Zuopeng Yang

Zuopeng Yang, Daqing Liu, Chaoyue Wang et al.

We present a method that achieves state-of-the-art results on challenging (few-shot) layout-to-image generation tasks by accurately modeling textures, structures and relationships contained in a complex scene. After compressing RGB images into patch tokens, we propose the Transformer with Focal Attention (TwFA) for exploring dependencies of object-to-object, object-to-patch and patch-to-patch. Compared to existing CNN-based and Transformer-based generation models that entangled modeling on pixel-level&patch-level and object-level&patch-level respectively, the proposed focal attention predicts the current patch token by only focusing on its highly-related tokens that specified by the spatial layout, thereby achieving disambiguation during training. Furthermore, the proposed TwFA largely increases the data efficiency during training, therefore we propose the first few-shot complex scene generation strategy based on the well-trained TwFA. Comprehensive experiments show the superiority of our method, which significantly increases both quantitative metrics and qualitative visual realism with respect to state-of-the-art CNN-based and transformer-based methods. Code is available at https://github.com/JohnDreamer/TwFA.

Zuopeng Yang, Tianshu Chu, Xin Lin et al.

The recent success of text-to-image generation diffusion models has also revolutionized semantic image editing, enabling the manipulation of images based on query/target texts. Despite these advancements, a significant challenge lies in the potential introduction of contextual prior bias in pre-trained models during image editing, e.g., making unexpected modifications to inappropriate regions. To address this issue, we present a novel approach called Dual-Cycle Diffusion, which generates an unbiased mask to guide image editing. The proposed model incorporates a Bias Elimination Cycle that consists of both a forward path and an inverted path, each featuring a Structural Consistency Cycle to ensure the preservation of image content during the editing process. The forward path utilizes the pre-trained model to produce the edited image, while the inverted path converts the result back to the source image. The unbiased mask is generated by comparing differences between the processed source image and the edited image to ensure that both conform to the same distribution. Our experiments demonstrate the effectiveness of the proposed method, as it significantly improves the D-CLIP score from 0.272 to 0.283. The code will be available at https://github.com/JohnDreamer/DualCycleDiffsion.

Minghui Hu, Chuanxia Zheng, Heliang Zheng et al.

The recently developed discrete diffusion models perform extraordinarily well in the text-to-image task, showing significant promise for handling the multi-modality signals. In this work, we harness these traits and present a unified multimodal generation model that can conduct both the "modality translation" and "multi-modality generation" tasks using a single model, performing text-based, image-based, and even vision-language simultaneous generation. Specifically, we unify the discrete diffusion process for multimodal signals by proposing a unified transition matrix. Moreover, we design a mutual attention module with fused embedding layer and a unified objective function to emphasise the inter-modal linkages, which are vital for multi-modality generation. Extensive experiments indicate that our proposed method can perform comparably to the state-of-the-art solutions in various generation tasks.

Kun Fang, Qinghua Tao, Zuopeng Yang et al.

Out-of-Distribution (OoD) detection aims to justify whether a given sample is from the training distribution of the classifier-under-protection, i.e., In-Distribution (InD), or from OoD. Diffusion Models (DMs) are recently utilized in OoD detection by using the perceptual distances between the given image and its DM generation. DM-based methods bring fresh insights to the field, yet remain under-explored. In this work, we point out two main limitations in DM-based OoD detection methods: (i) the perceptual metrics on the disparities between the given sample and its generation are devised only at human-perceived levels, ignoring the abstract or high-level patterns that help better reflect the intrinsic disparities in distribution; (ii) only the raw image contents are taken to measure the disparities, while other representations, i.e., the features and probabilities from the classifier-under-protection, are easy to access at hand but are ignored. To this end, our proposed detection framework goes beyond the perceptual distances and looks into the deep representations from the classifier-under-protection with our novel metrics devised correspondingly, leading to more informative disparity assessments between InD and OoD. An anomaly-removal strategy is integrated to remove the abnormal OoD information in the generation, further enhancing the distinctiveness of disparities. Our work has demonstrated state-of-the-art detection performances among DM-based methods in extensive experiments.

