Multimodal summarization aims to generate a concise summary based on the input text and image. However, the existing methods potentially suffer from unfactual output. To evaluate the factuality of multimodal summarization models, we propose two fine-grained and explainable evaluation frameworks (FALLACIOUS) for different application scenarios, i.e. reference-based factuality evaluation framework and reference-free factuality evaluation framework. Notably, the reference-free factuality evaluation framework doesn't need ground truth and hence it has a wider application scenario. To evaluate the effectiveness of the proposed frameworks, we compute the correlation between our frameworks and the other metrics. The experimental results show the effectiveness of our proposed method. We will release our code and dataset via github.
Infrared image destriping seeks to restore high-quality content from degraded images. Recent works mainly address this task by leveraging prior knowledge to separate stripe noise from the degraded image. However, constructing a robust decoupling model for that purpose remains challenging, especially when significant similarities exist between the stripe noise and vertical background structure. Addressing that, we introduce Asymmetric Residual wavelet Column correction Network (ARCNet) for image destriping, aiming to consistently preserve spatially precise high-resolution representations. Our neural model leverages a novel downsampler, residual haar discrete wavelet transform (RHDWT), stripe directional prior knowledge and data-driven learning to induce a model with enriched feature representation of stripe noise and background. In our technique, the inverse wavelet transform is replaced by transposed convolution for feature upsampling, which can suppress noise crosstalk and encourage the network to focus on robust image reconstruction. After each sampling, a proposed column non-uniformity correction module (CNCM) is leveraged by our method to enhance column uniformity, spatial correlation, and global self-dependence between each layer component. CNCM can establish structural characteristics of stripe noise and utilize contextual information at long-range dependencies to distinguish stripes with varying intensities and distributions. Extensive experiments on synthetic data, real data, and infrared small target detection tasks show that the proposed method outperforms state-of-the-art single-image destriping methods both visually and quantitatively by a considerable margin. Our code will be made publicly available at \url{https://github.com/xdFai}.
Connecting text and visual modalities plays an essential role in generative intelligence. For this reason, inspired by the success of large language models, significant research efforts are being devoted to the development of Multimodal Large Language Models (MLLMs). These models can seamlessly integrate visual and textual modalities, both as input and output, while providing a dialogue-based interface and instruction-following capabilities. In this paper, we provide a comprehensive review of recent visual-based MLLMs, analyzing their architectural choices, multimodal alignment strategies, and training techniques. We also conduct a detailed analysis of these models across a wide range of tasks, including visual grounding, image generation and editing, visual understanding, and domain-specific applications. Additionally, we compile and describe training datasets and evaluation benchmarks, conducting comparisons among existing models in terms of performance and computational requirements. Overall, this survey offers a comprehensive overview of the current state of the art, laying the groundwork for future MLLMs.
Object detection in documents is a key step to automate the structural elements identification process in a digital or scanned document through understanding the hierarchical structure and relationships between different elements. Large and complex models, while achieving high accuracy, can be computationally expensive and memory-intensive, making them impractical for deployment on resource constrained devices. Knowledge distillation allows us to create small and more efficient models that retain much of the performance of their larger counterparts. Here we present a graph-based knowledge distillation framework to correctly identify and localize the document objects in a document image. Here, we design a structured graph with nodes containing proposal-level features and edges representing the relationship between the different proposal regions. Also, to reduce text bias an adaptive node sampling strategy is designed to prune the weight distribution and put more weightage on non-text nodes. We encode the complete graph as a knowledge representation and transfer it from the teacher to the student through the proposed distillation loss by effectively capturing both local and global information concurrently. Extensive experimentation on competitive benchmarks demonstrates that the proposed framework outperforms the current state-of-the-art approaches. The code will be available at: https://github.com/ayanban011/GraphKD.
Deep neural networks are extensively applied to real-world tasks, such as face recognition and medical image classification, where privacy and data protection are critical. Image data, if not protected, can be exploited to infer personal or contextual information. Existing privacy preservation methods, like encryption, generate perturbed images that are unrecognizable to even humans. Adversarial attack approaches prohibit automated inference even for authorized stakeholders, limiting practical incentives for commercial and widespread adaptation. This pioneering study tackles an unexplored practical privacy preservation use case by generating human-perceivable images that maintain accurate inference by an authorized model while evading other unauthorized black-box models of similar or dissimilar objectives, and addresses the previous research gaps. The datasets employed are ImageNet, for image classification, Celeba-HQ dataset, for identity classification, and AffectNet, for emotion classification. Our results show that the generated images can successfully maintain the accuracy of a protected model and degrade the average accuracy of the unauthorized black-box models to 11.97%, 6.63%, and 55.51% on ImageNet, Celeba-HQ, and AffectNet datasets, respectively.
