Chen Chen

Xian Zhong, Zipeng Li, Shuqin Chen et al.

Video captioning aims to generate natural language sentences that describe the given video accurately. Existing methods obtain favorable generation by exploring richer visual representations in encode phase or improving the decoding ability. However, the long-tailed problem hinders these attempts at low-frequency tokens, which rarely occur but carry critical semantics, playing a vital role in the detailed generation. In this paper, we introduce a novel Refined Semantic enhancement method towards Frequency Diffusion (RSFD), a captioning model that constantly perceives the linguistic representation of the infrequent tokens. Concretely, a Frequency-Aware Diffusion (FAD) module is proposed to comprehend the semantics of low-frequency tokens to break through generation limitations. In this way, the caption is refined by promoting the absorption of tokens with insufficient occurrence. Based on FAD, we design a Divergent Semantic Supervisor (DSS) module to compensate for the information loss of high-frequency tokens brought by the diffusion process, where the semantics of low-frequency tokens is further emphasized to alleviate the long-tailed problem. Extensive experiments indicate that RSFD outperforms the state-of-the-art methods on two benchmark datasets, i.e., MSR-VTT and MSVD, demonstrate that the enhancement of low-frequency tokens semantics can obtain a competitive generation effect. Code is available at https://github.com/lzp870/RSFD.

Defeng Xie, Ruichen Wang, Jian Ma et al.

We introduce a new generative system called Edit Everything, which can take image and text inputs and produce image outputs. Edit Everything allows users to edit images using simple text instructions. Our system designs prompts to guide the visual module in generating requested images. Experiments demonstrate that Edit Everything facilitates the implementation of the visual aspects of Stable Diffusion with the use of Segment Anything model and CLIP. Our system is publicly available at https://github.com/DefengXie/Edit_Everything.

Yuxin Wen, Yuchen Liu, Chen Chen et al.

Recent breakthroughs in diffusion models have exhibited exceptional image-generation capabilities. However, studies show that some outputs are merely replications of training data. Such replications present potential legal challenges for model owners, especially when the generated content contains proprietary information. In this work, we introduce a straightforward yet effective method for detecting memorized prompts by inspecting the magnitude of text-conditional predictions. Our proposed method seamlessly integrates without disrupting sampling algorithms, and delivers high accuracy even at the first generation step, with a single generation per prompt. Building on our detection strategy, we unveil an explainable approach that shows the contribution of individual words or tokens to memorization. This offers an interactive medium for users to adjust their prompts. Moreover, we propose two strategies i.e., to mitigate memorization by leveraging the magnitude of text-conditional predictions, either through minimization during inference or filtering during training. These proposed strategies effectively counteract memorization while maintaining high-generation quality. Code is available at https://github.com/YuxinWenRick/diffusion_memorization.

Jian Ma, Yonglin Deng, Chen Chen et al.

Posters play a crucial role in marketing and advertising by enhancing visual communication and brand visibility, making significant contributions to industrial design. With the latest advancements in controllable T2I diffusion models, increasing research has focused on rendering text within synthesized images. Despite improvements in text rendering accuracy, the field of automatic poster generation remains underexplored. In this paper, we propose an automatic poster generation framework with text rendering capabilities leveraging LLMs, utilizing a triple-cross attention mechanism based on alignment learning. This framework aims to create precise poster text within a detailed contextual background. Additionally, the framework supports controllable fonts, adjustable image resolution, and the rendering of posters with descriptions and text in both English and Chinese.Furthermore, we introduce a high-resolution font dataset and a poster dataset with resolutions exceeding 1024 pixels. Our approach leverages the SDXL architecture. Extensive experiments validate our method's capability in generating poster images with complex and contextually rich backgrounds.Codes is available at https://github.com/OPPO-Mente-Lab/GlyphDraw2.

Chen Chen, Yuchen Hu, Chao-Han Huck Yang et al. · gatech

Code-switching (CS) speech refers to the phenomenon of mixing two or more languages within the same sentence. Despite the recent advances in automatic speech recognition (ASR), CS-ASR is still a challenging task ought to the grammatical structure complexity of the phenomenon and the data scarcity of specific training corpus. In this work, we propose to leverage large language models (LLMs) and lists of hypotheses generated by an ASR to address the CS problem. Specifically, we first employ multiple well-trained ASR models for N-best hypotheses generation, with the aim of increasing the diverse and informative elements in the set of hypotheses. Next, we utilize the LLMs to learn the hypotheses-to-transcription (H2T) mapping by adding a trainable low-rank adapter. Such a generative error correction (GER) method directly predicts the accurate transcription according to its expert linguistic knowledge and N-best hypotheses, resulting in a paradigm shift from the traditional language model rescoring or error correction techniques. Experimental evidence demonstrates that GER significantly enhances CS-ASR accuracy, in terms of reduced mixed error rate (MER). Furthermore, LLMs show remarkable data efficiency for H2T learning, providing a potential solution to the data scarcity problem of CS-ASR in low-resource languages.

Jian Ma, Chen Chen, Qingsong Xie et al.

Text-to-image diffusion models are well-known for their ability to generate realistic images based on textual prompts. However, the existing works have predominantly focused on English, lacking support for non-English text-to-image models. The most commonly used translation methods cannot solve the generation problem related to language culture, while training from scratch on a specific language dataset is prohibitively expensive. In this paper, we are inspired to propose a simple plug-and-play language transfer method based on knowledge distillation. All we need to do is train a lightweight MLP-like parameter-efficient adapter (PEA) with only 6M parameters under teacher knowledge distillation along with a small parallel data corpus. We are surprised to find that freezing the parameters of UNet can still achieve remarkable performance on the language-specific prompt evaluation set, demonstrating that PEA can stimulate the potential generation ability of the original UNet. Additionally, it closely approaches the performance of the English text-to-image model on a general prompt evaluation set. Furthermore, our adapter can be used as a plugin to achieve significant results in downstream tasks in cross-lingual text-to-image generation. Code will be available at: https://github.com/OPPO-Mente-Lab/PEA-Diffusion

Tom Tongjia Chen, Hongshan Yu, Zhengeng Yang et al.

