Recent advancements in text-to-image models have significantly enhanced image generation capabilities, yet a notable gap of open-source models persists in bilingual or Chinese language support. To address this need, we present Taiyi-Diffusion-XL, a new Chinese and English bilingual text-to-image model which is developed by extending the capabilities of CLIP and Stable-Diffusion-XL through a process of bilingual continuous pre-training. This approach includes the efficient expansion of vocabulary by integrating the most frequently used Chinese characters into CLIP's tokenizer and embedding layers, coupled with an absolute position encoding expansion. Additionally, we enrich text prompts by large vision-language model, leading to better images captions and possess higher visual quality. These enhancements are subsequently applied to downstream text-to-image models. Our empirical results indicate that the developed CLIP model excels in bilingual image-text retrieval.Furthermore, the bilingual image generation capabilities of Taiyi-Diffusion-XL surpass previous models. This research leads to the development and open-sourcing of the Taiyi-Diffusion-XL model, representing a notable advancement in the field of image generation, particularly for Chinese language applications. This contribution is a step forward in addressing the need for more diverse language support in multimodal research. The model and demonstration are made publicly available at \href{https://huggingface.co/IDEA-CCNL/Taiyi-Stable-Diffusion-XL-3.5B/}{this https URL}, fostering further research and collaboration in this domain.
In a scenario where multi-modal cameras are operating together, the problem of working with non-aligned images cannot be avoided. Yet, existing image fusion algorithms rely heavily on strictly registered input image pairs to produce more precise fusion results, as a way to improve the performance of downstream high-level vision tasks. In order to relax this assumption, one can attempt to register images first. However, the existing methods for registering multiple modalities have limitations, such as complex structures and reliance on significant semantic information. This paper aims to address the problem of image registration and fusion in a single framework, called BusRef. We focus on Infrared-Visible image registration and fusion task (IVRF). In this framework, the input unaligned image pairs will pass through three stages: Coarse registration, Fine registration and Fusion. It will be shown that the unified approach enables more robust IVRF. We also propose a novel training and evaluation strategy, involving the use of masks to reduce the influence of non-reconstructible regions on the loss functions, which greatly improves the accuracy and robustness of the fusion task. Last but not least, a gradient-aware fusion network is designed to preserve the complementary information. The advanced performance of this algorithm is demonstrated by
With the open-sourcing of text-to-image models (T2I) such as stable diffusion (SD) and stable diffusion XL (SD-XL), there is an influx of models fine-tuned in specific domains based on the open-source SD model, such as in anime, character portraits, etc. However, there are few specialized models in certain domains, such as interior design, which is attributed to the complex textual descriptions and detailed visual elements inherent in design, alongside the necessity for adaptable resolution. Therefore, text-to-image models for interior design are required to have outstanding prompt-following capabilities, as well as iterative collaboration with design professionals to achieve the desired outcome. In this paper, we collect and optimize text-image data in the design field and continue training in both English and Chinese on the basis of the open-source CLIP model. We also proposed a fine-tuning strategy with curriculum learning and reinforcement learning from CLIP feedback to enhance the prompt-following capabilities of our approach so as to improve the quality of image generation. The experimental results on the collected dataset demonstrate the effectiveness of the proposed approach, which achieves impressive results and outperforms strong baselines.
Large Vision Language Models (LVLMs) have demonstrated impressive zero-shot capabilities in various vision-language dialogue scenarios. However, the absence of fine-grained visual object detection hinders the model from understanding the details of images, leading to irreparable visual hallucinations and factual errors. In this paper, we propose Lyrics, a novel multi-modal pre-training and instruction fine-tuning paradigm that bootstraps vision-language alignment from fine-grained cross-modal collaboration. Building on the foundation of BLIP-2, Lyrics infuses local visual features extracted from a visual refiner that includes image tagging, object detection and semantic segmentation modules into the Querying Transformer, while on the text side, the language inputs equip the boundary boxes and tags derived from the visual refiner. We further introduce a two-stage training scheme, in which the pre-training stage bridges the modality gap through explicit and comprehensive vision-language alignment targets. During the instruction fine-tuning stage, we introduce semantic-aware visual feature extraction, a crucial method that enables the model to extract informative features from concrete visual objects. Our approach achieves strong performance on 13 held-out datasets across various vision-language tasks, and demonstrates promising multi-modal understanding and detailed depiction capabilities in real dialogue scenarios.
3D object detection in Bird's-Eye-View (BEV) space has recently emerged as a prevalent approach in the field of autonomous driving. Despite the demonstrated improvements in accuracy and velocity estimation compared to perspective view methods, the deployment of BEV-based techniques in real-world autonomous vehicles remains challenging. This is primarily due to their reliance on vision-transformer (ViT) based architectures, which introduce quadratic complexity with respect to the input resolution. To address this issue, we propose an efficient BEV-based 3D detection framework called BEVENet, which leverages a convolutional-only architectural design to circumvent the limitations of ViT models while maintaining the effectiveness of BEV-based methods. Our experiments show that BEVENet is 3$\times$ faster than contemporary state-of-the-art (SOTA) approaches on the NuScenes challenge, achieving a mean average precision (mAP) of 0.456 and a nuScenes detection score (NDS) of 0.555 on the NuScenes validation dataset, with an inference speed of 47.6 frames per second. To the best of our knowledge, this study stands as the first to achieve such significant efficiency improvements for BEV-based methods, highlighting their enhanced feasibility for real-world autonomous driving applications.
