Rongyao Fang, Wei Zhang et al.

Contrastive Vision-Language Pre-training, known as CLIP, has provided a new paradigm for learning visual representations by using large-scale contrastive image-text pairs. It shows impressive performance on zero-shot knowledge transfer to downstream tasks. To further enhance CLIP's few-shot capability, CLIP-Adapter proposed to fine-tune a lightweight residual feature adapter and significantly improves the performance for few-shot classification. However, such a process still needs extra training and computational resources. In this paper, we propose \textbf{T}raining-Free CL\textbf{IP}-\textbf{Adapter} (\textbf{Tip-Adapter}), which not only inherits CLIP's training-free advantage but also performs comparably or even better than CLIP-Adapter. Tip-Adapter does not require any back propagation for training the adapter, but creates the weights by a key-value cache model constructed from the few-shot training set. In this non-parametric manner, Tip-Adapter acquires well-performed adapter weights without any training, which is both efficient and effective. Moreover, the performance of Tip-Adapter can be further boosted by fine-tuning such properly initialized adapter for only a few epochs with super-fast convergence speed. We conduct extensive experiments of few-shot classification on ImageNet and other 10 datasets to demonstrate the superiority of proposed Tip-Adapter. The code will be released at \url{https://github.com/gaopengcuhk/Tip-Adapter}.

Peng Gao, Shijie Geng, Renrui Zhang et al.

Large-scale contrastive vision-language pre-training has shown significant progress in visual representation learning. Unlike traditional visual systems trained by a fixed set of discrete labels, a new paradigm was introduced in \cite{radford2021learning} to directly learn to align images with raw texts in an open-vocabulary setting. On downstream tasks, a carefully chosen text prompt is employed to make zero-shot predictions.~To avoid non-trivial prompt engineering, context optimization \cite{zhou2021coop} has been proposed to learn continuous vectors as task-specific prompts with few-shot training examples.~In this paper, we show that there is an alternative path to achieve better vision-language models other than prompt tuning.~While prompt tuning is for the textual inputs, we propose CLIP-Adapter to conduct fine-tuning with feature adapters on either visual or language branch. Specifically, CLIP-Adapter adopts an additional bottleneck layer to learn new features and performs residual-style feature blending with the original pre-trained features.~As a consequence, CLIP-Adapter is able to outperform context optimization while maintains a simple design. Experiments and extensive ablation studies on various visual classification tasks demonstrate the effectiveness of our approach. Code is released at t https://github.com/gaopengcuhk/CLIP-Adapter.

Peng Gao, Jiasen Lu, Hongsheng Li et al.

Convolutional neural networks (CNNs) are ubiquitous in computer vision, with a myriad of effective and efficient variations. Recently, Transformers -- originally introduced in natural language processing -- have been increasingly adopted in computer vision. While early adopters continue to employ CNN backbones, the latest networks are end-to-end CNN-free Transformer solutions. A recent surprising finding shows that a simple MLP based solution without any traditional convolutional or Transformer components can produce effective visual representations. While CNNs, Transformers and MLP-Mixers may be considered as completely disparate architectures, we provide a unified view showing that they are in fact special cases of a more general method to aggregate spatial context in a neural network stack. We present the \model (CONText AggregatIon NEtwoRk), a general-purpose building block for multi-head context aggregation that can exploit long-range interactions \emph{a la} Transformers while still exploiting the inductive bias of the local convolution operation leading to faster convergence speeds, often seen in CNNs. In contrast to Transformer-based methods that do not scale well to downstream tasks that rely on larger input image resolutions, our efficient network, named \modellight, can be employed in object detection and instance segmentation networks such as DETR, RetinaNet and Mask-RCNN to obtain an impressive detection mAP of 38.9, 43.8, 45.1 and mask mAP of 41.3, providing large improvements of 6.6, 7.3, 6.9 and 6.6 pts respectively, compared to a ResNet-50 backbone with a comparable compute and parameter size. Our method also achieves promising results on self-supervised learning compared to DeiT on the DINO framework. Code is released at \url{https://github.com/allenai/container}.

Bo Pang, Gao Peng, Yizhuo Li et al.