Affordance-Centric Question-driven Task Completion (AQTC) has been proposed to acquire knowledge from videos to furnish users with comprehensive and systematic instructions. However, existing methods have hitherto neglected the necessity of aligning spatiotemporal visual and linguistic signals, as well as the crucial interactional information between humans and objects. To tackle these limitations, we propose to combine large-scale pre-trained vision-language and video-language models, which serve to contribute stable and reliable multimodal data and facilitate effective spatiotemporal visual-textual alignment. Additionally, a novel hand-object-interaction (HOI) aggregation module is proposed which aids in capturing human-object interaction information, thereby further augmenting the capacity to understand the presented scenario. Our method achieved first place in the CVPR'2023 AQTC Challenge, with a Recall@1 score of 78.7\%. The code is available at https://github.com/tomchen-ctj/CVPR23-LOVEU-AQTC.

Chen Chen, Bowen Zhang, Liangliang Cao et al.

Image and text retrieval is one of the foundational tasks in the vision and language domain with multiple real-world applications. State-of-the-art approaches, e.g. CLIP, ALIGN, represent images and texts as dense embeddings and calculate the similarity in the dense embedding space as the matching score. On the other hand, sparse semantic features like bag-of-words models are more interpretable, but believed to suffer from inferior accuracy than dense representations. In this work, we show that it is possible to build a sparse semantic representation that is as powerful as, or even better than, dense presentations. We extend the CLIP model and build a sparse text and image representation (STAIR), where the image and text are mapped to a sparse token space. Each token in the space is a (sub-)word in the vocabulary, which is not only interpretable but also easy to integrate with existing information retrieval systems. STAIR model significantly outperforms a CLIP model with +$4.9\%$ and +$4.3\%$ absolute Recall@1 improvement on COCO-5k text$\rightarrow$image and image$\rightarrow$text retrieval respectively. It also achieved better performance on both of ImageNet zero-shot and linear probing compared to CLIP.

Jian Ma, Junhao Liang, Chen Chen et al.

Recent progress in personalized image generation using diffusion models has been significant. However, development in the area of open-domain and non-fine-tuning personalized image generation is proceeding rather slowly. In this paper, we propose Subject-Diffusion, a novel open-domain personalized image generation model that, in addition to not requiring test-time fine-tuning, also only requires a single reference image to support personalized generation of single- or multi-subject in any domain. Firstly, we construct an automatic data labeling tool and use the LAION-Aesthetics dataset to construct a large-scale dataset consisting of 76M images and their corresponding subject detection bounding boxes, segmentation masks and text descriptions. Secondly, we design a new unified framework that combines text and image semantics by incorporating coarse location and fine-grained reference image control to maximize subject fidelity and generalization. Furthermore, we also adopt an attention control mechanism to support multi-subject generation. Extensive qualitative and quantitative results demonstrate that our method outperforms other SOTA frameworks in single, multiple, and human customized image generation. Please refer to our \href{https://oppo-mente-lab.github.io/subject_diffusion/}{project page}

Zhe Zhao, Yudong Li, Cheng Hou et al.

Recently, the success of pre-training in text domain has been fully extended to vision, audio, and cross-modal scenarios. The proposed pre-training models of different modalities are showing a rising trend of homogeneity in their model structures, which brings the opportunity to implement different pre-training models within a uniform framework. In this paper, we present TencentPretrain, a toolkit supporting pre-training models of different modalities. The core feature of TencentPretrain is the modular design. The toolkit uniformly divides pre-training models into 5 components: embedding, encoder, target embedding, decoder, and target. As almost all of common modules are provided in each component, users can choose the desired modules from different components to build a complete pre-training model. The modular design enables users to efficiently reproduce existing pre-training models or build brand-new one. We test the toolkit on text, vision, and audio benchmarks and show that it can match the performance of the original implementations.

Chen Chen, Wei Emma Zhang, Alireza Seyed Shakeri et al.

Despite the great development of document summarisation techniques nowadays, factual inconsistencies between the generated summaries and the original texts still occur from time to time. This study explores the possibility of adopting prompts to incorporate factual knowledge into generated summaries. We specifically study prefix-tuning that uses a set of trainable continuous prefix prompts together with discrete natural language prompts to aid summary generation. Experimental results demonstrate that the trainable prefixes can help the summarisation model extract information from discrete prompts precisely, thus generating knowledge-preserving summaries that are factually consistent with the discrete prompts. The ROUGE improvements of the generated summaries indicate that explicitly adding factual knowledge into the summarisation process could boost the overall performance, showing great potential for applying it to other natural language processing tasks.

Tongjia Chen, Hongshan Yu, Zhengeng Yang et al.

Due to the resource-intensive nature of training vision-language models on expansive video data, a majority of studies have centered on adapting pre-trained image-language models to the video domain. Dominant pipelines propose to tackle the visual discrepancies with additional temporal learners while overlooking the substantial discrepancy for web-scaled descriptive narratives and concise action category names, leading to less distinct semantic space and potential performance limitations. In this work, we prioritize the refinement of text knowledge to facilitate generalizable video recognition. To address the limitations of the less distinct semantic space of category names, we prompt a large language model (LLM) to augment action class names into Spatio-Temporal Descriptors thus bridging the textual discrepancy and serving as a knowledge base for general recognition. Moreover, to assign the best descriptors with different video instances, we propose Optimal Descriptor Solver, forming the video recognition problem as solving the optimal matching flow across frame-level representations and descriptors. Comprehensive evaluations in zero-shot, few-shot, and fully supervised video recognition highlight the effectiveness of our approach. Our best model achieves a state-of-the-art zero-shot accuracy of 75.1% on Kinetics-600.