Xin Lin, Chong Shi, Zuopeng Yang et al.

Recent open-vocabulary human-object interaction (OV-HOI) detection methods primarily rely on large language model (LLM) for generating auxiliary descriptions and leverage knowledge distilled from CLIP to detect unseen interaction categories. Despite their effectiveness, these methods face two challenges: (1) feature granularity deficiency, due to reliance on last layer visual features for text alignment, leading to the neglect of crucial object-level details from intermediate layers; (2) semantic similarity confusion, resulting from CLIP's inherent biases toward certain classes, while LLM-generated descriptions based solely on labels fail to adequately capture inter-class similarities. To address these challenges, we propose a stratified granular comparison network. First, we introduce a granularity sensing alignment module that aggregates global semantic features with local details, refining interaction representations and ensuring robust alignment between intermediate visual features and text embeddings. Second, we develop a hierarchical group comparison module that recursively compares and groups classes using LLMs, generating fine-grained and discriminative descriptions for each interaction category. Experimental results on two widely-used benchmark datasets, SWIG-HOI and HICO-DET, demonstrate that our method achieves state-of-the-art results in OV-HOI detection. Codes will be released on https://github.com/Phil0212/SGC-Net.

Zuopeng Yang, Jiluan Fan, Anli Yan et al.

Multimodal Large Language Models (MLLMs) bridge the gap between visual and textual data, enabling a range of advanced applications. However, complex internal interactions among visual elements and their alignment with text can introduce vulnerabilities, which may be exploited to bypass safety mechanisms. To address this, we analyze the relationship between image content and task and find that the complexity of subimages, rather than their content, is key. Building on this insight, we propose the Distraction Hypothesis, followed by a novel framework called Contrasting Subimage Distraction Jailbreaking (CS-DJ), to achieve jailbreaking by disrupting MLLMs alignment through multi-level distraction strategies. CS-DJ consists of two components: structured distraction, achieved through query decomposition that induces a distributional shift by fragmenting harmful prompts into sub-queries, and visual-enhanced distraction, realized by constructing contrasting subimages to disrupt the interactions among visual elements within the model. This dual strategy disperses the model's attention, reducing its ability to detect and mitigate harmful content. Extensive experiments across five representative scenarios and four popular closed-source MLLMs, including GPT-4o-mini, GPT-4o, GPT-4V, and Gemini-1.5-Flash, demonstrate that CS-DJ achieves average success rates of 52.40% for the attack success rate and 74.10% for the ensemble attack success rate. These results reveal the potential of distraction-based approaches to exploit and bypass MLLMs' defenses, offering new insights for attack strategies.

Xin Lin, Chong Shi, Yibing Zhan et al.

Dynamic scene graph generation (SGG) focuses on detecting objects in a video and determining their pairwise relationships. Existing dynamic SGG methods usually suffer from several issues, including 1) Contextual noise, as some frames might contain occluded and blurred objects. 2) Label bias, primarily due to the high imbalance between a few positive relationship samples and numerous negative ones. Additionally, the distribution of relationships exhibits a long-tailed pattern. To address the above problems, in this paper, we introduce a network named TD$^2$-Net that aims at denoising and debiasing for dynamic SGG. Specifically, we first propose a denoising spatio-temporal transformer module that enhances object representation with robust contextual information. This is achieved by designing a differentiable Top-K object selector that utilizes the gumbel-softmax sampling strategy to select the relevant neighborhood for each object. Second, we introduce an asymmetrical reweighting loss to relieve the issue of label bias. This loss function integrates asymmetry focusing factors and the volume of samples to adjust the weights assigned to individual samples. Systematic experimental results demonstrate the superiority of our proposed TD$^2$-Net over existing state-of-the-art approaches on Action Genome databases. In more detail, TD$^2$-Net outperforms the second-best competitors by 12.7 \% on mean-Recall@10 for predicate classification.