Convolutional video models have an order of magnitude larger computational complexity than their counterpart image-level models. Constrained by computational resources, there is no model or training method that can train long video sequences end-to-end. Currently, the main-stream method is to split a raw video into clips, leading to incomplete fragmentary temporal information flow. Inspired by natural language processing techniques dealing with long sentences, we propose to treat videos as serial fragments satisfying Markov property, and train it as a whole by progressively propagating information through the temporal dimension in multiple steps. This progressive training (PGT) method is able to train long videos end-to-end with limited resources and ensures the effective transmission of information. As a general and robust training method, we empirically demonstrate that it yields significant performance improvements on different models and datasets. As an illustrative example, the proposed method improves SlowOnly network by 3.7 mAP on Charades and 1.9 top-1 accuracy on Kinetics with negligible parameter and computation overhead. Code is available at https://github.com/BoPang1996/PGT.

Shijie Geng, Peng Gao, Zuohui Fu et al.

BERT has achieved superior performances on Natural Language Understanding (NLU) tasks. However, BERT possesses a large number of parameters and demands certain resources to deploy. For acceleration, Dynamic Early Exiting for BERT (DeeBERT) has been proposed recently, which incorporates multiple exits and adopts a dynamic early-exit mechanism to ensure efficient inference. While obtaining an efficiency-performance tradeoff, the performances of early exits in multi-exit BERT are significantly worse than late exits. In this paper, we leverage gradient regularized self-distillation for RObust training of Multi-Exit BERT (RomeBERT), which can effectively solve the performance imbalance problem between early and late exits. Moreover, the proposed RomeBERT adopts a one-stage joint training strategy for multi-exits and the BERT backbone while DeeBERT needs two stages that require more training time. Extensive experiments on GLUE datasets are performed to demonstrate the superiority of our approach. Our code is available at https://github.com/romebert/RomeBERT.

Minghang Zheng, Peng Gao, Renrui Zhang et al.

End-to-end Object Detection with Transformer (DETR)proposes to perform object detection with Transformer and achieve comparable performance with two-stage object detection like Faster-RCNN. However, DETR needs huge computational resources for training and inference due to the high-resolution spatial input. In this paper, a novel variant of transformer named Adaptive Clustering Transformer(ACT) has been proposed to reduce the computation cost for high-resolution input. ACT cluster the query features adaptively using Locality Sensitive Hashing (LSH) and ap-proximate the query-key interaction using the prototype-key interaction. ACT can reduce the quadratic O(N2) complexity inside self-attention into O(NK) where K is the number of prototypes in each layer. ACT can be a drop-in module replacing the original self-attention module without any training. ACT achieves a good balance between accuracy and computation cost (FLOPs). The code is available as supplementary for the ease of experiment replication and verification. Code is released at \url{https://github.com/gaopengcuhk/SMCA-DETR/}

Lei Shi, Kai Shuang, Shijie Geng et al.

Several multi-modality representation learning approaches such as LXMERT and ViLBERT have been proposed recently. Such approaches can achieve superior performance due to the high-level semantic information captured during large-scale multimodal pretraining. However, as ViLBERT and LXMERT adopt visual region regression and classification loss, they often suffer from domain gap and noisy label problems, based on the visual features having been pretrained on the Visual Genome dataset. To overcome these issues, we propose unbiased Contrastive Visual-Linguistic Pretraining (CVLP), which constructs a visual self-supervised loss built upon contrastive learning. We evaluate CVLP on several down-stream tasks, including VQA, GQA and NLVR2 to validate the superiority of contrastive learning on multi-modality representation learning. Our code is available at: https://github.com/ArcherYunDong/CVLP-.

Zhengkai Jiang, Yu Liu, Ceyuan Yang et al.