Jian Ma, Mingjun Zhao, Chen Chen et al.

Recent breakthroughs in the field of language-guided image generation have yielded impressive achievements, enabling the creation of high-quality and diverse images based on user instructions.Although the synthesis performance is fascinating, one significant limitation of current image generation models is their insufficient ability to generate text coherently within images, particularly for complex glyph structures like Chinese characters. To address this problem, we introduce GlyphDraw, a general learning framework aiming to endow image generation models with the capacity to generate images coherently embedded with text for any specific language.We first sophisticatedly design the image-text dataset's construction strategy, then build our model specifically on a diffusion-based image generator and carefully modify the network structure to allow the model to learn drawing language characters with the help of glyph and position information.Furthermore, we maintain the model's open-domain image synthesis capability by preventing catastrophic forgetting by using parameter-efficient fine-tuning techniques.Extensive qualitative and quantitative experiments demonstrate that our method not only produces accurate language characters as in prompts, but also seamlessly blends the generated text into the background.Please refer to our \href{https://1073521013.github.io/glyph-draw.github.io/}{project page}. \end{abstract}

Sijia Li, Chen Chen, Haonan Lu

Diffusion-model-based text-guided image generation has recently made astounding progress, producing fascinating results in open-domain image manipulation tasks. Few models, however, currently have complete zero-shot capabilities for both global and local image editing due to the complexity and diversity of image manipulation tasks. In this work, we propose a method with a mixture-of-expert (MOE) controllers to align the text-guided capacity of diffusion models with different kinds of human instructions, enabling our model to handle various open-domain image manipulation tasks with natural language instructions. First, we use large language models (ChatGPT) and conditional image synthesis models (ControlNet) to generate a large number of global image transfer dataset in addition to the instruction-based local image editing dataset. Then, using an MOE technique and task-specific adaptation training on a large-scale dataset, our conditional diffusion model can edit images globally and locally. Extensive experiments demonstrate that our approach performs surprisingly well on various image manipulation tasks when dealing with open-domain images and arbitrary human instructions. Please refer to our project page: [https://oppo-mente-lab.github.io/moe_controller/]

Ming Li, Taojiannan Yang, Huafeng Kuang et al.

To enhance the controllability of text-to-image diffusion models, existing efforts like ControlNet incorporated image-based conditional controls. In this paper, we reveal that existing methods still face significant challenges in generating images that align with the image conditional controls. To this end, we propose ControlNet++, a novel approach that improves controllable generation by explicitly optimizing pixel-level cycle consistency between generated images and conditional controls. Specifically, for an input conditional control, we use a pre-trained discriminative reward model to extract the corresponding condition of the generated images, and then optimize the consistency loss between the input conditional control and extracted condition. A straightforward implementation would be generating images from random noises and then calculating the consistency loss, but such an approach requires storing gradients for multiple sampling timesteps, leading to considerable time and memory costs. To address this, we introduce an efficient reward strategy that deliberately disturbs the input images by adding noise, and then uses the single-step denoised images for reward fine-tuning. This avoids the extensive costs associated with image sampling, allowing for more efficient reward fine-tuning. Extensive experiments show that ControlNet++ significantly improves controllability under various conditional controls. For example, it achieves improvements over ControlNet by 11.1% mIoU, 13.4% SSIM, and 7.6% RMSE, respectively, for segmentation mask, line-art edge, and depth conditions. All the code, models, demo and organized data have been open sourced on our Github Repo.

Yuchen Hu, Chen Chen, Siyin Wang et al.

In this paper, we propose reverse inference optimization (RIO), a simple and effective method designed to enhance the robustness of autoregressive-model-based zero-shot text-to-speech (TTS) systems using reinforcement learning from human feedback (RLHF). To assess the quality of speech produced by the TTS system without human annotations, RIO introduces a novel concept termed as reverse inference based on the Bayesian principle, which suggests that a high-quality generated speech should be able to be used as a prompt for subsequent generation using the same TTS model. By leveraging reverse inference as the standard to select exemplars used in RLHF from the speech samples generated by the TTS system itself, RIO steers the subsequent optimization towards a direction of enhancing the TTS robustness. The RIO framework, comprising sampling, automatic annotating, and learning, obviates the need for a reward model or pairwise preference data, and significantly improves the stability of zero-shot TTS performance by reducing the discrepancies between training and inference conditions. Our experimental results verify that RIO can effectively improve both subjective and objective metrics, including mean opinion scores, word error rates, and speaker similarity. Remarkably, RIO can also diminish the incidence of bad outputs to nearly zero percent, rivalling the robustness when using ground-truth speech as the prompt.

Chen Chen, Daochang Liu, Chang Xu

Pretrained diffusion models and their outputs are widely accessible due to their exceptional capacity for synthesizing high-quality images and their open-source nature. The users, however, may face litigation risks owing to the models' tendency to memorize and regurgitate training data during inference. To address this, we introduce Anti-Memorization Guidance (AMG), a novel framework employing three targeted guidance strategies for the main causes of memorization: image and caption duplication, and highly specific user prompts. Consequently, AMG ensures memorization-free outputs while maintaining high image quality and text alignment, leveraging the synergy of its guidance methods, each indispensable in its own right. AMG also features an innovative automatic detection system for potential memorization during each step of inference process, allows selective application of guidance strategies, minimally interfering with the original sampling process to preserve output utility. We applied AMG to pretrained Denoising Diffusion Probabilistic Models (DDPM) and Stable Diffusion across various generation tasks. The results demonstrate that AMG is the first approach to successfully eradicates all instances of memorization with no or marginal impacts on image quality and text-alignment, as evidenced by FID and CLIP scores.

Shuo Liu, Weize Quan, Ming Zhou et al.

