Multimodal transformer exhibits high capacity and flexibility to align image and text for visual grounding. However, the existing encoder-only grounding framework (e.g., TransVG) suffers from heavy computation due to the self-attention operation with quadratic time complexity. To address this issue, we present a new multimodal transformer architecture, coined as Dynamic Mutilmodal DETR (Dynamic MDETR), by decoupling the whole grounding process into encoding and decoding phases. The key observation is that there exists high spatial redundancy in images. Thus, we devise a new dynamic multimodal transformer decoder by exploiting this sparsity prior to speed up the visual grounding process. Specifically, our dynamic decoder is composed of a 2D adaptive sampling module and a text guided decoding module. The sampling module aims to select these informative patches by predicting the offsets with respect to a reference point, while the decoding module works for extracting the grounded object information by performing cross attention between image features and text features. These two modules are stacked alternatively to gradually bridge the modality gap and iteratively refine the reference point of grounded object, eventually realizing the objective of visual grounding. Extensive experiments on five benchmarks demonstrate that our proposed Dynamic MDETR achieves competitive trade-offs between computation and accuracy. Notably, using only 9% feature points in the decoder, we can reduce ~44% GFLOPs of the multimodal transformer, but still get higher accuracy than the encoder-only counterpart. In addition, to verify its generalization ability and scale up our Dynamic MDETR, we build the first one-stage CLIP empowered visual grounding framework, and achieve the state-of-the-art performance on these benchmarks.
相關內容
We introduce a novel task of 3D visual grounding in monocular RGB images using language descriptions with both appearance and geometry information. Specifically, we build a large-scale dataset, Mono3DRefer, which contains 3D object targets with their corresponding geometric text descriptions, generated by ChatGPT and refined manually. To foster this task, we propose Mono3DVG-TR, an end-to-end transformer-based network, which takes advantage of both the appearance and geometry information in text embeddings for multi-modal learning and 3D object localization. Depth predictor is designed to explicitly learn geometry features. The dual text-guided adapter is proposed to refine multiscale visual and geometry features of the referred object. Based on depth-text-visual stacking attention, the decoder fuses object-level geometric cues and visual appearance into a learnable query. Comprehensive benchmarks and some insightful analyses are provided for Mono3DVG. Extensive comparisons and ablation studies show that our method significantly outperforms all baselines. The dataset and code will be publicly available at: //github.com/ZhanYang-nwpu/Mono3DVG.
We present DrivingGaussian, an efficient and effective framework for surrounding dynamic autonomous driving scenes. For complex scenes with moving objects, we first sequentially and progressively model the static background of the entire scene with incremental static 3D Gaussians. We then leverage a composite dynamic Gaussian graph to handle multiple moving objects, individually reconstructing each object and restoring their accurate positions and occlusion relationships within the scene. We further use a LiDAR prior for Gaussian Splatting to reconstruct scenes with greater details and maintain panoramic consistency. DrivingGaussian outperforms existing methods in driving scene reconstruction and enables photorealistic surround-view synthesis with high-fidelity and multi-camera consistency. The source code and trained models will be released.
In Near Memory Processing (NMP), processing elements(PEs) are placed near the 3D memory, reducing unnecessary data transfers between the CPU and the memory. However, as the CPUs and the PEs of the NMP use a shared memory space, maintaining coherency between them is a challenge. Most current literature relies on maintaining coherence for fine-grained or coarse-grained instruction granularities for the offloaded code blocks. We understand that for most NMP-offloaded instructions, the coherence conflict is low, and waiting for the coherence transaction hinders the performance. We construct an analytical model for an existing coherence strategy called CONDA, which is within 4% accuracy. This model indicates the key parameters responsible - the granularity of offloaded code, probability of conflicts, transaction times, and commit time. This paper identifies the prospective optimizations using the analytical model for CONDA. It proposes a new coherence scheme called MRCN: Monitored Rollback Coherence for NMP. MRCN addresses the coherence issue while eliminating unnecessary re-executions with limited hardware overhead. The MRCN is evaluated on synthetic as well as Rodinia benchmarks. The analytical results are within 4% accuracy of the simulation results. The MRCN shows improvement of upto 25% over CONDA strategy for the same benchmark under different execution conditions.