Diffusion models have achieved remarkable success in generating high quality image and video data. More recently, they have also been used for image compression with high perceptual quality. In this paper, we present a novel approach to extreme video compression leveraging the predictive power of diffusion-based generative models at the decoder. The conditional diffusion model takes several neural compressed frames and generates subsequent frames. When the reconstruction quality drops below the desired level, new frames are encoded to restart prediction. The entire video is sequentially encoded to achieve a visually pleasing reconstruction, considering perceptual quality metrics such as the learned perceptual image patch similarity (LPIPS) and the Frechet video distance (FVD), at bit rates as low as 0.02 bits per pixel (bpp). Experimental results demonstrate the effectiveness of the proposed scheme compared to standard codecs such as H.264 and H.265 in the low bpp regime. The results showcase the potential of exploiting the temporal relations in video data using generative models. Code is available at: https://github.com/ElesionKyrie/Extreme-Video-Compression-With-Prediction-Using-Pre-trainded-Diffusion-Models-
In recent years, synthetic visual instructions by generative language model have demonstrated plausible text generation performance on the visual question-answering tasks. However, challenges persist in the hallucination of generative language models, i.e., the generated image-text data contains unintended contents. This paper presents a novel and scalable method for generating visually dehallucinative instructions, dubbed CAP2QA, that constrains the scope to only image contents. Our key contributions lie in introducing image-aligned instructive QA dataset CAP2QA-COCO and its scalable recipe. In our experiments, we compare synthetic visual instruction datasets that share the same source data by visual instruction tuning and conduct general visual recognition tasks. It shows that our proposed method significantly reduces visual hallucination while consistently improving visual recognition ability and expressiveness.
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.
In this paper, we propose a new setting for generating product descriptions from images, augmented by marketing keywords. It leverages the combined power of visual and textual information to create descriptions that are more tailored to the unique features of products. For this setting, previous methods utilize visual and textual encoders to encode the image and keywords and employ a language model-based decoder to generate the product description. However, the generated description is often inaccurate and generic since same-category products have similar copy-writings, and optimizing the overall framework on large-scale samples makes models concentrate on common words yet ignore the product features. To alleviate the issue, we present a simple and effective Multimodal In-Context Tuning approach, named ModICT, which introduces a similar product sample as the reference and utilizes the in-context learning capability of language models to produce the description. During training, we keep the visual encoder and language model frozen, focusing on optimizing the modules responsible for creating multimodal in-context references and dynamic prompts. This approach preserves the language generation prowess of large language models (LLMs), facilitating a substantial increase in description diversity. To assess the effectiveness of ModICT across various language model scales and types, we collect data from three distinct product categories within the E-commerce domain. Extensive experiments demonstrate that ModICT significantly improves the accuracy (by up to 3.3% on Rouge-L) and diversity (by up to 9.4% on D-5) of generated results compared to conventional methods. Our findings underscore the potential of ModICT as a valuable tool for enhancing automatic generation of product descriptions in a wide range of applications.
Efforts to decode neural network vision models necessitate a comprehensive grasp of both the spatial and semantic facets governing feature responses within images. Most research has primarily centered around attribution methods, which provide explanations in the form of heatmaps, showing where the model directs its attention for a given feature. However, grasping 'where' alone falls short, as numerous studies have highlighted the limitations of those methods and the necessity to understand 'what' the model has recognized at the focal point of its attention. In parallel, 'Feature visualization' offers another avenue for interpreting neural network features. This approach synthesizes an optimal image through gradient ascent, providing clearer insights into 'what' features respond to. However, feature visualizations only provide one global explanation per feature; they do not explain why features activate for particular images. In this work, we introduce a new method to the interpretability tool-kit, 'feature accentuation', which is capable of conveying both where and what in arbitrary input images induces a feature's response. At its core, feature accentuation is image-seeded (rather than noise-seeded) feature visualization. We find a particular combination of parameterization, augmentation, and regularization yields naturalistic visualizations that resemble the seed image and target feature simultaneously. Furthermore, we validate these accentuations are processed along a natural circuit by the model. We make our precise implementation of feature accentuation available to the community as the Faccent library, an extension of Lucent.