Yalong Bai

Mohan Zhou, Yalong Bai, Wei Zhang et al.

A reliable and comprehensive evaluation metric that aligns with manual preference assessments is crucial for conversational head video synthesis methods development. Existing quantitative evaluations often fail to capture the full complexity of human preference, as they only consider limited evaluation dimensions. Qualitative evaluations and user studies offer a solution but are time-consuming and labor-intensive. This limitation hinders the advancement of conversational head generation algorithms and systems. In this paper, we propose a novel learning-based evaluation metric named Preference Score (PS) for fitting human preference according to the quantitative evaluations across different dimensions. PS can serve as a quantitative evaluation without the need for human annotation. Experimental results validate the superiority of Preference Score in aligning with human perception, and also demonstrate robustness and generalizability to unseen data, making it a valuable tool for advancing conversation head generation. We expect this metric could facilitate new advances in conversational head generation. Project Page: https://https://github.com/dc3ea9f/PreferenceScore.

Jing Xu, Wei Zhang, Yalong Bai et al.

People naturally conduct spontaneous body motions to enhance their speeches while giving talks. Body motion generation from speech is inherently difficult due to the non-deterministic mapping from speech to body motions. Most existing works map speech to motion in a deterministic way by conditioning on certain styles, leading to sub-optimal results. Motivated by studies in linguistics, we decompose the co-speech motion into two complementary parts: pose modes and rhythmic dynamics. Accordingly, we introduce a novel freeform motion generation model (FreeMo) by equipping a two-stream architecture, i.e., a pose mode branch for primary posture generation, and a rhythmic motion branch for rhythmic dynamics synthesis. On one hand, diverse pose modes are generated by conditional sampling in a latent space, guided by speech semantics. On the other hand, rhythmic dynamics are synced with the speech prosody. Extensive experiments demonstrate the superior performance against several baselines, in terms of motion diversity, quality and syncing with speech. Code and pre-trained models will be publicly available through https://github.com/TheTempAccount/Co-Speech-Motion-Generation.

Jie Ma, Yalong Bai, Bineng Zhong et al.

Vision Transformer (ViT) has become a leading tool in various computer vision tasks, owing to its unique self-attention mechanism that learns visual representations explicitly through cross-patch information interactions. Despite having good success, the literature seldom explores the explainability of vision transformer, and there is no clear picture of how the attention mechanism with respect to the correlation across comprehensive patches will impact the performance and what is the further potential. In this work, we propose a novel explainable visualization approach to analyze and interpret the crucial attention interactions among patches for vision transformer. Specifically, we first introduce a quantification indicator to measure the impact of patch interaction and verify such quantification on attention window design and indiscriminative patches removal. Then, we exploit the effective responsive field of each patch in ViT and devise a window-free transformer architecture accordingly. Extensive experiments on ImageNet demonstrate that the exquisitely designed quantitative method is shown able to facilitate ViT model learning, leading the top-1 accuracy by 4.28% at most. Moreover, the results on downstream fine-grained recognition tasks further validate the generalization of our proposal.

Wei Yu, Kuiyuan Yang, Yalong Bai et al.

The gap between low-level visual signals and high-level semantics has been progressively bridged by continuous development of deep neural network (DNN). With recent progress of DNN, almost all image classification tasks have achieved new records of accuracy. To extend the ability of DNN to image retrieval tasks, we proposed a unified DNN model for image-query similarity calculation by simultaneously modeling image and query in one network. The unified DNN is named the cross space mapping (CSM) model, which contains two parts, a convolutional part and a query-embedding part. The image and query are mapped to a common vector space via these two parts respectively, and image-query similarity is naturally defined as an inner product of their mappings in the space. To ensure good generalization ability of the DNN, we learn weights of the DNN from a large number of click-through logs which consists of 23 million clicked image-query pairs between 1 million images and 11.7 million queries. Both the qualitative results and quantitative results on an image retrieval evaluation task with 1000 queries demonstrate the superiority of the proposed method.

Jinhong Ni, Yalong Bai, Wei Zhang et al.