Various large language models (LLMs) have been proposed in recent years, including closed- and open-source ones, continually setting new records on multiple benchmarks. However, the development of LLMs still faces several issues, such as high cost of training models from scratch, and continual pre-training leading to catastrophic forgetting, etc. Although many such issues are addressed along the line of research on LLMs, an important yet practical limitation is that many studies overly pursue enlarging model sizes without comprehensively analyzing and optimizing the use of pre-training data in their learning process, as well as appropriate organization and leveraging of such data in training LLMs under cost-effective settings. In this work, we propose Ziya2, a model with 13 billion parameters adopting LLaMA2 as the foundation model, and further pre-trained on 700 billion tokens, where we focus on pre-training techniques and use data-centric optimization to enhance the learning process of Ziya2 on different stages. Experiments show that Ziya2 significantly outperforms other models in multiple benchmarks especially with promising results compared to representative open-source ones. Ziya2 (Base) is released at https://huggingface.co/IDEA-CCNL/Ziya2-13B-Base and https://modelscope.cn/models/Fengshenbang/Ziya2-13B-Base/summary.
Recent advancements enlarge the capabilities of large language models (LLMs) in zero-shot image-to-text generation and understanding by integrating multi-modal inputs. However, such success is typically limited to English scenarios due to the lack of large-scale and high-quality non-English multi-modal resources, making it extremely difficult to establish competitive counterparts in other languages. In this paper, we introduce the Ziya-Visual series, a set of bilingual large-scale vision-language models (LVLMs) designed to incorporate visual semantics into LLM for multi-modal dialogue. Composed of Ziya-Visual-Base and Ziya-Visual-Chat, our models adopt the Querying Transformer from BLIP-2, further exploring the assistance of optimization schemes such as instruction tuning, multi-stage training and low-rank adaptation module for visual-language alignment. In addition, we stimulate the understanding ability of GPT-4 in multi-modal scenarios, translating our gathered English image-text datasets into Chinese and generating instruction-response through the in-context learning method. The experiment results demonstrate that compared to the existing LVLMs, Ziya-Visual achieves competitive performance across a wide range of English-only tasks including zero-shot image-text retrieval, image captioning, and visual question answering. The evaluation leaderboard accessed by GPT-4 also indicates that our models possess satisfactory image-text understanding and generation capabilities in Chinese multi-modal scenario dialogues. Code, demo and models are available at ~\url{https://huggingface.co/IDEA-CCNL/Ziya-BLIP2-14B-Visual-v1}.
Recent advancements enlarge the capabilities of large language models (LLMs) in zero-shot image-to-text generation and understanding by integrating multi-modal inputs. However, such success is typically limited to English scenarios due to the lack of large-scale and high-quality non-English multi-modal resources, making it extremely difficult to establish competitive counterparts in other languages. In this paper, we introduce the Ziya-VL series, a set of bilingual large-scale vision-language models (LVLMs) designed to incorporate visual semantics into LLM for multi-modal dialogue. Composed of Ziya-VL-Base and Ziya-VL-Chat, our models adopt the Querying Transformer from BLIP-2, further exploring the assistance of optimization schemes such as instruction tuning, multi-stage training and low-rank adaptation module for visual-language alignment. In addition, we stimulate the understanding ability of GPT-4 in multi-modal scenarios, translating our gathered English image-text datasets into Chinese and generating instruction-response through the in-context learning method. The experiment results demonstrate that compared to the existing LVLMs, Ziya-VL achieves competitive performance across a wide range of English-only tasks including zero-shot image-text retrieval, image captioning, and visual question answering. The evaluation leaderboard accessed by GPT-4 also indicates that our models possess satisfactory image-text understanding and generation capabilities in Chinese multi-modal scenario dialogues. Code, demo and models are available at ~\url{https://huggingface.co/IDEA-CCNL/Ziya-BLIP2-14B-Visual-v1}.
In the field of remote sensing, we often utilize oriented bounding boxes (OBB) to bound the objects. This approach significantly reduces the overlap among dense detection boxes and minimizes the inclusion of background content within the bounding boxes. To enhance the detection accuracy of oriented objects, we propose a unique loss function based on edge gradients, inspired by the similarity measurement function used in template matching task. During this process, we address the issues of non-differentiability of the function and the semantic alignment between gradient vectors in ground truth (GT) boxes and predicted boxes (PB). Experimental results show that our proposed loss function achieves $0.6\%$ mAP improvement compared to the commonly used Smooth L1 loss in the baseline algorithm. Additionally, we design an edge-based self-attention module to encourage the detection network to focus more on the object edges. Leveraging these two innovations, we achieve a mAP increase of 1.3% on the DOTA dataset.