The goal of No-Reference Image Quality Assessment (NR-IQA) is to predict the perceptual quality of an image in line with its subjective evaluation. To put the NR-IQA models into practice, it is essential to study their potential loopholes for model refinement. This paper makes the first attempt to explore the black-box adversarial attacks on NR-IQA models. Specifically, we first formulate the attack problem as maximizing the deviation between the estimated quality scores of original and perturbed images, while restricting the perturbed image distortions for visual quality preservation. Under such formulation, we then design a Bi-directional loss function to mislead the estimated quality scores of adversarial examples towards an opposite direction with maximum deviation. On this basis, we finally develop an efficient and effective black-box attack method against NR-IQA models. Extensive experiments reveal that all the evaluated NR-IQA models are vulnerable to the proposed attack method. And the generated perturbations are not transferable, enabling them to serve the investigation of specialities of disparate IQA models.
Diffusion model is a promising approach to image generation and has been employed for Pose-Guided Person Image Synthesis (PGPIS) with competitive performance. While existing methods simply align the person appearance to the target pose, they are prone to overfitting due to the lack of a high-level semantic understanding on the source person image. In this paper, we propose a novel Coarse-to-Fine Latent Diffusion (CFLD) method for PGPIS. In the absence of image-caption pairs and textual prompts, we develop a novel training paradigm purely based on images to control the generation process of the pre-trained text-to-image diffusion model. A perception-refined decoder is designed to progressively refine a set of learnable queries and extract semantic understanding of person images as a coarse-grained prompt. This allows for the decoupling of fine-grained appearance and pose information controls at different stages, and thus circumventing the potential overfitting problem. To generate more realistic texture details, a hybrid-granularity attention module is proposed to encode multi-scale fine-grained appearance features as bias terms to augment the coarse-grained prompt. Both quantitative and qualitative experimental results on the DeepFashion benchmark demonstrate the superiority of our method over the state of the arts for PGPIS. Code is available at https://github.com/YanzuoLu/CFLD.
Existing two-stream models for image-text matching show good performance while ensuring retrieval speed and have received extensive attention from industry and academia. These methods use a single representation to encode image and text separately and get a matching score with cosine similarity or the inner product of vectors. However, the performance of the two-stream model is often sub-optimal. On the one hand, a single representation is challenging to cover complex content comprehensively. On the other hand, in this framework of lack of interaction, it is challenging to match multiple meanings which leads to information being ignored. To address the problems mentioned above and facilitate the performance of the two-stream model, we propose a multi-view attention approach for two-stream image-text matching MVAM (\textbf{M}ulti-\textbf{V}iew \textbf{A}ttention \textbf{M}odel). It first learns multiple image and text representations by diverse attention heads with different view codes. And then concatenate these representations into one for matching. A diversity objective is also used to promote diversity between attention heads. With this method, models are able to encode images and text from different views and attend to more key points. So we can get representations that contain more information. When doing retrieval tasks, the matching scores between images and texts can be calculated from different aspects, leading to better matching performance. Experiment results on MSCOCO and Flickr30K show that our proposed model brings improvements over existing models. Further case studies show that different attention heads can focus on different contents and finally obtain a more comprehensive representation.
Diffusion models, trained on large amounts of data, showed remarkable performance for image synthesis. They have high error consistency with humans and low texture bias when used for classification. Furthermore, prior work demonstrated the decomposability of their bottleneck layer representations into semantic directions. In this work, we analyze how well such representations are aligned to human responses on a triplet odd-one-out task. We find that despite the aforementioned observations: I) The representational alignment with humans is comparable to that of models trained only on ImageNet-1k. II) The most aligned layers of the denoiser U-Net are intermediate layers and not the bottleneck. III) Text conditioning greatly improves alignment at high noise levels, hinting at the importance of abstract textual information, especially in the early stage of generation.
With the advent and widespread deployment of Multimodal Large Language Models (MLLMs), the imperative to ensure their safety has become increasingly pronounced. However, with the integration of additional modalities, MLLMs are exposed to new vulnerabilities, rendering them prone to structured-based jailbreak attacks, where semantic content (e.g., "harmful text") has been injected into the images to mislead MLLMs. In this work, we aim to defend against such threats. Specifically, we propose \textbf{Ada}ptive \textbf{Shield} Prompting (\textbf{AdaShield}), which prepends inputs with defense prompts to defend MLLMs against structure-based jailbreak attacks without fine-tuning MLLMs or training additional modules (e.g., post-stage content detector). Initially, we present a manually designed static defense prompt, which thoroughly examines the image and instruction content step by step and specifies response methods to malicious queries. Furthermore, we introduce an adaptive auto-refinement framework, consisting of a target MLLM and a LLM-based defense prompt generator (Defender). These components collaboratively and iteratively communicate to generate a defense prompt. Extensive experiments on the popular structure-based jailbreak attacks and benign datasets show that our methods can consistently improve MLLMs' robustness against structure-based jailbreak attacks without compromising the model's general capabilities evaluated on standard benign tasks. Our code is available at https://github.com/rain305f/AdaShield.