Multimodal fusion integrates the complementary information present in multiple modalities and has gained much attention recently. Most existing fusion approaches either learn a fixed fusion strategy during training and inference, or are only capable of fusing the information to a certain extent. Such solutions may fail to fully capture the dynamics of interactions across modalities especially when there are complex intra- and inter-modality correlations to be considered for informative multimodal fusion. In this paper, we propose a novel deep equilibrium (DEQ) method towards multimodal fusion via seeking a fixed point of the dynamic multimodal fusion process and modeling the feature correlations in an adaptive and recursive manner. This new way encodes the rich information within and across modalities thoroughly from low level to high level for efficacious downstream multimodal learning and is readily pluggable to various multimodal frameworks. Extensive experiments on BRCA, MM-IMDB, CMU-MOSI, SUN RGB-D, and VQA-v2 demonstrate the superiority of our DEQ fusion. More remarkably, DEQ fusion consistently achieves state-of-the-art performance on multiple multimodal benchmarks. The code will be released.

Mohan Zhou, Yalong Bai, Wei Zhang et al.

We introduce a new conversation head generation benchmark for synthesizing behaviors of a single interlocutor in a face-to-face conversation. The capability to automatically synthesize interlocutors which can participate in long and multi-turn conversations is vital and offer benefits for various applications, including digital humans, virtual agents, and social robots. While existing research primarily focuses on talking head generation (one-way interaction), hindering the ability to create a digital human for conversation (two-way) interaction due to the absence of listening and interaction parts. In this work, we construct two datasets to address this issue, ``ViCo'' for independent talking and listening head generation tasks at the sentence level, and ``ViCo-X'', for synthesizing interlocutors in multi-turn conversational scenarios. Based on ViCo and ViCo-X, we define three novel tasks targeting the interaction modeling during the face-to-face conversation: 1) responsive listening head generation making listeners respond actively to the speaker with non-verbal signals, 2) expressive talking head generation guiding speakers to be aware of listeners' behaviors, and 3) conversational head generation to integrate the talking/listening ability in one interlocutor. Along with the datasets, we also propose corresponding baseline solutions to the three aforementioned tasks. Experimental results show that our baseline method could generate responsive and vivid agents that can collaborate with real person to fulfil the whole conversation. Project page: https://vico.solutions/.

Mohan Zhou, Yalong Bai, Wei Zhang et al.

Dynamically synthesizing talking speech that actively responds to a listening head is critical during the face-to-face interaction. For example, the speaker could take advantage of the listener's facial expression to adjust the tones, stressed syllables, or pauses. In this work, we present a new visual-aware text-to-speech (VA-TTS) task to synthesize speech conditioned on both textual inputs and sequential visual feedback (e.g., nod, smile) of the listener in face-to-face communication. Different from traditional text-to-speech, VA-TTS highlights the impact of visual modality. On this newly-minted task, we devise a baseline model to fuse phoneme linguistic information and listener visual signals for speech synthesis. Extensive experiments on multimodal conversation dataset ViCo-X verify our proposal for generating more natural audio with scenario-appropriate rhythm and prosody.

Zhicong Tang, Zhao Zhang, Jingye Chen et al.

Layered image generation and editing is a fundamental capability that enables layer-wise reuse, editing, and composition of generated visual content, analogous to word-level editing in natural language. Despite its importance, this remains an underexplored area at scale. To address this gap, we present MRT, a 20B-parameter masked region diffusion model tailored for multi-layer transparent image generation and editing, trained on over 10M multilingual design samples spanning diverse aspect ratios and textual prompts. To fully leverage this scale, we make two key technical contributions. First, we unify three complementary tasks including text-to-layers, image-to-layers, and layers-to-layers within a shared masked region diffusion framework, where selective token masking enables flexible layer-wise generation and editing. Second, to enable overflow layer generation, we introduce an overflow-aware canvas layer that handles boundary inconsistencies and supports semi-transparent background synthesis, enabling complete editable layers extending beyond visible canvas boundaries. Additionally, we apply diffusion distillation to achieve 8-step, real-time multi-layer generation with minimal quality degradation. Extensive experiments demonstrate that our framework substantially outperforms prior state-of-the-art approaches, including various commercial systems, across all three tasks, establishing a new benchmark for multi-layer transparent image generation. Notably, our model significantly outperforms the concurrent Qwen-Image-Layered model in image-to-layers quality according to user-study results, while achieving 10-100\times faster inference and reducing activation GPU memory consumption by 50-90\% during image-to-layer inference.