Transferring existing image-based detectors to the video is non-trivial since the quality of frames is always deteriorated by part occlusion, rare pose, and motion blur. Previous approaches exploit to propagate and aggregate features across video frames by using optical flow-warping. However, directly applying image-level optical flow onto the high-level features might not establish accurate spatial correspondences. Therefore, a novel module called Learnable Spatio-Temporal Sampling (LSTS) has been proposed to learn semantic-level correspondences among adjacent frame features accurately. The sampled locations are first randomly initialized, then updated iteratively to find better spatial correspondences guided by detection supervision progressively. Besides, Sparsely Recursive Feature Updating (SRFU) module and Dense Feature Aggregation (DFA) module are also introduced to model temporal relations and enhance per-frame features, respectively. Without bells and whistles, the proposed method achieves state-of-the-art performance on the ImageNet VID dataset with less computational complexity and real-time speed. Code will be made available at https://github.com/jiangzhengkai/LSTS.

Chun-Lin Ji, Tao Yu, Peng Gao et al.

Object detection, a crucial aspect of computer vision, has seen significant advancements in accuracy and robustness. Despite these advancements, practical applications still face notable challenges, primarily the inaccurate detection or missed detection of small objects. In this paper, we propose YOLO-TLA, an advanced object detection model building on YOLOv5. We first introduce an additional detection layer for small objects in the neck network pyramid architecture, thereby producing a feature map of a larger scale to discern finer features of small objects. Further, we integrate the C3CrossCovn module into the backbone network. This module uses sliding window feature extraction, which effectively minimizes both computational demand and the number of parameters, rendering the model more compact. Additionally, we have incorporated a global attention mechanism into the backbone network. This mechanism combines the channel information with global information to create a weighted feature map. This feature map is tailored to highlight the attributes of the object of interest, while effectively ignoring irrelevant details. In comparison to the baseline YOLOv5s model, our newly developed YOLO-TLA model has shown considerable improvements on the MS COCO validation dataset, with increases of 4.6% in mAP@0.5 and 4% in mAP@0.5:0.95, all while keeping the model size compact at 9.49M parameters. Further extending these improvements to the YOLOv5m model, the enhanced version exhibited a 1.7% and 1.9% increase in mAP@0.5 and mAP@0.5:0.95, respectively, with a total of 27.53M parameters. These results validate the YOLO-TLA model's efficient and effective performance in small object detection, achieving high accuracy with fewer parameters and computational demands.

Weichen Fan, Chenyang Si, Junhao Song et al.

We present Vchitect-2.0, a parallel transformer architecture designed to scale up video diffusion models for large-scale text-to-video generation. The overall Vchitect-2.0 system has several key designs. (1) By introducing a novel Multimodal Diffusion Block, our approach achieves consistent alignment between text descriptions and generated video frames, while maintaining temporal coherence across sequences. (2) To overcome memory and computational bottlenecks, we propose a Memory-efficient Training framework that incorporates hybrid parallelism and other memory reduction techniques, enabling efficient training of long video sequences on distributed systems. (3) Additionally, our enhanced data processing pipeline ensures the creation of Vchitect T2V DataVerse, a high-quality million-scale training dataset through rigorous annotation and aesthetic evaluation. Extensive benchmarking demonstrates that Vchitect-2.0 outperforms existing methods in video quality, training efficiency, and scalability, serving as a suitable base for high-fidelity video generation.

Le Zhuo, Liangbing Zhao, Sayak Paul et al.

Recent text-to-image diffusion models achieve impressive visual quality through extensive scaling of training data and model parameters, yet they often struggle with complex scenes and fine-grained details. Inspired by the self-reflection capabilities emergent in large language models, we propose ReflectionFlow, an inference-time framework enabling diffusion models to iteratively reflect upon and refine their outputs. ReflectionFlow introduces three complementary inference-time scaling axes: (1) noise-level scaling to optimize latent initialization; (2) prompt-level scaling for precise semantic guidance; and most notably, (3) reflection-level scaling, which explicitly provides actionable reflections to iteratively assess and correct previous generations. To facilitate reflection-level scaling, we construct GenRef, a large-scale dataset comprising 1 million triplets, each containing a reflection, a flawed image, and an enhanced image. Leveraging this dataset, we efficiently perform reflection tuning on state-of-the-art diffusion transformer, FLUX.1-dev, by jointly modeling multimodal inputs within a unified framework. Experimental results show that ReflectionFlow significantly outperforms naive noise-level scaling methods, offering a scalable and compute-efficient solution toward higher-quality image synthesis on challenging tasks.