Videos contain multi-modal content, and exploring multi-level cross-modal interactions with natural language queries can provide great prominence to text-video retrieval task (TVR). However, new trending methods applying large-scale pre-trained model CLIP for TVR do not focus on multi-modal cues in videos. Furthermore, the traditional methods simply concatenating multi-modal features do not exploit fine-grained cross-modal information in videos. In this paper, we propose a multi-level multi-modal hybrid fusion (M2HF) network to explore comprehensive interactions between text queries and each modality content in videos. Specifically, M2HF first utilizes visual features extracted by CLIP to early fuse with audio and motion features extracted from videos, obtaining audio-visual fusion features and motion-visual fusion features respectively. Multi-modal alignment problem is also considered in this process. Then, visual features, audio-visual fusion features, motion-visual fusion features, and texts extracted from videos establish cross-modal relationships with caption queries in a multi-level way. Finally, the retrieval outputs from all levels are late fused to obtain final text-video retrieval results. Our framework provides two kinds of training strategies, including an ensemble manner and an end-to-end manner. Moreover, a novel multi-modal balance loss function is proposed to balance the contributions of each modality for efficient end-to-end training. M2HF allows us to obtain state-of-the-art results on various benchmarks, eg, Rank@1 of 64.9\%, 68.2\%, 33.2\%, 57.1\%, 57.8\% on MSR-VTT, MSVD, LSMDC, DiDeMo, and ActivityNet, respectively.

Youbo Lei, Feifei He, Chen Chen et al.

Due to the success of large-scale visual-language pretraining (VLP) models and the widespread use of image-text retrieval in industry areas, it is now critically necessary to reduce the model size and streamline their mobile-device deployment. Single- and dual-stream model structures are commonly used in image-text retrieval with the goal of closing the semantic gap between textual and visual modalities. While single-stream models use deep feature fusion to achieve more accurate cross-model alignment, dual-stream models are better at offline indexing and fast inference.We propose a Multi-teacher Cross-modality Alignment Distillation (MCAD) technique to integrate the advantages of single- and dual-stream models. By incorporating the fused single-stream features into the image and text features of the dual-stream model, we formulate new modified teacher similarity distributions and features. Then, we conduct both distribution and feature distillation to boost the capability of the student dual-stream model, achieving high retrieval performance without increasing inference complexity.Extensive experiments demonstrate the remarkable performance and high efficiency of MCAD on image-text retrieval tasks. Furthermore, we implement a lightweight CLIP model on Snapdragon/Dimensity chips with only $\sim$100M running memory and $\sim$8.0ms search latency, achieving the mobile-device application of VLP models.

Zhaoning Wang, Ming Li, Chen Chen

With the recent development of generative models, Text-to-3D generations have also seen significant growth, opening a door for creating video-game 3D assets from a more general public. Nonetheless, people without any professional 3D editing experience would find it hard to achieve precise control over the 3D generation, especially if there are multiple objects in the prompt, as using text to control often leads to missing objects and imprecise locations. In this paper, we present LucidDreaming as an effective pipeline capable of spatial and numerical control over 3D generation from only textual prompt commands or 3D bounding boxes. Specifically, our research demonstrates that Large Language Models (LLMs) possess 3D spatial awareness and can effectively translate textual 3D information into precise 3D bounding boxes. We leverage LLMs to get individual object information and their 3D bounding boxes as the initial step of our process. Then with the bounding boxes, We further propose clipped ray sampling and object-centric density blob bias to generate 3D objects aligning with the bounding boxes. We show that our method exhibits remarkable adaptability across a spectrum of mainstream Score Distillation Sampling-based 3D generation frameworks and our pipeline can even used to insert objects into an existing NeRF scene. Moreover, we also provide a dataset of prompts with 3D bounding boxes, benchmarking 3D spatial controllability. With extensive qualitative and quantitative experiments, we demonstrate that LucidDreaming achieves superior results in object placement precision and generation fidelity compared to current approaches, while maintaining flexibility and ease of use for non-expert users.

Cuifeng Shen, Yulu Gan, Chen Chen et al.

The goal of conditional image-to-video (cI2V) generation is to create a believable new video by beginning with the condition, i.e., one image and text.The previous cI2V generation methods conventionally perform in RGB pixel space, with limitations in modeling motion consistency and visual continuity. Additionally, the efficiency of generating videos in pixel space is quite low.In this paper, we propose a novel approach to address these challenges by disentangling the target RGB pixels into two distinct components: spatial content and temporal motions. Specifically, we predict temporal motions which include motion vector and residual based on a 3D-UNet diffusion model. By explicitly modeling temporal motions and warping them to the starting image, we improve the temporal consistency of generated videos. This results in a reduction of spatial redundancy, emphasizing temporal details. Our proposed method achieves performance improvements by disentangling content and motion, all without introducing new structural complexities to the model. Extensive experiments on various datasets confirm our approach's superior performance over the majority of state-of-the-art methods in both effectiveness and efficiency.

Chen Chen, Enhuai Liu, Daochang Liu et al.

Diffusion models, widely used for image and video generation, face a significant limitation: the risk of memorizing and reproducing training data during inference, potentially generating unauthorized copyrighted content. While prior research has focused on image diffusion models (IDMs), video diffusion models (VDMs) remain underexplored. To address this gap, we first formally define the two types of memorization in VDMs (content memorization and motion memorization) in a practical way that focuses on privacy preservation and applies to all generation types. We then introduce new metrics specifically designed to separately assess content and motion memorization in VDMs. Additionally, we curate a dataset of text prompts that are most prone to triggering memorization when used as conditioning in VDMs. By leveraging these prompts, we generate diverse videos from various open-source VDMs, successfully extracting numerous training videos from each tested model. Through the application of our proposed metrics, we systematically analyze memorization across various pretrained VDMs, including text-conditional and unconditional models, on a variety of datasets. Our comprehensive study reveals that memorization is widespread across all tested VDMs, indicating that VDMs can also memorize image training data in addition to video datasets. Finally, we propose efficient and effective detection strategies for both content and motion memorization, offering a foundational approach for improving privacy in VDMs.