Wenyi Mo, Tianyu Zhang, Yalong Bai et al.

Text-to-image generative models, specifically those based on diffusion models like Imagen and Stable Diffusion, have made substantial advancements. Recently, there has been a surge of interest in the delicate refinement of text prompts. Users assign weights or alter the injection time steps of certain words in the text prompts to improve the quality of generated images. However, the success of fine-control prompts depends on the accuracy of the text prompts and the careful selection of weights and time steps, which requires significant manual intervention. To address this, we introduce the \textbf{P}rompt \textbf{A}uto-\textbf{E}diting (PAE) method. Besides refining the original prompts for image generation, we further employ an online reinforcement learning strategy to explore the weights and injection time steps of each word, leading to the dynamic fine-control prompts. The reward function during training encourages the model to consider aesthetic score, semantic consistency, and user preferences. Experimental results demonstrate that our proposed method effectively improves the original prompts, generating visually more appealing images while maintaining semantic alignment. Code is available at https://github.com/Mowenyii/PAE.

Zihao Wang, Yuxiang Wei, Xinpeng Zhou et al.

Text-to-image generation has advanced rapidly, yet it still struggles to capture the nuanced user preferences. Existing approaches typically rely on multimodal large language models to infer user preferences, but the derived prompts or latent codes rarely reflect them faithfully, leading to suboptimal personalization. We present Premier, a novel preference modulation framework for personalized image generation. Premier represents each user's preference as a learnable embedding and introduces a preference adapter that fuses the user embedding with the text prompt. To enable accurate and fine-grained preference control, the fused preference embedding is further used to modulate the generative process. To enhance the distinctness of individual preference and improve alignment between outputs and user-specific styles, we incorporate a dispersion loss that enforces separation among user embeddings. When user data are scarce, new users are represented as linear combinations of existing preference embeddings learned during training, enabling effective generalization. Experiments show that Premier outperforms prior methods under the same history length, achieving stronger preference alignment and superior performance on text consistency, ViPer proxy metrics, and expert evaluations.

Wenyi Mo, Tianyu Zhang, Yalong Bai et al.

Preference-conditioned image generation seeks to adapt generative models to individual users, producing outputs that reflect personal aesthetic choices beyond the given textual prompt. Despite recent progress, existing approaches either fail to capture nuanced user preferences or lack effective mechanisms to encode personalized visual signals. In this work, we propose a multimodal framework that leverages multimodal large language models (MLLMs) to extract rich user representations and inject them into diffusion-based image generation. We train the MLLM with a preference-oriented visual question answering task to capture fine-grained semantic cues. To isolate preference-relevant features, we introduce two complementary probing tasks: inter-user discrimination to distinguish between different users, and intra-user discrimination to separate liked from disliked content. To ensure compatibility with diffusion text encoders, we design a maximum mean discrepancy-based alignment loss that bridges the modality gap while preserving multimodal structure. The resulting embeddings are used to condition the generator, enabling faithful adherence to both prompts and user preferences. Extensive experiments demonstrate that our method substantially outperforms strong baselines in both image quality and preference alignment, highlighting the effectiveness of representation extraction and alignment for personalized generation.

Guiwei Zhang, Tianyu Zhang, Mohan Zhou et al.