Rui Liu, Yu Shen, Peng Gao et al.

Multi-modal learning has become a crucial technique for improving the performance of machine learning applications across domains such as autonomous driving, robotics, and perception systems. However, in certain scenarios, particularly in resource-constrained environments, some modalities available during training may be absent during inference. While existing frameworks effectively utilize multiple data sources during training and enable inference with reduced modalities, they are primarily designed for single-agent settings. This poses a critical limitation in dynamic environments such as connected autonomous vehicles (CAV), where incomplete data coverage can lead to decision-making blind spots. Conversely, some works explore multi-agent collaboration but without addressing missing modality at test time. To overcome these limitations, we propose Collaborative Auxiliary Modality Learning (CAML), a novel multi-modal multi-agent framework that enables agents to collaborate and share multi-modal data during training, while allowing inference with reduced modalities during testing. Experimental results in collaborative decision-making for CAV in accident-prone scenarios demonstrate that CAML achieves up to a ${\bf 58.1}\%$ improvement in accident detection. Additionally, we validate CAML on real-world aerial-ground robot data for collaborative semantic segmentation, achieving up to a ${\bf 10.6}\%$ improvement in mIoU.

Rui Liu, Zikang Wang, Peng Gao et al.

Autonomous systems have advanced significantly, but challenges persist in accident-prone environments where robust decision-making is crucial. A single vehicle's limited sensor range and obstructed views increase the likelihood of accidents. Multi-vehicle connected systems and multi-modal approaches, leveraging RGB images and LiDAR point clouds, have emerged as promising solutions. However, existing methods often assume the availability of all data modalities and connected vehicles during both training and testing, which is impractical due to potential sensor failures or missing connected vehicles. To address these challenges, we introduce a novel framework MMCD (Multi-Modal Collaborative Decision-making) for connected autonomy. Our framework fuses multi-modal observations from ego and collaborative vehicles to enhance decision-making under challenging conditions. To ensure robust performance when certain data modalities are unavailable during testing, we propose an approach based on cross-modal knowledge distillation with a teacher-student model structure. The teacher model is trained with multiple data modalities, while the student model is designed to operate effectively with reduced modalities. In experiments on $\textit{connected autonomous driving with ground vehicles}$ and $\textit{aerial-ground vehicles collaboration}$, our method improves driving safety by up to ${\it 20.7}\%$, surpassing the best-existing baseline in detecting potential accidents and making safe driving decisions. More information can be found on our website https://ruiiu.github.io/mmcd.

Peng Gao, Feng Gao, Peng Wang et al.

Multi-hop machine reading comprehension is a challenging task in natural language processing as it requires more reasoning ability across multiple documents. Spectral models based on graph convolutional networks have shown good inferring abilities and lead to competitive results. However, the analysis and reasoning of some are inconsistent with those of humans. Inspired by the concept of grandmother cells in cognitive neuroscience, we propose a heterogeneous graph attention network model named ClueReader to imitate the grandmother cell concept. The model is designed to assemble the semantic features in multi-level representations and automatically concentrate or alleviate information for reasoning through the attention mechanism. The name ClueReader is a metaphor for the pattern of the model: it regards the subjects of queries as the starting points of clues, takes the reasoning entities as bridge points, considers the latent candidate entities as grandmother cells, and the clues end up in candidate entities. The proposed model enables the visualization of the reasoning graph, making it possible to analyze the importance of edges connecting entities and the selectivity in the mention and candidate nodes, which is easier to comprehend empirically. Evaluations on the open-domain multi-hop reading dataset WikiHop and drug-drug interaction dataset MedHop proved the validity of ClueReader and showed the feasibility of its application of the model in the molecular biology domain.

Peng Gao, Shijie Geng, Yu Qiao et al.