Recently, an audio-visual segmentation (AVS) task has been introduced, aiming to group pixels with sounding objects within a given video. This task necessitates a first-ever audio-driven pixel-level understanding of the scene, posing significant challenges. In this paper, we propose an innovative audio-visual transformer framework, termed COMBO, an acronym for COoperation of Multi-order Bilateral relatiOns. For the first time, our framework explores three types of bilateral entanglements within AVS: pixel entanglement, modality entanglement, and temporal entanglement. Regarding pixel entanglement, we employ a Siam-Encoder Module (SEM) that leverages prior knowledge to generate more precise visual features from the foundational model. For modality entanglement, we design a Bilateral-Fusion Module (BFM), enabling COMBO to align corresponding visual and auditory signals bi-directionally. As for temporal entanglement, we introduce an innovative adaptive inter-frame consistency loss according to the inherent rules of temporal. Comprehensive experiments and ablation studies on AVSBench-object (84.7 mIoU on S4, 59.2 mIou on MS3) and AVSBench-semantic (42.1 mIoU on AVSS) datasets demonstrate that COMBO surpasses previous state-of-the-art methods. Code and more results will be publicly available at //combo-avs.github.io/.
Recently, the incredible progress of large language models (LLMs) has ignited the spark of task automation, which decomposes the complex tasks described by user instructions into sub-tasks, and invokes external tools to execute them, and plays a central role in autonomous agents. However, there lacks a systematic and standardized benchmark to foster the development of LLMs in task automation. To this end, we introduce TaskBench to evaluate the capability of LLMs in task automation. Specifically, task automation can be formulated into three critical stages: task decomposition, tool invocation, and parameter prediction to fulfill user intent. This complexity makes data collection and evaluation more challenging compared to common NLP tasks. To generate high-quality evaluation datasets, we introduce the concept of Tool Graph to represent the decomposed tasks in user intent, and adopt a back-instruct method to simulate user instruction and annotations. Furthermore, we propose TaskEval to evaluate the capability of LLMs from different aspects, including task decomposition, tool invocation, and parameter prediction. Experimental results demonstrate that TaskBench can effectively reflects the capability of LLMs in task automation. Benefiting from the mixture of automated data construction and human verification, TaskBench achieves a high consistency compared to the human evaluation, which can be utilized as a comprehensive and faithful benchmark for LLM-based autonomous agents.
Recently, diffusion-based generative models have achieved remarkable success for image generation and edition. However, their use for video editing still faces important limitations. This paper introduces VidEdit, a novel method for zero-shot text-based video editing ensuring strong temporal and spatial consistency. Firstly, we propose to combine atlas-based and pre-trained text-to-image diffusion models to provide a training-free and efficient editing method, which by design fulfills temporal smoothness. Secondly, we leverage off-the-shelf panoptic segmenters along with edge detectors and adapt their use for conditioned diffusion-based atlas editing. This ensures a fine spatial control on targeted regions while strictly preserving the structure of the original video. Quantitative and qualitative experiments show that VidEdit outperforms state-of-the-art methods on DAVIS dataset, regarding semantic faithfulness, image preservation, and temporal consistency metrics. With this framework, processing a single video only takes approximately one minute, and it can generate multiple compatible edits based on a unique text prompt. Project web-page at //videdit.github.io
This study delves into the application of Generative Adversarial Networks (GANs) within the context of imbalanced datasets. Our primary aim is to enhance the performance and stability of GANs in such datasets. In pursuit of this objective, we introduce a novel network architecture known as Damage GAN, building upon the ContraD GAN framework which seamlessly integrates GANs and contrastive learning. Through the utilization of contrastive learning, the discriminator is trained to develop an unsupervised representation capable of distinguishing all provided samples. Our approach draws inspiration from the straightforward framework for contrastive learning of visual representations (SimCLR), leading to the formulation of a distinctive loss function. We also explore the implementation of self-damaging contrastive learning (SDCLR) to further enhance the optimization of the ContraD GAN model. Comparative evaluations against baseline models including the deep convolutional GAN (DCGAN) and ContraD GAN demonstrate the evident superiority of our proposed model, Damage GAN, in terms of generated image distribution, model stability, and image quality when applied to imbalanced datasets.