We propose V2Flow, a novel tokenizer that produces discrete visual tokens capable of high-fidelity reconstruction, while ensuring structural and latent distribution alignment with the vocabulary space of large language models (LLMs). Leveraging this tight visual-vocabulary coupling, V2Flow enables autoregressive visual generation on top of existing LLMs. Our approach formulates visual tokenization as a flow-matching problem, aiming to learn a mapping from a standard normal prior to the continuous image distribution, conditioned on token sequences embedded within the LLMs vocabulary space. The effectiveness of V2Flow stems from two core designs. First, we propose a Visual Vocabulary resampler, which compresses visual data into compact token sequences, with each represented as a soft categorical distribution over LLM's vocabulary. This allows seamless integration of visual tokens into existing LLMs for autoregressive visual generation. Second, we present a masked autoregressive Rectified-Flow decoder, employing a masked transformer encoder-decoder to refine visual tokens into contextually enriched embeddings. These embeddings then condition a dedicated velocity field for precise reconstruction. Additionally, an autoregressive rectified-flow sampling strategy is incorporated, ensuring flexible sequence lengths while preserving competitive reconstruction quality. Extensive experiments show that V2Flow outperforms mainstream VQ-based tokenizers and facilitates autoregressive visual generation on top of existing. https://github.com/zhangguiwei610/V2Flow

Ying Ba, Tianyu Zhang, Yalong Bai et al.

Contemporary image generation systems have achieved high fidelity and superior aesthetic quality beyond basic text-image alignment. However, existing evaluation frameworks have failed to evolve in parallel. This study reveals that human preference reward models fine-tuned based on CLIP and BLIP architectures have inherent flaws: they inappropriately assign low scores to images with rich details and high aesthetic value, creating a significant discrepancy with actual human aesthetic preferences. To address this issue, we design a novel evaluation score, ICT (Image-Contained-Text) score, that achieves and surpasses the objectives of text-image alignment by assessing the degree to which images represent textual content. Building upon this foundation, we further train an HP (High-Preference) score model using solely the image modality to enhance image aesthetics and detail quality while maintaining text-image alignment. Experiments demonstrate that the proposed evaluation model improves scoring accuracy by over 10\% compared to existing methods, and achieves significant results in optimizing state-of-the-art text-to-image models. This research provides theoretical and empirical support for evolving image generation technology toward higher-order human aesthetic preferences. Code is available at https://github.com/BarretBa/ICTHP.

Shengqi Xu, Xinpeng Zhou, Yabo Zhang et al.

Personalized image preference assessment aims to evaluate an individual user's image preferences by relying only on a small set of reference images as prior information. Existing methods mainly focus on general preference assessment, training models with large-scale data to tackle well-defined tasks such as text-image alignment. However, these approaches struggle to handle personalized preference because user-specific data are scarce and not easily scalable, and individual tastes are often diverse and complex. To overcome these challenges, we introduce a common preference profile that serves as a bridge across users, allowing large-scale user data to be leveraged for training profile prediction and capturing complex personalized preferences. Building on this idea, we propose a reasoning-based personalized image preference assessment framework that follows a \textit{predict-then-assess} paradigm: it first predicts a user's preference profile from reference images, and then provides interpretable, multi-dimensional scores and assessments of candidate images based on the predicted profile. To support this, we first construct a large-scale Chain-of-Thought (CoT)-style personalized assessment dataset annotated with diverse user preference profiles and high-quality CoT-style reasoning, enabling explicit supervision of structured reasoning. Next, we adopt a two-stage training strategy: a cold-start supervised fine-tuning phase to empower the model with structured reasoning capabilities, followed by reinforcement learning to incentivize the model to explore more reasonable assessment paths and enhance generalization. Furthermore, we propose a similarity-aware prediction reward to encourage better prediction of the user's preference profile, which facilitates more reasonable assessments exploration. Extensive experiments demonstrate the superiority of the proposed method.

Wenyi Mo, Tianyu Zhang, Yalong Bai et al.