Transformer has been widely adopted in Neural Machine Translation (NMT) because of its large capacity and parallel training of sequence generation. However, the deployment of Transformer is challenging because different scenarios require models of different complexities and scales. Naively training multiple Transformers is redundant in terms of both computation and memory. In this paper, we propose a novel Scalable Transformers, which naturally contains sub-Transformers of different scales and have shared parameters. Each sub-Transformer can be easily obtained by cropping the parameters of the largest Transformer. A three-stage training scheme is proposed to tackle the difficulty of training the Scalable Transformers, which introduces additional supervisions from word-level and sequence-level self-distillation. Extensive experiments were conducted on WMT EN-De and En-Fr to validate our proposed Scalable Transformers.

Mingyuan Mao, Renrui Zhang, Honghui Zheng et al.

Transformers with remarkable global representation capacities achieve competitive results for visual tasks, but fail to consider high-level local pattern information in input images. In this paper, we present a generic Dual-stream Network (DS-Net) to fully explore the representation capacity of local and global pattern features for image classification. Our DS-Net can simultaneously calculate fine-grained and integrated features and efficiently fuse them. Specifically, we propose an Intra-scale Propagation module to process two different resolutions in each block and an Inter-Scale Alignment module to perform information interaction across features at dual scales. Besides, we also design a Dual-stream FPN (DS-FPN) to further enhance contextual information for downstream dense predictions. Without bells and whistles, the proposed DS-Net outperforms DeiT-Small by 2.4% in terms of top-1 accuracy on ImageNet-1k and achieves state-of-the-art performance over other Vision Transformers and ResNets. For object detection and instance segmentation, DS-Net-Small respectively outperforms ResNet-50 by 6.4% and 5.5% in terms of mAP on MSCOCO 2017, and surpasses the previous state-of-the-art scheme, which significantly demonstrates its potential to be a general backbone in vision tasks. The code will be released soon.

Peng Gao, Minghang Zheng, Xiaogang Wang et al.

The recently proposed Detection Transformer (DETR) model successfully applies Transformer to objects detection and achieves comparable performance with two-stage object detection frameworks, such as Faster-RCNN. However, DETR suffers from its slow convergence. Training DETR \cite{carion2020end} from scratch needs 500 epochs to achieve a high accuracy. To accelerate its convergence, we propose a simple yet effective scheme for improving the DETR framework, namely Spatially Modulated Co-Attention (SMCA) mechanism. The core idea of SMCA is to conduct regression-aware co-attention in DETR by constraining co-attention responses to be high near initially estimated bounding box locations. Our proposed SMCA increases DETR's convergence speed by replacing the original co-attention mechanism in the decoder while keeping other operations in DETR unchanged. Furthermore, by integrating multi-head and scale-selection attention designs into SMCA, our fully-fledged SMCA can achieve better performance compared to DETR with a dilated convolution-based backbone (45.6 mAP at 108 epochs vs. 43.3 mAP at 500 epochs). We perform extensive ablation studies on COCO dataset to validate the effectiveness of the proposed SMCA.

Peng Gao, Chiori Hori, Shijie Geng et al.

In contrast with previous approaches where information flows only towards deeper layers of a stack, we consider a multi-pass transformer (MPT) architecture in which earlier layers are allowed to process information in light of the output of later layers. To maintain a directed acyclic graph structure, the encoder stack of a transformer is repeated along a new multi-pass dimension, keeping the parameters tied, and information is allowed to proceed unidirectionally both towards deeper layers within an encoder stack and towards any layer of subsequent stacks. We consider both soft (i.e., continuous) and hard (i.e., discrete) connections between parallel encoder stacks, relying on a neural architecture search to find the best connection pattern in the hard case. We perform an extensive ablation study of the proposed MPT architecture and compare it with other state-of-the-art transformer architectures. Surprisingly, Base Transformer equipped with MPT can surpass the performance of Large Transformer on the challenging machine translation En-De and En-Fr datasets. In the hard connection case, the optimal connection pattern found for En-De also leads to improved performance for En-Fr.

Shijie Geng, Peng Gao, Moitreya Chatterjee et al.