Point Cloud Registration (PCR) is a critical and challenging task in computer vision. One of the primary difficulties in PCR is identifying salient and meaningful points that exhibit consistent semantic and geometric properties across different scans. Previous methods have encountered challenges with ambiguous matching due to the similarity among patch blocks throughout the entire point cloud and the lack of consideration for efficient global geometric consistency. To address these issues, we propose a new framework that includes several novel techniques. Firstly, we introduce a semantic-aware geometric encoder that combines object-level and patch-level semantic information. This encoder significantly improves registration recall by reducing ambiguity in patch-level superpoint matching. Additionally, we incorporate a prior knowledge approach that utilizes an intrinsic shape signature to identify salient points. This enables us to extract the most salient super points and meaningful dense points in the scene. Secondly, we introduce an innovative transformer that encodes High-Order (HO) geometric features. These features are crucial for identifying salient points within initial overlap regions while considering global high-order geometric consistency. To optimize this high-order transformer further, we introduce an anchor node selection strategy. By encoding inter-frame triangle or polyhedron consistency features based on these anchor nodes, we can effectively learn high-order geometric features of salient super points. These high-order features are then propagated to dense points and utilized by a Sinkhorn matching module to identify key correspondences for successful registration. In our experiments conducted on well-known datasets such as 3DMatch/3DLoMatch and KITTI, our approach has shown promising results, highlighting the effectiveness of our novel method.
Diffusion models (DMs) have shown great potential for high-quality image synthesis. However, when it comes to producing images with complex scenes, how to properly describe both image global structures and object details remains a challenging task. In this paper, we present Frido, a Feature Pyramid Diffusion model performing a multi-scale coarse-to-fine denoising process for image synthesis. Our model decomposes an input image into scale-dependent vector quantized features, followed by a coarse-to-fine gating for producing image output. During the above multi-scale representation learning stage, additional input conditions like text, scene graph, or image layout can be further exploited. Thus, Frido can be also applied for conditional or cross-modality image synthesis. We conduct extensive experiments over various unconditioned and conditional image generation tasks, ranging from text-to-image synthesis, layout-to-image, scene-graph-to-image, to label-to-image. More specifically, we achieved state-of-the-art FID scores on five benchmarks, namely layout-to-image on COCO and OpenImages, scene-graph-to-image on COCO and Visual Genome, and label-to-image on COCO. Code is available at //github.com/davidhalladay/Frido.
Images can convey rich semantics and induce various emotions in viewers. Recently, with the rapid advancement of emotional intelligence and the explosive growth of visual data, extensive research efforts have been dedicated to affective image content analysis (AICA). In this survey, we will comprehensively review the development of AICA in the recent two decades, especially focusing on the state-of-the-art methods with respect to three main challenges -- the affective gap, perception subjectivity, and label noise and absence. We begin with an introduction to the key emotion representation models that have been widely employed in AICA and description of available datasets for performing evaluation with quantitative comparison of label noise and dataset bias. We then summarize and compare the representative approaches on (1) emotion feature extraction, including both handcrafted and deep features, (2) learning methods on dominant emotion recognition, personalized emotion prediction, emotion distribution learning, and learning from noisy data or few labels, and (3) AICA based applications. Finally, we discuss some challenges and promising research directions in the future, such as image content and context understanding, group emotion clustering, and viewer-image interaction.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191