Text-guided image generation and editing using diffusion models have achieved remarkable advancements. Among these, tuning-free methods have gained attention for their ability to perform edits without extensive model adjustments, offering simplicity and efficiency. However, existing tuning-free approaches often struggle with balancing fidelity and editing precision. Reconstruction errors in DDIM Inversion are partly attributed to the cross-attention mechanism in U-Net, which introduces misalignments during the inversion and reconstruction process. To address this, we analyze reconstruction from a structural perspective and propose a novel approach that replaces traditional cross-attention with uniform attention maps, significantly enhancing image reconstruction fidelity. Our method effectively minimizes distortions caused by varying text conditions during noise prediction. To complement this improvement, we introduce an adaptive mask-guided editing technique that integrates seamlessly with our reconstruction approach, ensuring consistency and accuracy in editing tasks. Experimental results demonstrate that our approach not only excels in achieving high-fidelity image reconstruction but also performs robustly in real image composition and editing scenarios. This study underscores the potential of uniform attention maps to enhance the fidelity and versatility of diffusion-based image processing methods. Code is available at https://github.com/Mowenyii/Uniform-Attention-Maps.

Ying Ba, Tianyu Zhang, Mohan Zhou et al.

Text-to-image generation models have achieved remarkable progress in preference optimization, yet achieving robust alignment across diverse reward models remains a significant challenge. Existing multi-reward fusion approaches rely on weighted summation, which is costly to tune and insufficient for balancing conflicting objectives. More critically, optimization with reward models is highly susceptible to reward hacking, where reward scores increase while the perceived quality of generated images deteriorates. We demonstrate that optimizing against a unified global target under heterogeneous reward upper bounds can induce reward hacking, a risk further exacerbated by the inherent instability of weak reward models. To mitigate this, we propose a Pareto Frontier-Guided Optimal Transport (PG-OT) framework. Our method constructs a prompt-specific Pareto frontier and maps dominated samples toward it via distribution-aware optimal transport. Furthermore, we develop both online and offline optimization strategies tailored to diverse reward signal characteristics. To provide a more rigorous assessment, we introduce the Joint Domination Rate (JDR) and Joint Collapse Rate (JCR) as principled metrics to quantify multi-reward synergy and reward hacking. Experimental results show that our approach outperforms strong baselines with an 11% gain in JDR and achieves a near 80% win rate in human evaluations.

Mohan Zhou, Yalong Bai, Wei Zhang et al.

Most object recognition approaches predominantly focus on learning discriminative visual patterns while overlooking the holistic object structure. Though important, structure modeling usually requires significant manual annotations and therefore is labor-intensive. In this paper, we propose to "look into object" (explicitly yet intrinsically model the object structure) through incorporating self-supervisions into the traditional framework. We show the recognition backbone can be substantially enhanced for more robust representation learning, without any cost of extra annotation and inference speed. Specifically, we first propose an object-extent learning module for localizing the object according to the visual patterns shared among the instances in the same category. We then design a spatial context learning module for modeling the internal structures of the object, through predicting the relative positions within the extent. These two modules can be easily plugged into any backbone networks during training and detached at inference time. Extensive experiments show that our look-into-object approach (LIO) achieves large performance gain on a number of benchmarks, including generic object recognition (ImageNet) and fine-grained object recognition tasks (CUB, Cars, Aircraft). We also show that this learning paradigm is highly generalizable to other tasks such as object detection and segmentation (MS COCO). Project page: https://github.com/JDAI-CV/LIO.

Wenyi Mo, Ying Ba, Tianyu Zhang et al.

User preference prediction requires a comprehensive and accurate understanding of individual tastes. This includes both surface-level attributes, such as color and style, and deeper content-related aspects, such as themes and composition. However, existing methods typically rely on general human preferences or assume static user profiles, often neglecting individual variability and the dynamic, multifaceted nature of personal taste. To address these limitations, we propose an approach built upon Multimodal Large Language Models, introducing contrastive preference loss and preference tokens to learn personalized user preferences from historical interactions. The contrastive preference loss is designed to effectively distinguish between user ''likes'' and ''dislikes'', while the learnable preference tokens capture shared interest representations among existing users, enabling the model to activate group-specific preferences and enhance consistency across similar users. Extensive experiments demonstrate our model outperforms other methods in preference prediction accuracy, effectively identifying users with similar aesthetic inclinations and providing more precise guidance for generating images that align with individual tastes. The project page is \texttt{https://learn-user-pref.github.io/}.