Given an input video, its associated audio, and a brief caption, the audio-visual scene aware dialog (AVSD) task requires an agent to indulge in a question-answer dialog with a human about the audio-visual content. This task thus poses a challenging multi-modal representation learning and reasoning scenario, advancements into which could influence several human-machine interaction applications. To solve this task, we introduce a semantics-controlled multi-modal shuffled Transformer reasoning framework, consisting of a sequence of Transformer modules, each taking a modality as input and producing representations conditioned on the input question. Our proposed Transformer variant uses a shuffling scheme on their multi-head outputs, demonstrating better regularization. To encode fine-grained visual information, we present a novel dynamic scene graph representation learning pipeline that consists of an intra-frame reasoning layer producing spatio-semantic graph representations for every frame, and an inter-frame aggregation module capturing temporal cues. Our entire pipeline is trained end-to-end. We present experiments on the benchmark AVSD dataset, both on answer generation and selection tasks. Our results demonstrate state-of-the-art performances on all evaluation metrics.

Keqi Wang, Peng Gao, Steven Hoi et al.

Low-light imaging is challenging since images may appear to be dark and noised due to low signal-to-noise ratio, complex image content, and the variety in shooting scenes in extreme low-light condition. Many methods have been proposed to enhance the imaging quality under extreme low-light conditions, but it remains difficult to obtain satisfactory results, especially when they attempt to retain high dynamic range (HDR). In this paper, we propose a novel method of multi-granulation cooperative networks (MCN) with bidirectional information flow to enhance extreme low-light images, and design an illumination map estimation function (IMEF) to preserve high dynamic range (HDR). To facilitate this research, we also contribute to create a new benchmark dataset of real-world Dark High Dynamic Range (DHDR) images to evaluate the performance of high dynamic preservation in low light environment. Experimental results show that the proposed method outperforms the state-of-the-art approaches in terms of both visual effects and quantitative analysis.

Shijie Geng, Ji Zhang, Zuohui Fu et al.

Different from short videos and GIFs, video stories contain clear plots and lists of principal characters. Without identifying the connection between appearing people and character names, a model is not able to obtain a genuine understanding of the plots. Video Story Question Answering (VSQA) offers an effective way to benchmark higher-level comprehension abilities of a model. However, current VSQA methods merely extract generic visual features from a scene. With such an approach, they remain prone to learning just superficial correlations. In order to attain a genuine understanding of who did what to whom, we propose a novel model that continuously refines character-aware relations. This model specifically considers the characters in a video story, as well as the relations connecting different characters and objects. Based on these signals, our framework enables weakly-supervised face naming through multi-instance co-occurrence matching and supports high-level reasoning utilizing Transformer structures. We train and test our model on the six diverse TV shows in the TVQA dataset, which is by far the largest and only publicly available dataset for VSQA. We validate our proposed approach over TVQA dataset through extensive ablation study.

Lei Shi, Shijie Geng, Kai Shuang et al.

Multi-modality fusion technologies have greatly improved the performance of neural network-based Video Description/Caption, Visual Question Answering (VQA) and Audio Visual Scene-aware Dialog (AVSD) over the recent years. Most previous approaches only explore the last layers of multiple layer feature fusion while omitting the importance of intermediate layers. To solve the issue for the intermediate layers, we propose an efficient Quaternion Block Network (QBN) to learn interaction not only for the last layer but also for all intermediate layers simultaneously. In our proposed QBN, we use the holistic text features to guide the update of visual features. In the meantime, Hamilton quaternion products can efficiently perform information flow from higher layers to lower layers for both visual and text modalities. The evaluation results show our QBN improved the performance on VQA 2.0, even though using surpass large scale BERT or visual BERT pre-trained models. Extensive ablation study has been carried out to testify the influence of each proposed module in this study.

Peng Gao, Qiquan Zhang, Fei Wang et al.

Although numerous recent tracking approaches have made tremendous advances in the last decade, achieving high-performance visual tracking remains a challenge. In this paper, we propose an end-to-end network model to learn reinforced attentional representation for accurate target object discrimination and localization. We utilize a novel hierarchical attentional module with long short-term memory and multi-layer perceptrons to leverage both inter- and intra-frame attention to effectively facilitate visual pattern emphasis. Moreover, we incorporate a contextual attentional correlation filter into the backbone network to make our model trainable in an end-to-end fashion. Our proposed approach not only takes full advantage of informative geometries and semantics but also updates correlation filters online without fine-tuning the backbone network to enable the adaptation of variations in the target object's appearance. Extensive experiments conducted on several popular benchmark datasets demonstrate that our proposed approach is effective and computationally efficient.