Yuhang Liu, Tao Li, Zhehao Huang et al.

Fine-tuning large-scale pre-trained models with limited data presents significant challenges for generalization. While Sharpness-Aware Minimization (SAM) has proven effective in improving generalization by seeking flat minima, its substantial extra memory and computation overhead make it impractical for large models. Integrating SAM with parameter-efficient fine-tuning methods like Low-Rank Adaptation (LoRA) is a promising direction. However, we find that directly applying SAM to LoRA parameters limits the sharpness optimization to a restricted subspace, hindering its effectiveness. To address this limitation, we propose Bi-directional Low-Rank Adaptation (Bi-LoRA), which introduces an auxiliary LoRA module to model SAM's adversarial weight perturbations. It decouples SAM's weight perturbations from LoRA optimization: the primary LoRA module adapts to specific tasks via standard gradient descent, while the auxiliary module captures the sharpness of the loss landscape through gradient ascent. Such dual-module design enables Bi-LoRA to capture broader sharpness for achieving flatter minima while remaining memory-efficient. Another important benefit is that the dual design allows for simultaneous optimization and perturbation, eliminating SAM's doubled training costs. Extensive experiments across diverse tasks and architectures demonstrate Bi-LoRA's efficiency and effectiveness in enhancing generalization.

Yuncheng Yang, Chuyan Zhang, Zuopeng Yang et al.

Prompt learning is effective for fine-tuning foundation models to improve their generalization across a variety of downstream tasks. However, the prompts that are independently optimized along a single modality path, may sacrifice the vision-language alignment of pre-trained models in return for improved performance on specific tasks and classes, leading to poorer generalization. In this paper, we first demonstrate that prompt tuning along only one single branch of CLIP (e.g., language or vision) is the reason why the misalignment occurs. Without proper regularization across the learnable parameters in different modalities, prompt learning violates the original pre-training constraints inherent in the two-tower architecture. To address such misalignment, we first propose feature shift, which is defined as the variation of embeddings after introducing the learned prompts, to serve as an explanatory tool. We dive into its relation with generalizability and thereafter propose RESTORE, a multi-modal prompt learning method that exerts explicit constraints on cross-modal consistency. To be more specific, to prevent feature misalignment, a feature shift consistency is introduced to synchronize inter-modal feature shifts by measuring and regularizing the magnitude of discrepancy during prompt tuning. In addition, we propose a "surgery" block to avoid short-cut hacking, where cross-modal misalignment can still be severe if the feature shift of each modality varies drastically at the same rate. It is implemented as feed-forward adapters upon both modalities to alleviate the misalignment problem. Extensive experiments on 15 datasets demonstrate that our method outperforms the state-of-the-art prompt tuning methods without compromising feature alignment.

Jianbin Zheng, Daqing Liu, Chaoyue Wang et al.

Existing multimodal conditional image synthesis (MCIS) methods generate images conditioned on any combinations of various modalities that require all of them must be exactly conformed, hindering the synthesis controllability and leaving the potential of cross-modality under-exploited. To this end, we propose to generate images conditioned on the compositions of multimodal control signals, where modalities are imperfectly complementary, i.e., composed multimodal conditional image synthesis (CMCIS). Specifically, we observe two challenging issues of the proposed CMCIS task, i.e., the modality coordination problem and the modality imbalance problem. To tackle these issues, we introduce a Mixture-of-Modality-Tokens Transformer (MMoT) that adaptively fuses fine-grained multimodal control signals, a multimodal balanced training loss to stabilize the optimization of each modality, and a multimodal sampling guidance to balance the strength of each modality control signal. Comprehensive experimental results demonstrate that MMoT achieves superior performance on both unimodal conditional image synthesis (UCIS) and MCIS tasks with high-quality and faithful image synthesis on complex multimodal conditions. The project website is available at https://jabir-zheng.github.io/MMoT.