Xiaoxiao Ma, Mohan Zhou, Tao Liang et al.

We introduce STAR, a text-to-image model that employs a scale-wise auto-regressive paradigm. Unlike VAR, which is constrained to class-conditioned synthesis for images up to 256$\times$256, STAR enables text-driven image generation up to 1024$\times$1024 through three key designs. First, we introduce a pre-trained text encoder to extract and adopt representations for textual constraints, enhancing details and generalizability. Second, given the inherent structural correlation across different scales, we leverage 2D Rotary Positional Encoding (RoPE) and tweak it into a normalized version, ensuring consistent interpretation of relative positions across token maps and stabilizing the training process. Third, we observe that simultaneously sampling all tokens within a single scale can disrupt inter-token relationships, leading to structural instability, particularly in high-resolution generation. To address this, we propose a novel stable sampling method that incorporates causal relationships into the sampling process, ensuring both rich details and stable structures. Compared to previous diffusion models and auto-regressive models, STAR surpasses existing benchmarks in fidelity, text-image consistency, and aesthetic quality, requiring just 2.21s for 1024$\times$1024 images on A100. This highlights the potential of auto-regressive methods in high-quality image synthesis, offering new directions for the text-to-image generation.

Mohan Zhou, Yalong Bai, Qing Yang et al.

The ability to fine-tune generative models for text-to-image generation tasks is crucial, particularly facing the complexity involved in accurately interpreting and visualizing textual inputs. While LoRA is efficient for language model adaptation, it often falls short in text-to-image tasks due to the intricate demands of image generation, such as accommodating a broad spectrum of styles and nuances. To bridge this gap, we introduce StyleInject, a specialized fine-tuning approach tailored for text-to-image models. StyleInject comprises multiple parallel low-rank parameter matrices, maintaining the diversity of visual features. It dynamically adapts to varying styles by adjusting the variance of visual features based on the characteristics of the input signal. This approach significantly minimizes the impact on the original model's text-image alignment capabilities while adeptly adapting to various styles in transfer learning. StyleInject proves particularly effective in learning from and enhancing a range of advanced, community-fine-tuned generative models. Our comprehensive experiments, including both small-sample and large-scale data fine-tuning as well as base model distillation, show that StyleInject surpasses traditional LoRA in both text-image semantic consistency and human preference evaluation, all while ensuring greater parameter efficiency.

Mohan Zhou, Yalong Bai, Wei Zhang et al.

We present a new listening head generation benchmark, for synthesizing responsive feedbacks of a listener (e.g., nod, smile) during a face-to-face conversation. As the indispensable complement to talking heads generation, listening head generation has seldomly been studied in literature. Automatically synthesizing listening behavior that actively responds to a talking head, is critical to applications such as digital human, virtual agents and social robots. In this work, we propose a novel dataset "ViCo", highlighting the listening head generation during a face-to-face conversation. A total number of 92 identities (67 speakers and 76 listeners) are involved in ViCo, featuring 483 clips in a paired "speaking-listening" pattern, where listeners show three listening styles based on their attitudes: positive, neutral, negative. Different from traditional speech-to-gesture or talking-head generation, listening head generation takes as input both the audio and visual signals from the speaker, and gives non-verbal feedbacks (e.g., head motions, facial expressions) in a real-time manner. Our dataset supports a wide range of applications such as human-to-human interaction, video-to-video translation, cross-modal understanding and generation. To encourage further research, we also release a listening head generation baseline, conditioning on different listening attitudes. Code & ViCo dataset: https://project.mhzhou.com/vico.

Yalong Bai, Yifan Yang, Wei Zhang et al.