Peng Gao, Haoxuan You, Zhanpeng Zhang et al.

Exploiting relationships between visual regions and question words have achieved great success in learning multi-modality features for Visual Question Answering (VQA). However, we argue that existing methods mostly model relations between individual visual regions and words, which are not enough to correctly answer the question. From humans' perspective, answering a visual question requires understanding the summarizations of visual and language information. In this paper, we proposed the Multi-modality Latent Interaction module (MLI) to tackle this problem. The proposed module learns the cross-modality relationships between latent visual and language summarizations, which summarize visual regions and question into a small number of latent representations to avoid modeling uninformative individual region-word relations. The cross-modality information between the latent summarizations are propagated to fuse valuable information from both modalities and are used to update the visual and word features. Such MLI modules can be stacked for several stages to model complex and latent relations between the two modalities and achieves highly competitive performance on public VQA benchmarks, VQA v2.0 and TDIUC . In addition, we show that the performance of our methods could be significantly improved by combining with pre-trained language model BERT.

Zibin Zhou, Fei Wang, Wenjuan Xi et al.

Tracking living cells in video sequence is difficult, because of cell morphology and high similarities between cells. Tracking-by-detection methods are widely used in multi-cell tracking. We perform multi-cell tracking based on the cell centroid detection, and the performance of the detector has high impact on tracking performance. In this paper, UNet is utilized to extract inter-frame and intra-frame spatio-temporal information of cells. Detection performance of cells in mitotic phase is improved by multi-frame input. Good detection results facilitate multi-cell tracking. A mitosis detection algorithm is proposed to detect cell mitosis and the cell lineage is built up. Another UNet is utilized to acquire primary segmentation. Jointly using detection and primary segmentation, cells can be fine segmented in highly dense cell population. Experiments are conducted to evaluate the effectiveness of our method, and results show its state-of-the-art performance.

Qi Ni, Fei Wang, Ziwei Zhao et al.

Image feature extraction and matching is a fundamental but computation intensive task in machine vision. This paper proposes a novel FPGA-based embedded system to accelerate feature extraction and matching. It implements SURF feature point detection and BRIEF feature descriptor construction and matching. For binocular stereo vision, feature matching includes both tracking matching and stereo matching, which simultaneously provide feature point correspondences and parallax information. Our system is evaluated on a ZYNQ XC7Z045 FPGA. The result demonstrates that it can process binocular video data at a high frame rate (640$\times$480 @ 162fps). Moreover, an extensive test proves our system has robustness for image compression, blurring and illumination.

Peng Gao, Yipeng Ma, Ruyue Yuan et al.

Visual tracking is one of the most challenging computer vision problems. In order to achieve high performance visual tracking in various negative scenarios, a novel cascaded Siamese network is proposed and developed based on two different deep learning networks: a matching subnetwork and a classification subnetwork. The matching subnetwork is a fully convolutional Siamese network. According to the similarity score between the exemplar image and the candidate image, it aims to search possible object positions and crop scaled candidate patches. The classification subnetwork is designed to further evaluate the cropped candidate patches and determine the optimal tracking results based on the classification score. The matching subnetwork is trained offline and fixed online, while the classification subnetwork performs stochastic gradient descent online to learn more target-specific information. To improve the tracking performance further, an effective classification subnetwork update method based on both similarity and classification scores is utilized for updating the classification subnetwork. Extensive experimental results demonstrate that our proposed approach achieves state-of-the-art performance in recent benchmarks.

Peng Gao, Ruyue Yuan, Fei Wang et al.

