Peng Gao

Jiaming Han, Renrui Zhang, Wenqi Shao et al. · berkeley

We present ImageBind-LLM, a multi-modality instruction tuning method of large language models (LLMs) via ImageBind. Existing works mainly focus on language and image instruction tuning, different from which, our ImageBind-LLM can respond to multi-modality conditions, including audio, 3D point clouds, video, and their embedding-space arithmetic by only image-text alignment training. During training, we adopt a learnable bind network to align the embedding space between LLaMA and ImageBind's image encoder. Then, the image features transformed by the bind network are added to word tokens of all layers in LLaMA, which progressively injects visual instructions via an attention-free and zero-initialized gating mechanism. Aided by the joint embedding of ImageBind, the simple image-text training enables our model to exhibit superior multi-modality instruction-following capabilities. During inference, the multi-modality inputs are fed into the corresponding ImageBind encoders, and processed by a proposed visual cache model for further cross-modal embedding enhancement. The training-free cache model retrieves from three million image features extracted by ImageBind, which effectively mitigates the training-inference modality discrepancy. Notably, with our approach, ImageBind-LLM can respond to instructions of diverse modalities and demonstrate significant language generation quality. Code is released at https://github.com/OpenGVLab/LLaMA-Adapter.

Ziyu Guo, Renrui Zhang, Xiangyang Zhu et al.

We introduce SAM2Point, a preliminary exploration adapting Segment Anything Model 2 (SAM 2) for zero-shot and promptable 3D segmentation. SAM2Point interprets any 3D data as a series of multi-directional videos, and leverages SAM 2 for 3D-space segmentation, without further training or 2D-3D projection. Our framework supports various prompt types, including 3D points, boxes, and masks, and can generalize across diverse scenarios, such as 3D objects, indoor scenes, outdoor environments, and raw sparse LiDAR. Demonstrations on multiple 3D datasets, e.g., Objaverse, S3DIS, ScanNet, Semantic3D, and KITTI, highlight the robust generalization capabilities of SAM2Point. To our best knowledge, we present the most faithful implementation of SAM in 3D, which may serve as a starting point for future research in promptable 3D segmentation. Online Demo: https://huggingface.co/spaces/ZiyuG/SAM2Point . Code: https://github.com/ZiyuGuo99/SAM2Point .

Song Wen, Guian Fang, Renrui Zhang et al.

Recent advancements in text-to-image models, particularly diffusion models, have shown significant promise. However, compositional text-to-image models frequently encounter difficulties in generating high-quality images that accurately align with input texts describing multiple objects, variable attributes, and intricate spatial relationships. To address this limitation, we employ large vision-language models (LVLMs) for multi-dimensional assessment of the alignment between generated images and their corresponding input texts. Utilizing this assessment, we fine-tune the diffusion model to enhance its alignment capabilities. During the inference phase, an initial image is produced using the fine-tuned diffusion model. The LVLM is then employed to pinpoint areas of misalignment in the initial image, which are subsequently corrected using the image editing algorithm until no further misalignments are detected by the LVLM. The resultant image is consequently more closely aligned with the input text. Our experimental results validate that the proposed methodology significantly improves text-image alignment in compositional image generation, particularly with respect to object number, attribute binding, spatial relationships, and aesthetic quality.

Fanqing Meng, Wenqi Shao, Quanfeng Lu et al.

Charts play a vital role in data visualization, understanding data patterns, and informed decision-making. However, their unique combination of graphical elements (e.g., bars, lines) and textual components (e.g., labels, legends) poses challenges for general-purpose multimodal models. While vision-language models trained on chart data excel in comprehension, they struggle with generalization. To address these challenges, we propose ChartAssistant, a chart-based vision-language model for universal chart comprehension and reasoning. ChartAssistant leverages ChartSFT, a comprehensive dataset covering diverse chart-related tasks with basic (e.g. bars and pies) and specialized (e.g. radars, and bubbles) chart types. It undergoes a two-stage training process, starting with pre-training on chart-to-table parsing to align chart and text, followed by multitask instruction-following fine-tuning. This approach enables ChartAssistant to achieve competitive performance across various chart tasks. Experimental results demonstrate significant performance gains over the state-of-the-art UniChart and Chartllama method, especially outperforming them on real-world chart data with zero-shot setting. The code and data are available at https://github.com/OpenGVLab/ChartAst.

Peng Xu, Wenqi Shao, Mengzhao Chen et al.

Large language models (LLMs) have demonstrated outstanding performance in various tasks, such as text summarization, text question-answering, and etc. While their performance is impressive, the computational footprint due to their vast number of parameters can be prohibitive. Existing solutions such as SparseGPT and Wanda attempt to alleviate this issue through weight pruning. However, their layer-wise approach results in significant perturbation to the model's output and requires meticulous hyperparameter tuning, such as the pruning rate, which can adversely affect overall model performance. To address this, this paper introduces a novel LLM pruning technique dubbed blockwise parameter-efficient sparsity allocation (BESA) by applying a blockwise reconstruction loss. In contrast to the typical layer-wise pruning techniques, BESA is characterized by two distinctive attributes: i) it targets the overall pruning error with respect to individual transformer blocks, and ii) it allocates layer-specific sparsity in a differentiable manner, both of which ensure reduced performance degradation after pruning. Our experiments show that BESA achieves state-of-the-art performance, efficiently pruning LLMs like LLaMA1, and LLaMA2 with 7B to 70B parameters on a single A100 GPU in just five hours. Code is available at https://github.com/OpenGVLab/LLMPrune-BESA.

Dingning Liu, Xiaomeng Dong, Renrui Zhang et al.