Despite the large augmentation family, only a few cherry-picked robust augmentation policies are beneficial to self-supervised image representation learning. In this paper, we propose a directional self-supervised learning paradigm (DSSL), which is compatible with significantly more augmentations. Specifically, we adapt heavy augmentation policies after the views lightly augmented by standard augmentations, to generate harder view (HV). HV usually has a higher deviation from the original image than the lightly augmented standard view (SV). Unlike previous methods equally pairing all augmented views to symmetrically maximize their similarities, DSSL treats augmented views of the same instance as a partially ordered set (with directions as SV$\leftrightarrow $SV, SV$\leftarrow$HV), and then equips a directional objective function respecting to the derived relationships among views. DSSL can be easily implemented with a few lines of codes and is highly flexible to popular self-supervised learning frameworks, including SimCLR, SimSiam, BYOL. Extensive experimental results on CIFAR and ImageNet demonstrated that DSSL can stably improve various baselines with compatibility to a wider range of augmentations.

Yalong Bai, Mohan Zhou, Wei Zhang et al.

Data augmentation is practically helpful for visual recognition, especially at the time of data scarcity. However, such success is only limited to quite a few light augmentations (e.g., random crop, flip). Heavy augmentations are either unstable or show adverse effects during training, owing to the big gap between the original and augmented images. This paper introduces a novel network design, noted as Augmentation Pathways (AP), to systematically stabilize training on a much wider range of augmentation policies. Notably, AP tames various heavy data augmentations and stably boosts performance without a careful selection among augmentation policies. Unlike traditional single pathway, augmented images are processed in different neural paths. The main pathway handles the light augmentations, while other pathways focus on the heavier augmentations. By interacting with multiple paths in a dependent manner, the backbone network robustly learns from shared visual patterns among augmentations, and suppresses the side effect of heavy augmentations at the same time. Furthermore, we extend AP to high-order versions for high-order scenarios, demonstrating its robustness and flexibility in practical usage. Experimental results on ImageNet demonstrate the compatibility and effectiveness on a much wider range of augmentations, while consuming fewer parameters and lower computational costs at inference time.

Tianyu Hua, Hongdong Zheng, Yalong Bai et al.

The significant progress on Generative Adversarial Networks (GANs) has facilitated realistic single-object image generation based on language input. However, complex-scene generation (with various interactions among multiple objects) still suffers from messy layouts and object distortions, due to diverse configurations in layouts and appearances. Prior methods are mostly object-driven and ignore their inter-relations that play a significant role in complex-scene images. This work explores relationship-aware complex-scene image generation, where multiple objects are inter-related as a scene graph. With the help of relationships, we propose three major updates in the generation framework. First, reasonable spatial layouts are inferred by jointly considering the semantics and relationships among objects. Compared to standard location regression, we show relative scales and distances serve a more reliable target. Second, since the relations between objects significantly influence an object's appearance, we design a relation-guided generator to generate objects reflecting their relationships. Third, a novel scene graph discriminator is proposed to guarantee the consistency between the generated image and the input scene graph. Our method tends to synthesize plausible layouts and objects, respecting the interplay of multiple objects in an image. Experimental results on Visual Genome and HICO-DET datasets show that our proposed method significantly outperforms prior arts in terms of IS and FID metrics. Based on our user study and visual inspection, our method is more effective in generating logical layout and appearance for complex-scenes.

Yalong Bai, Yuxiang Chen, Wei Yu et al.

With the rapid development of electronic commerce, the way of shopping has experienced a revolutionary evolution. To fully meet customers' massive and diverse online shopping needs with quick response, the retailing AI system needs to automatically recognize products from images and videos at the stock-keeping unit (SKU) level with high accuracy. However, product recognition is still a challenging task, since many of SKU-level products are fine-grained and visually similar by a rough glimpse. Although there are already some products benchmarks available, these datasets are either too small (limited number of products) or noisy-labeled (lack of human labeling). In this paper, we construct a human-labeled product image dataset named "Products-10K", which contains 10,000 fine-grained SKU-level products frequently bought by online customers in JD.com. Based on our new database, we also introduced several useful tips and tricks for fine-grained product recognition. The products-10K dataset is available via https://products-10k.github.io/.

Hongdong Zheng, Yalong Bai, Wei Zhang et al.