In this paper, we investigate the impacts of three main aspects of visual tracking, i.e., the backbone network, the attentional mechanism, and the detection component, and propose a Siamese Attentional Keypoint Network, dubbed SATIN, for efficient tracking and accurate localization. Firstly, a new Siamese lightweight hourglass network is specially designed for visual tracking. It takes advantage of the benefits of the repeated bottom-up and top-down inference to capture more global and local contextual information at multiple scales. Secondly, a novel cross-attentional module is utilized to leverage both channel-wise and spatial intermediate attentional information, which can enhance both discriminative and localization capabilities of feature maps. Thirdly, a keypoints detection approach is invented to trace any target object by detecting the top-left corner point, the centroid point, and the bottom-right corner point of its bounding box. Therefore, our SATIN tracker not only has a strong capability to learn more effective object representations, but also is computational and memory storage efficiency, either during the training or testing stages. To the best of our knowledge, we are the first to propose this approach. Without bells and whistles, experimental results demonstrate that our approach achieves state-of-the-art performance on several recent benchmark datasets, at a speed far exceeding 27 frames per second.

Gao Peng, Zhengkai Jiang, Haoxuan You et al.

Learning effective fusion of multi-modality features is at the heart of visual question answering. We propose a novel method of dynamically fusing multi-modal features with intra- and inter-modality information flow, which alternatively pass dynamic information between and across the visual and language modalities. It can robustly capture the high-level interactions between language and vision domains, thus significantly improves the performance of visual question answering. We also show that the proposed dynamic intra-modality attention flow conditioned on the other modality can dynamically modulate the intra-modality attention of the target modality, which is vital for multimodality feature fusion. Experimental evaluations on the VQA 2.0 dataset show that the proposed method achieves state-of-the-art VQA performance. Extensive ablation studies are carried out for the comprehensive analysis of the proposed method.

Zelin Zhao, Gao Peng, Haoyu Wang et al.

In this paper, we present an accurate yet effective solution for 6D pose estimation from an RGB image. The core of our approach is that we first designate a set of surface points on target object model as keypoints and then train a keypoint detector (KPD) to localize them. Finally a PnP algorithm can recover the 6D pose according to the 2D-3D relationship of keypoints. Different from recent state-of-the-art CNN-based approaches that rely on a time-consuming post-processing procedure, our method can achieve competitive accuracy without any refinement after pose prediction. Meanwhile, we obtain a 30% relative improvement in terms of ADD accuracy among methods without using refinement. Moreover, we succeed in handling heavy occlusion by selecting the most confident keypoints to recover the 6D pose. For the sake of reproducibility, we will make our code and models publicly available soon.

Yipeng Ma, Chun Yuan, Peng Gao et al.

Correlation filter (CF) based tracking algorithms have demonstrated favorable performance recently. Nevertheless, the top performance trackers always employ complicated optimization methods which constraint their real-time applications. How to accelerate the tracking speed while retaining the tracking accuracy is a significant issue. In this paper, we propose a multi-level CF-based tracking approach named MLCFT which further explores the potential capacity of CF with two-stage detection: primal detection and oriented re-detection. The cascaded detection scheme is simple but competent to prevent model drift and accelerate the speed. An effective fusion method based on relative entropy is introduced to combine the complementary features extracted from deep and shallow layers of convolutional neural networks (CNN). Moreover, a novel online model update strategy is utilized in our tracker, which enhances the tracking performance further. Experimental results demonstrate that our proposed approach outperforms the most state-of-the-art trackers while tracking at speed of exceeded 16 frames per second on challenging benchmarks.

Ke Song, Chun Yuan, Peng Gao et al.

Visual tracking is one of the most important application areas of computer vision. At present, most algorithms are mainly implemented on PCs, and it is difficult to ensure real-time performance when applied in the real scenario. In order to improve the tracking speed and reduce the overall power consumption of visual tracking, this paper proposes a real-time visual tracking algorithm based on DSST(Discriminative Scale Space Tracking) approach. We implement a hardware system on Xilinx XC7K325T FPGA platform based on our proposed visual tracking algorithm. Our hardware system can run at more than 153 frames per second. In order to reduce the resource occupation, our system adopts the batch processing method in the feature extraction module. In the filter processing module, the FFT IP core is time-division multiplexed. Therefore, our hardware system utilizes LUTs and storage blocks of 33% and 40%, respectively. Test results show that the proposed visual tracking hardware system has excellent performance.