Zhenyi Liao, Qingsong Xie, Chen Chen et al.

Diffusion models (DMs) have achieved significant success in generating imaginative images given textual descriptions. However, they are likely to fall short when it comes to real-life scenarios with intricate details. The low-quality, unrealistic human faces in text-to-image generation are one of the most prominent issues, hindering the wide application of DMs in practice. Targeting addressing such an issue, we first assess the face quality of generations from popular pre-trained DMs with the aid of human annotators and then evaluate the alignment between existing metrics with human judgments. Observing that existing metrics can be unsatisfactory for quantifying face quality, we develop a novel metric named FaceScore (FS) by fine-tuning the widely used ImageReward on a dataset of (win, loss) face pairs cheaply crafted by an inpainting pipeline of DMs. Extensive studies reveal FS enjoys a superior alignment with humans. On the other hand, FS opens up the door for enhancing DMs for better face generation. With FS offering image ratings, we can easily perform preference learning algorithms to refine DMs like SDXL. Comprehensive experiments verify the efficacy of our approach for improving face quality. The code is released at https://github.com/OPPO-Mente-Lab/FaceScore.

Ruichen Wang, Zekang Chen, Chen Chen et al.

Recent text-to-image (T2I) diffusion models show outstanding performance in generating high-quality images conditioned on textual prompts. However, they fail to semantically align the generated images with the prompts due to their limited compositional capabilities, leading to attribute leakage, entity leakage, and missing entities. In this paper, we propose a novel attention mask control strategy based on predicted object boxes to address these issues. In particular, we first train a BoxNet to predict a box for each entity that possesses the attribute specified in the prompt. Then, depending on the predicted boxes, a unique mask control is applied to the cross- and self-attention maps. Our approach produces a more semantically accurate synthesis by constraining the attention regions of each token in the prompt to the image. In addition, the proposed method is straightforward and effective and can be readily integrated into existing cross-attention-based T2I generators. We compare our approach to competing methods and demonstrate that it can faithfully convey the semantics of the original text to the generated content and achieve high availability as a ready-to-use plugin. Please refer to https://github.com/OPPOMente-Lab/attention-mask-control.

Yue He, Chen Chen, Jing Zhang et al.

Existing Scene Text Recognition (STR) methods typically use a language model to optimize the joint probability of the 1D character sequence predicted by a visual recognition (VR) model, which ignore the 2D spatial context of visual semantics within and between character instances, making them not generalize well to arbitrary shape scene text. To address this issue, we make the first attempt to perform textual reasoning based on visual semantics in this paper. Technically, given the character segmentation maps predicted by a VR model, we construct a subgraph for each instance, where nodes represent the pixels in it and edges are added between nodes based on their spatial similarity. Then, these subgraphs are sequentially connected by their root nodes and merged into a complete graph. Based on this graph, we devise a graph convolutional network for textual reasoning (GTR) by supervising it with a cross-entropy loss. GTR can be easily plugged in representative STR models to improve their performance owing to better textual reasoning. Specifically, we construct our model, namely S-GTR, by paralleling GTR to the language model in a segmentation-based STR baseline, which can effectively exploit the visual-linguistic complementarity via mutual learning. S-GTR sets new state-of-the-art on six challenging STR benchmarks and generalizes well to multi-linguistic datasets. Code is available at https://github.com/adeline-cs/GTR.

Xiandong Meng, Xuan Deng, Shuyuan Zhu et al.

In video compression, most of the existing deep learning approaches concentrate on the visual quality of a single frame, while ignoring the useful priors as well as the temporal information of adjacent frames. In this paper, we propose a multi-frame guided attention network (MGANet) to enhance the quality of compressed videos. Our network is composed of a temporal encoder that discovers inter-frame relations, a guided encoder-decoder subnet that encodes and enhances the visual patterns of target frame, and a multi-supervised reconstruction component that aggregates information to predict details. We design a bidirectional residual convolutional LSTM unit to implicitly discover frames variations over time with respect to the target frame. Meanwhile, the guided map is proposed to guide our network to concentrate more on the block boundary. Our approach takes advantage of intra-frame prior information and inter-frame information to improve the quality of compressed video. Experimental results show the robustness and superior performance of the proposed method.Code is available at https://github.com/mengab/MGANet

Haotian Zhang, Haoxuan You, Philipp Dufter et al.

While Ferret seamlessly integrates regional understanding into the Large Language Model (LLM) to facilitate its referring and grounding capability, it poses certain limitations: constrained by the pre-trained fixed visual encoder and failed to perform well on broader tasks. In this work, we unveil Ferret-v2, a significant upgrade to Ferret, with three key designs. (1) Any resolution grounding and referring: A flexible approach that effortlessly handles higher image resolution, improving the model's ability to process and understand images in greater detail. (2) Multi-granularity visual encoding: By integrating the additional DINOv2 encoder, the model learns better and diverse underlying contexts for global and fine-grained visual information. (3) A three-stage training paradigm: Besides image-caption alignment, an additional stage is proposed for high-resolution dense alignment before the final instruction tuning. Experiments show that Ferret-v2 provides substantial improvements over Ferret and other state-of-the-art methods, thanks to its high-resolution scaling and fine-grained visual processing.

Zonglin Lyu, Ming Li, Xinxin Liu et al.