The significant progress on Generative Adversarial Networks (GANs) have made it possible to generate surprisingly realistic images for single object based on natural language descriptions. However, controlled generation of images for multiple entities with explicit interactions is still difficult to achieve due to the scene layout generation heavily suffer from the diversity object scaling and spatial locations. In this paper, we proposed a novel framework for generating realistic image layout from textual scene graphs. In our framework, a spatial constraint module is designed to fit reasonable scaling and spatial layout of object pairs with considering relationship between them. Moreover, a contextual fusion module is introduced for fusing pair-wise spatial information in terms of object dependency in scene graph. By using these two modules, our proposed framework tends to generate more commonsense layout which is helpful for realistic image generation. Experimental results including quantitative results, qualitative results and user studies on two different scene graph datasets demonstrate our proposed framework's ability to generate complex and logical layout with multiple objects from scene graph.

Yuanzhi Liang, Yalong Bai, Wei Zhang et al.

Relationships encode the interactions among individual instances, and play a critical role in deep visual scene understanding. Suffering from the high predictability with non-visual information, existing methods tend to fit the statistical bias rather than ``learning'' to ``infer'' the relationships from images. To encourage further development in visual relationships, we propose a novel method to automatically mine more valuable relationships by pruning visually-irrelevant ones. We construct a new scene-graph dataset named Visually-Relevant Relationships Dataset (VrR-VG) based on Visual Genome. Compared with existing datasets, the performance gap between learnable and statistical method is more significant in VrR-VG, and frequency-based analysis does not work anymore. Moreover, we propose to learn a relationship-aware representation by jointly considering instances, attributes and relationships. By applying the representation-aware feature learned on VrR-VG, the performances of image captioning and visual question answering are systematically improved with a large margin, which demonstrates the gain of our dataset and the features embedding schema. VrR-VG is available via http://vrr-vg.com/.

Yalong Bai, Kuiyuan Yang, Tao Mei et al.

Large scale image dataset and deep convolutional neural network (DCNN) are two primary driving forces for the rapid progress made in generic object recognition tasks in recent years. While lots of network architectures have been continuously designed to pursue lower error rates, few efforts are devoted to enlarge existing datasets due to high labeling cost and unfair comparison issues. In this paper, we aim to achieve lower error rate by augmenting existing datasets in an automatic manner. Our method leverages both Web and DCNN, where Web provides massive images with rich contextual information, and DCNN replaces human to automatically label images under guidance of Web contextual information. Experiments show our method can automatically scale up existing datasets significantly from billions web pages with high accuracy, and significantly improve the performance on object recognition tasks by using the automatically augmented datasets, which demonstrates that more supervisory information has been automatically gathered from the Web. Both the dataset and models trained on the dataset are made publicly available.

Wei Yu, Kuiyuan Yang, Yalong Bai et al.

Convolutional Neural Networks (CNNs) have achieved comparable error rates to well-trained human on ILSVRC2014 image classification task. To achieve better performance, the complexity of CNNs is continually increasing with deeper and bigger architectures. Though CNNs achieved promising external classification behavior, understanding of their internal work mechanism is still limited. In this work, we attempt to understand the internal work mechanism of CNNs by probing the internal representations in two comprehensive aspects, i.e., visualizing patches in the representation spaces constructed by different layers, and visualizing visual information kept in each layer. We further compare CNNs with different depths and show the advantages brought by deeper architecture.

Yalong Bai, Kuiyuan Yang, Wei Yu et al.

Image retrieval refers to finding relevant images from an image database for a query, which is considered difficult for the gap between low-level representation of images and high-level representation of queries. Recently further developed Deep Neural Network sheds light on automatically learning high-level image representation from raw pixels. In this paper, we proposed a multi-task DNN learned for image retrieval, which contains two parts, i.e., query-sharing layers for image representation computation and query-specific layers for relevance estimation. The weights of multi-task DNN are learned on clickthrough data by Ring Training. Experimental results on both simulated and real dataset show the effectiveness of the proposed method.