Templates serve as a good starting point to implement a design (e.g., banner, slide) but it takes great effort from designers to manually create. In this paper, we present Desigen, an automatic template creation pipeline which generates background images as well as harmonious layout elements over the background. Different from natural images, a background image should preserve enough non-salient space for the overlaying layout elements. To equip existing advanced diffusion-based models with stronger spatial control, we propose two simple but effective techniques to constrain the saliency distribution and reduce the attention weight in desired regions during the background generation process. Then conditioned on the background, we synthesize the layout with a Transformer-based autoregressive generator. To achieve a more harmonious composition, we propose an iterative inference strategy to adjust the synthesized background and layout in multiple rounds. We constructed a design dataset with more than 40k advertisement banners to verify our approach. Extensive experiments demonstrate that the proposed pipeline generates high-quality templates comparable to human designers. More than a single-page design, we further show an application of presentation generation that outputs a set of theme-consistent slides. The data and code are available at https://whaohan.github.io/desigen.
Event camera, a novel bio-inspired vision sensor, has drawn a lot of attention for its low latency, low power consumption, and high dynamic range. Currently, overfitting remains a critical problem in event-based classification tasks for Spiking Neural Network (SNN) due to its relatively weak spatial representation capability. Data augmentation is a simple but efficient method to alleviate overfitting and improve the generalization ability of neural networks, and saliency-based augmentation methods are proven to be effective in the image processing field. However, there is no approach available for extracting saliency maps from SNNs. Therefore, for the first time, we present Spiking Layer-Time-wise Relevance Propagation rule (SLTRP) and Spiking Layer-wise Relevance Propagation rule (SLRP) in order for SNN to generate stable and accurate CAMs and saliency maps. Based on this, we propose EventRPG, which leverages relevance propagation on the spiking neural network for more efficient augmentation. Our proposed method has been evaluated on several SNN structures, achieving state-of-the-art performance in object recognition tasks including N-Caltech101, CIFAR10-DVS, with accuracies of 85.62% and 85.55%, as well as action recognition task SL-Animals with an accuracy of 91.59%. Our code is available at https://github.com/myuansun/EventRPG.
Large Vision-Language Models (LVLMs) have shown significant progress in well responding to visual-instructions from users. However, these instructions, encompassing images and text, are susceptible to both intentional and inadvertent attacks. Despite the critical importance of LVLMs' robustness against such threats, current research in this area remains limited. To bridge this gap, we introduce AVIBench, a framework designed to analyze the robustness of LVLMs when facing various adversarial visual-instructions (AVIs), including four types of image-based AVIs, ten types of text-based AVIs, and nine types of content bias AVIs (such as gender, violence, cultural, and racial biases, among others). We generate 260K AVIs encompassing five categories of multimodal capabilities (nine tasks) and content bias. We then conduct a comprehensive evaluation involving 14 open-source LVLMs to assess their performance. AVIBench also serves as a convenient tool for practitioners to evaluate the robustness of LVLMs against AVIs. Our findings and extensive experimental results shed light on the vulnerabilities of LVLMs, and highlight that inherent biases exist even in advanced closed-source LVLMs like GeminiProVision and GPT-4V. This underscores the importance of enhancing the robustness, security, and fairness of LVLMs. The source code and benchmark will be made publicly available.
Semantic communications (SemCom) have emerged as a new paradigm for supporting sixth-generation applications, where semantic features of data are transmitted using artificial intelligence algorithms to attain high communication efficiencies. Most existing SemCom techniques utilize deep neural networks (DNNs) to implement analog source-channel mappings, which are incompatible with existing digital communication architectures. To address this issue, this paper proposes a novel framework of digital deep joint source-channel coding (D$^2$-JSCC) targeting image transmission in SemCom. The framework features digital source and channel codings that are jointly optimized to reduce the end-to-end (E2E) distortion. First, deep source coding with an adaptive density model is designed to encode semantic features according to their distributions. Second, digital channel coding is employed to protect encoded features against channel distortion. To facilitate their joint design, the E2E distortion is characterized as a function of the source and channel rates via the analysis of the Bayesian model and Lipschitz assumption on the DNNs. Then to minimize the E2E distortion, a two-step algorithm is proposed to control the source-channel rates for a given channel signal-to-noise ratio. Simulation results reveal that the proposed framework outperforms classic deep JSCC and mitigates the cliff and leveling-off effects, which commonly exist for separation-based approaches.
The class-conditional image generation based on diffusion models is renowned for generating high-quality and diverse images. However, most prior efforts focus on generating images for general categories, e.g., 1000 classes in ImageNet-1k. A more challenging task, large-scale fine-grained image generation, remains the boundary to explore. In this work, we present a parameter-efficient strategy, called FineDiffusion, to fine-tune large pre-trained diffusion models scaling to large-scale fine-grained image generation with 10,000 categories. FineDiffusion significantly accelerates training and reduces storage overhead by only fine-tuning tiered class embedder, bias terms, and normalization layers' parameters. To further improve the image generation quality of fine-grained categories, we propose a novel sampling method for fine-grained image generation, which utilizes superclass-conditioned guidance, specifically tailored for fine-grained categories, to replace the conventional classifier-free guidance sampling. Compared to full fine-tuning, FineDiffusion achieves a remarkable 1.56x training speed-up and requires storing merely 1.77% of the total model parameters, while achieving state-of-the-art FID of 9.776 on image generation of 10,000 classes. Extensive qualitative and quantitative experiments demonstrate the superiority of our method compared to other parameter-efficient fine-tuning methods. The code and more generated results are available at our project website: https://finediffusion.github.io/.