To enhance controllability in text-to-image generation, ControlNet introduces image-based control signals, while ControlNet++ improves pixel-level cycle consistency between generated images and the input control signal. To avoid the prohibitive cost of back-propagating through the sampling process, ControlNet++ optimizes only low-noise timesteps (e.g., $t < 200$) using a single-step approximation, which not only ignores the contribution of high-noise timesteps but also introduces additional approximation errors. A straightforward alternative for optimizing controllability across all timesteps is Direct Preference Optimization (DPO), a fine-tuning method that increases model preference for more controllable images ($I^{w}$) over less controllable ones ($I^{l}$). However, due to uncertainty in generative models, it is difficult to ensure that win--lose image pairs differ only in controllability while keeping other factors, such as image quality, fixed. To address this, we propose performing preference learning over control conditions rather than generated images. Specifically, we construct winning and losing control signals, $\mathbf{c}^{w}$ and $\mathbf{c}^{l}$, and train the model to prefer $\mathbf{c}^{w}$. This method, which we term \textit{Condition Preference Optimization} (CPO), eliminates confounding factors and yields a low-variance training objective. Our approach theoretically exhibits lower contrastive loss variance than DPO and empirically achieves superior results. Moreover, CPO requires less computation and storage for dataset curation. Extensive experiments show that CPO significantly improves controllability over the state-of-the-art ControlNet++ across multiple control types: over $10\%$ error rate reduction in segmentation, $70$--$80\%$ in human pose, and consistent $2$--$5\%$ reductions in edge and depth maps.

Yifan Wang, Yafei Liu, Chufan Shi et al.

Instruction tuning effectively optimizes Large Language Models (LLMs) for downstream tasks. Due to the changing environment in real-life applications, LLMs necessitate continual task-specific adaptation without catastrophic forgetting. Considering the heavy computational cost, replay-based Continual Learning (CL) methods are the simplest and most widely used for LLMs to address the forgetting issue. However, traditional replay-based methods do not fully utilize instructions to customize the replay strategy. In this work, we propose a novel paradigm called Instruction-based Continual Learning (InsCL). InsCL dynamically replays previous data based on task similarity, calculated by Wasserstein Distance with instructions. Moreover, we further introduce an Instruction Information Metric (InsInfo) to quantify the complexity and diversity of instructions. According to InsInfo, InsCL guides the replay process more inclined to high-quality data. We conduct extensive experiments over 16 tasks with different training orders, observing consistent performance improvements of InsCL. When all tasks have been trained, InsCL achieves performance gains of 3.0 Relative Gain compared with Random Replay, and 27.96 Relative Gain compared with No Replay.

Yuchen Hu, Chen Chen, Chao-Han Huck Yang et al.

Recent advances in large language models (LLMs) have stepped forward the development of multilingual speech and machine translation by its reduced representation errors and incorporated external knowledge. However, both translation tasks typically utilize beam search decoding and top-1 hypothesis selection for inference. These techniques struggle to fully exploit the rich information in the diverse N-best hypotheses, making them less optimal for translation tasks that require a single, high-quality output sequence. In this paper, we propose a new generative paradigm for translation tasks, namely "GenTranslate", which builds upon LLMs to generate better results from the diverse translation versions in N-best list. Leveraging the rich linguistic knowledge and strong reasoning abilities of LLMs, our new paradigm can integrate the rich information in N-best candidates to generate a higher-quality translation result. Furthermore, to support LLM finetuning, we build and release a HypoTranslate dataset that contains over 592K hypotheses-translation pairs in 11 languages. Experiments on various speech and machine translation benchmarks (e.g., FLEURS, CoVoST-2, WMT) demonstrate that our GenTranslate significantly outperforms the state-of-the-art model.

Hongjian Liu, Qingsong Xie, TianXiang Ye et al.

The iterative sampling procedure employed by diffusion models (DMs) often leads to significant inference latency. To address this, we propose Stochastic Consistency Distillation (SCott) to enable accelerated text-to-image generation, where high-quality and diverse generations can be achieved within just 2-4 sampling steps. In contrast to vanilla consistency distillation (CD) which distills the ordinary differential equation solvers-based sampling process of a pre-trained teacher model into a student, SCott explores the possibility and validates the efficacy of integrating stochastic differential equation (SDE) solvers into CD to fully unleash the potential of the teacher. SCott is augmented with elaborate strategies to control the noise strength and sampling process of the SDE solver. An adversarial loss is further incorporated to strengthen the consistency constraints in rare sampling steps. Empirically, on the MSCOCO-2017 5K dataset with a Stable Diffusion-V1.5 teacher, SCott achieves an FID of 21.9 with 2 sampling steps, surpassing that of the 1-step InstaFlow (23.4) and the 4-step UFOGen (22.1). Moreover, SCott can yield more diverse samples than other consistency models for high-resolution image generation, with up to 16% improvement in a qualified metric.

Nazmul Karim, Hasan Iqbal, Umar Khalid et al.

Text-to-Image (T2I) diffusion models have recently gained traction for their versatility and user-friendliness in 2D content generation and editing. However, training a diffusion model specifically for 3D scene editing is challenging due to the scarcity of large-scale datasets. Currently, editing 3D scenes necessitates either retraining the model to accommodate various 3D edits or developing specific methods tailored to each unique editing type. Moreover, state-of-the-art (SOTA) techniques require multiple synchronized edited images from the same scene to enable effective scene editing. Given the current limitations of T2I models, achieving consistent editing effects across multiple images remains difficult, leading to multi-view inconsistency in editing. This inconsistency undermines the performance of 3D scene editing when these images are utilized. In this study, we introduce a novel, training-free 3D scene editing technique called \textsc{Free-Editor}, which enables users to edit 3D scenes without the need for model retraining during the testing phase. Our method effectively addresses the issue of multi-view style inconsistency found in state-of-the-art (SOTA) methods through the implementation of a single-view editing scheme. Specifically, we demonstrate that editing a particular 3D scene can be achieved by modifying only a single view. To facilitate this, we present an Edit Transformer that ensures intra-view consistency and inter-view style transfer using self-view and cross-view attention mechanisms, respectively. By eliminating the need for model retraining and multi-view editing, our approach significantly reduces editing time and memory resource requirements, achieving runtimes approximately 20 times faster than SOTA methods. We have performed extensive experiments on various benchmark datasets, showcasing the diverse editing capabilities of our proposed technique.

Chen Chen, Daochang Liu, Mubarak Shah et al.