In this work, we present a new visual prompting method called 3DAxiesPrompts (3DAP) to unleash the capabilities of GPT-4V in performing 3D spatial tasks. Our investigation reveals that while GPT-4V exhibits proficiency in discerning the position and interrelations of 2D entities through current visual prompting techniques, its abilities in handling 3D spatial tasks have yet to be explored. In our approach, we create a 3D coordinate system tailored to 3D imagery, complete with annotated scale information. By presenting images infused with the 3DAP visual prompt as inputs, we empower GPT-4V to ascertain the spatial positioning information of the given 3D target image with a high degree of precision. Through experiments, We identified three tasks that could be stably completed using the 3DAP method, namely, 2D to 3D Point Reconstruction, 2D to 3D point matching, and 3D Object Detection. We perform experiments on our proposed dataset 3DAP-Data, the results from these experiments validate the efficacy of 3DAP-enhanced GPT-4V inputs, marking a significant stride in 3D spatial task execution.

Peng Gao, Yujian Lee, Hui Zhang et al.

Visible-infrared person re-identification (VI-ReID) aims to match people with the same identity between visible and infrared modalities. VI-ReID is a challenging task due to the large differences in individual appearance under different modalities. Existing methods generally try to bridge the cross-modal differences at image or feature level, which lacks exploring the discriminative embeddings. Effectively minimizing these cross-modal discrepancies relies on obtaining representations that are guided by identity and consistent across modalities, while also filtering out representations that are irrelevant to identity. To address these challenges, we introduce a dynamic identity-guided attention network (DIAN) to mine identity-guided and modality-consistent embeddings, facilitating effective bridging the gap between different modalities. Specifically, in DIAN, to pursue a semantically richer representation, we first use orthogonal projection to fuse the features from two connected coarse and fine layers. Furthermore, we first use dynamic convolution kernels to mine identity-guided and modality-consistent representations. More notably, a cross embedding balancing loss is introduced to effectively bridge cross-modal discrepancies by above embeddings. Experimental results on SYSU-MM01 and RegDB datasets show that DIAN achieves state-of-the-art performance. Specifically, for indoor search on SYSU-MM01, our method achieves 86.28% rank-1 accuracy and 87.41% mAP, respectively. Our code will be available soon.

Jiaquan Ye, Xianbiao Qi, Yelin He et al.

This paper presents our solution for ICDAR 2021 competition on scientific literature parsing taskB: table recognition to HTML. In our method, we divide the table content recognition task into foursub-tasks: table structure recognition, text line detection, text line recognition, and box assignment.Our table structure recognition algorithm is customized based on MASTER [1], a robust image textrecognition algorithm. PSENet [2] is used to detect each text line in the table image. For text linerecognition, our model is also built on MASTER. Finally, in the box assignment phase, we associatedthe text boxes detected by PSENet with the structure item reconstructed by table structure prediction,and fill the recognized content of the text line into the corresponding item. Our proposed methodachieves a 96.84% TEDS score on 9,115 validation samples in the development phase, and a 96.32%TEDS score on 9,064 samples in the final evaluation phase.

Yelin He, Xianbiao Qi, Jiaquan Ye et al.

This paper presents our solution for the ICDAR 2021 Competition on Scientific Table Image Recognition to LaTeX. This competition has two sub-tasks: Table Structure Reconstruction (TSR) and Table Content Reconstruction (TCR). We treat both sub-tasks as two individual image-to-sequence recognition problems. We leverage our previously proposed algorithm MASTER \cite{lu2019master}, which is originally proposed for scene text recognition. We optimize the MASTER model from several perspectives: network structure, optimizer, normalization method, pre-trained model, resolution of input image, data augmentation, and model ensemble. Our method achieves 0.7444 Exact Match and 0.8765 Exact Match @95\% on the TSR task, and obtains 0.5586 Exact Match and 0.7386 Exact Match 95\% on the TCR task.

Peng Gao, Rui Guo, Hongsheng Lu et al.

Collaborative object localization aims to collaboratively estimate locations of objects observed from multiple views or perspectives, which is a critical ability for multi-agent systems such as connected vehicles. To enable collaborative localization, several model-based state estimation and learning-based localization methods have been developed. Given their encouraging performance, model-based state estimation often lacks the ability to model the complex relationships among multiple objects, while learning-based methods are typically not able to fuse the observations from an arbitrary number of views and cannot well model uncertainty. In this paper, we introduce a novel spatiotemporal graph filter approach that integrates graph learning and model-based estimation to perform multi-view sensor fusion for collaborative object localization. Our approach models complex object relationships using a new spatiotemporal graph representation and fuses multi-view observations in a Bayesian fashion to improve location estimation under uncertainty. We evaluate our approach in the applications of connected autonomous driving and multiple pedestrian localization. Experimental results show that our approach outperforms previous techniques and achieves the state-of-the-art performance on collaboration localization.

Zhencai Hu, Peng Gao, Fei Wang

Unmanned aircraft systems can perform some more dangerous and difficult missions than manned aircraft systems. In some highly complicated and changeable tasks, such as air combat, the maneuvering decision mechanism is required to sense the combat situation accurately and make the optimal strategy in real-time. This paper presents a formulation of a 3-D one-on-one air combat maneuvering problem and an approximate dynamic programming approach for computing an optimal policy on autonomous maneuvering decision making. The aircraft learns combat strategies in a Reinforcement Leaning method, while sensing the environment, taking available maneuvering actions and getting feedback reward signals. To solve the problem of dimensional explosion in the air combat, the proposed method is implemented through feature selection, trajectory sampling, function approximation and Bellman backup operation in the air combat simulation environment. This approximate dynamic programming approach provides a fast response to a rapidly changing tactical situation, learns in long-term planning, without any explicitly coded air combat rule base.