Text-to-image diffusion models have achieved unprecedented proficiency in generating realistic images. However, their inherent tendency to memorize and replicate training data during inference raises significant concerns, including potential copyright infringement. In response, various methods have been proposed to evaluate, detect, and mitigate memorization. Our analysis reveals that existing approaches significantly underperform in handling local memorization, where only specific image regions are memorized, compared to global memorization, where the entire image is replicated. Also, they cannot locate the local memorization regions, making it hard to investigate locally. To address these, we identify a novel "bright ending" (BE) anomaly in diffusion models prone to memorizing training images. BE refers to a distinct cross-attention pattern observed in text-to-image diffusion models, where memorized image patches exhibit significantly greater attention to the final text token during the last inference step than non-memorized patches. This pattern highlights regions where the generated image replicates training data and enables efficient localization of memorized regions. Equipped with this, we propose a simple yet effective method to integrate BE into existing frameworks, significantly improving their performance by narrowing the performance gap caused by local memorization. Our results not only validate the successful execution of the new localization task but also establish new state-of-the-art performance across all existing tasks, underscoring the significance of the BE phenomenon.

Wenhan Wu, Zhishuai Guo, Chen Chen et al.

Zero-shot skeleton-based action recognition aims to develop models capable of identifying actions beyond the categories encountered during training. Previous approaches have primarily focused on aligning visual and semantic representations but often overlooked the importance of fine-grained action patterns in the semantic space (e.g., the hand movements in drinking water and brushing teeth). To address these limitations, we propose a Frequency-Semantic Enhanced Variational Autoencoder (FS-VAE) to explore the skeleton semantic representation learning with frequency decomposition. FS-VAE consists of three key components: 1) a frequency-based enhancement module with high- and low-frequency adjustments to enrich the skeletal semantics learning and improve the robustness of zero-shot action recognition; 2) a semantic-based action description with multilevel alignment to capture both local details and global correspondence, effectively bridging the semantic gap and compensating for the inherent loss of information in skeleton sequences; 3) a calibrated cross-alignment loss that enables valid skeleton-text pairs to counterbalance ambiguous ones, mitigating discrepancies and ambiguities in skeleton and text features, thereby ensuring robust alignment. Evaluations on the benchmarks demonstrate the effectiveness of our approach, validating that frequency-enhanced semantic features enable robust differentiation of visually and semantically similar action clusters, improving zero-shot action recognition.

Hao Ai, Zidong Cao, Haonan Lu et al.

360 images, with a field-of-view (FoV) of 180x360, provide immersive and realistic environments for emerging virtual reality (VR) applications, such as virtual tourism, where users desire to create diverse panoramic scenes from a narrow FoV photo they take from a viewpoint via portable devices. It thus brings us to a technical challenge: `How to allow the users to freely create diverse and immersive virtual scenes from a narrow FoV image with a specified viewport?' To this end, we propose a transformer-based 360 image outpainting framework called Dream360, which can generate diverse, high-fidelity, and high-resolution panoramas from user-selected viewports, considering the spherical properties of 360 images. Compared with existing methods, e.g., [3], which primarily focus on inputs with rectangular masks and central locations while overlooking the spherical property of 360 images, our Dream360 offers higher outpainting flexibility and fidelity based on the spherical representation. Dream360 comprises two key learning stages: (I) codebook-based panorama outpainting via Spherical-VQGAN (S-VQGAN), and (II) frequency-aware refinement with a novel frequency-aware consistency loss. Specifically, S-VQGAN learns a sphere-specific codebook from spherical harmonic (SH) values, providing a better representation of spherical data distribution for scene modeling. The frequency-aware refinement matches the resolution and further improves the semantic consistency and visual fidelity of the generated results. Our Dream360 achieves significantly lower Frechet Inception Distance (FID) scores and better visual fidelity than existing methods. We also conducted a user study involving 15 participants to interactively evaluate the quality of the generated results in VR, demonstrating the flexibility and superiority of our Dream360 framework.

Letian Zhang, Ming Li, Chen Chen et al.

Neural radiance fields (NeRF) is a promising approach for generating photorealistic images and representing complex scenes. However, when processing data sequentially, it can suffer from catastrophic forgetting, where previous data is easily forgotten after training with new data. Existing incremental learning methods using knowledge distillation assume that continuous data chunks contain both 2D images and corresponding camera pose parameters, pre-estimated from the complete dataset. This poses a paradox as the necessary camera pose must be estimated from the entire dataset, even though the data arrives sequentially and future chunks are inaccessible. In contrast, we focus on a practical scenario where camera poses are unknown. We propose IL-NeRF, a novel framework for incremental NeRF training, to address this challenge. IL-NeRF's key idea lies in selecting a set of past camera poses as references to initialize and align the camera poses of incoming image data. This is followed by a joint optimization of camera poses and replay-based NeRF distillation. Our experiments on real-world indoor and outdoor scenes show that IL-NeRF handles incremental NeRF training and outperforms the baselines by up to $54.04\%$ in rendering quality.

Nazmul Karim, Umar Khalid, Mohsen Joneidi et al.

Text-to-Image (T2I) diffusion models have achieved remarkable success in synthesizing high-quality images conditioned on text prompts. Recent methods have tried to replicate the success by either training text-to-video (T2V) models on a very large number of text-video pairs or adapting T2I models on text-video pairs independently. Although the latter is computationally less expensive, it still takes a significant amount of time for per-video adaption. To address this issue, we propose SAVE, a novel spectral-shift-aware adaptation framework, in which we fine-tune the spectral shift of the parameter space instead of the parameters themselves. Specifically, we take the spectral decomposition of the pre-trained T2I weights and only update the singular values while freezing the corresponding singular vectors. In addition, we introduce a spectral shift regularizer aimed at placing tighter constraints on larger singular values compared to smaller ones. This form of regularization enables the model to grasp finer details within the video that align with the provided textual descriptions. We also offer theoretical justification for our proposed regularization technique. Since we are only dealing with spectral shifts, the proposed method reduces the adaptation time significantly (approx. 10 times) and has fewer resource constraints for training. Such attributes posit SAVE to be more suitable for real-world applications, e.g. editing undesirable content during video streaming. We validate the effectiveness of SAVE with an extensive experimental evaluation under different settings, e.g. style transfer, object replacement, privacy preservation, etc.

Wenxuan Wang, Jing Liu, Xingjian He et al.

Referring image segmentation (RIS) is a fundamental vision-language task that intends to segment a desired object from an image based on a given natural language expression. Due to the essentially distinct data properties between image and text, most of existing methods either introduce complex designs towards fine-grained vision-language alignment or lack required dense alignment, resulting in scalability issues or mis-segmentation problems such as over- or under-segmentation. To achieve effective and efficient fine-grained feature alignment in the RIS task, we explore the potential of masked multimodal modeling coupled with self-distillation and propose a novel cross-modality masked self-distillation framework named CM-MaskSD, in which our method inherits the transferred knowledge of image-text semantic alignment from CLIP model to realize fine-grained patch-word feature alignment for better segmentation accuracy. Moreover, our CM-MaskSD framework can considerably boost model performance in a nearly parameter-free manner, since it shares weights between the main segmentation branch and the introduced masked self-distillation branches, and solely introduces negligible parameters for coordinating the multimodal features. Comprehensive experiments on three benchmark datasets (i.e. RefCOCO, RefCOCO+, G-Ref) for the RIS task convincingly demonstrate the superiority of our proposed framework over previous state-of-the-art methods.

Liangliang Cao, Bowen Zhang, Chen Chen et al.

The CLIP (Contrastive Language-Image Pre-training) model and its variants are becoming the de facto backbone in many applications. However, training a CLIP model from hundreds of millions of image-text pairs can be prohibitively expensive. Furthermore, the conventional CLIP model doesn't differentiate between the visual semantics and meaning of text regions embedded in images. This can lead to non-robustness when the text in the embedded region doesn't match the image's visual appearance. In this paper, we discuss two effective approaches to improve the efficiency and robustness of CLIP training: (1) augmenting the training dataset while maintaining the same number of optimization steps, and (2) filtering out samples that contain text regions in the image. By doing so, we significantly improve the classification and retrieval accuracy on public benchmarks like ImageNet and CoCo. Filtering out images with text regions also protects the model from typographic attacks. To verify this, we build a new dataset named ImageNet with Adversarial Text Regions (ImageNet-Attr). Our filter-based CLIP model demonstrates a top-1 accuracy of 68.78\%, outperforming previous models whose accuracy was all below 50\%.

Haoran Sun, Chen Chen, Lantian Li et al.

SpeechFlow is a powerful factorization model based on information bottleneck (IB), and its effectiveness has been reported by several studies. A potential problem of SpeechFlow, however, is that if the IB channels are not well designed, the resultant factors cannot be well disentangled. In this study, we propose a CycleFlow model that combines random factor substitution and cycle loss to solve this problem. Experiments on voice conversion tasks demonstrate that this simple technique can effectively reduce mutual information among individual factors, and produce clearly better conversion than the IB-based SpeechFlow. CycleFlow can also be used as a powerful tool for speech editing. We demonstrate this usage by an emotion perception experiment.

Yinglong Wang, Shuaicheng Liu, Chen Chen et al.

Rain streaks will inevitably be captured by some outdoor vision systems, which lowers the image visual quality and also interferes various computer vision applications. We present a novel rain removal method in this paper, which consists of two steps, i.e., detection of rain streaks and reconstruction of the rain-removed image. An accurate detection of rain streaks determines the quality of the overall performance. To this end, we first detect rain streaks according to pixel intensities, motivated by the observation that rain streaks often possess higher intensities compared to other neighboring image structures. Some mis-detected locations are then refined through a morphological processing and the principal component analysis (PCA) such that only locations corresponding to real rain streaks are retained. In the second step, we separate image gradients into a background layer and a rain streak layer, thanks to the image quasi-sparsity prior, so that a rain image can be decomposed into a background layer and a rain layer. We validate the effectiveness of our method through quantitative and qualitative evaluations. We show that our method can remove rain (even for some relatively bright rain) from images robustly and outperforms some state-of-the-art rain removal algorithms.

Chen Chen, Baochang Zhang, Alessio Del Bue et al.

Low-rank decomposition (LRD) is a state-of-the-art method for visual data reconstruction and modelling. However, it is a very challenging problem when the image data contains significant occlusion, noise, illumination variation, and misalignment from rotation or viewpoint changes. We leverage the specific structure of data in order to improve the performance of LRD when the data are not ideal. To this end, we propose a new framework that embeds manifold priors into LRD. To implement the framework, we design an alternating direction method of multipliers (ADMM) method which efficiently integrates the manifold constraints during the optimization process. The proposed approach is successfully used to calculate low-rank models from face images, hand-written digits and planar surface images. The results show a consistent increase of performance when compared to the state-of-the-art over a wide range of realistic image misalignments and corruptions.

Yuzhuo Ren, Chen Chen, Shangwen Li et al.

The task of estimating the spatial layout of cluttered indoor scenes from a single RGB image is addressed in this work. Existing solutions to this problems largely rely on hand-craft features and vanishing lines, and they often fail in highly cluttered indoor rooms. The proposed coarse-to-fine indoor layout estimation (CFILE) method consists of two stages: 1) coarse layout estimation; and 2) fine layout localization. In the first stage, we adopt a fully convolutional neural network (FCN) to obtain a coarse-scale room layout estimate that is close to the ground truth globally. The proposed FCN considers combines the layout contour property and the surface property so as to provide a robust estimate in the presence of cluttered objects. In the second stage, we formulate an optimization framework that enforces several constraints such as layout contour straightness, surface smoothness and geometric constraints for layout detail refinement. Our proposed system offers the state-of-the-art performance on two commonly used benchmark datasets.