2024-08-26 更新
Penny-Wise and Pound-Foolish in Deepfake Detection
Authors:Yabin Wang, Zhiwu Huang, Su Zhou, Adam Prugel-Bennett, Xiaopeng Hong
The diffusion of deepfake technologies has sparked serious concerns about its potential misuse across various domains, prompting the urgent need for robust detection methods. Despite advancement, many current approaches prioritize short-term gains at expense of long-term effectiveness. This paper critiques the overly specialized approach of fine-tuning pre-trained models solely with a penny-wise objective on a single deepfake dataset, while disregarding the pound-wise balance for generalization and knowledge retention. To address this “Penny-Wise and Pound-Foolish” issue, we propose a novel learning framework (PoundNet) for generalization of deepfake detection on a pre-trained vision-language model. PoundNet incorporates a learnable prompt design and a balanced objective to preserve broad knowledge from upstream tasks (object classification) while enhancing generalization for downstream tasks (deepfake detection). We train PoundNet on a standard single deepfake dataset, following common practice in the literature. We then evaluate its performance across 10 public large-scale deepfake datasets with 5 main evaluation metrics-forming the largest benchmark test set for assessing the generalization ability of deepfake detection models, to our knowledge. The comprehensive benchmark evaluation demonstrates the proposed PoundNet is significantly less “Penny-Wise and Pound-Foolish”, achieving a remarkable improvement of 19% in deepfake detection performance compared to state-of-the-art methods, while maintaining a strong performance of 63% on object classification tasks, where other deepfake detection models tend to be ineffective. Code and data are open-sourced at https://github.com/iamwangyabin/PoundNet.
PDF
点此查看论文截图
An End-to-End Model for Photo-Sharing Multi-modal Dialogue Generation
Authors:Peiming Guo, Sinuo Liu, Yanzhao Zhang, Dingkun Long, Pengjun Xie, Meishan Zhang, Min Zhang
Photo-Sharing Multi-modal dialogue generation requires a dialogue agent not only to generate text responses but also to share photos at the proper moment. Using image text caption as the bridge, a pipeline model integrates an image caption model, a text generation model, and an image generation model to handle this complex multi-modal task. However, representing the images with text captions may loss important visual details and information and cause error propagation in the complex dialogue system. Besides, the pipeline model isolates the three models separately because discrete image text captions hinder end-to-end gradient propagation. We propose the first end-to-end model for photo-sharing multi-modal dialogue generation, which integrates an image perceptron and an image generator with a large language model. The large language model employs the Q-Former to perceive visual images in the input end. For image generation in the output end, we propose a dynamic vocabulary transformation matrix and use straight-through and gumbel-softmax techniques to align the large language model and stable diffusion model and achieve end-to-end gradient propagation. We perform experiments on PhotoChat and DialogCC datasets to evaluate our end-to-end model. Compared with pipeline models, the end-to-end model gains state-of-the-art performances on various metrics of text and image generation. More analysis experiments also verify the effectiveness of the end-to-end model for photo-sharing multi-modal dialogue generation.
PDF Work in progress
点此查看论文截图
Instruction-Based Molecular Graph Generation with Unified Text-Graph Diffusion Model
Authors:Yuran Xiang, Haiteng Zhao, Chang Ma, Zhi-Hong Deng
Recent advancements in computational chemistry have increasingly focused on synthesizing molecules based on textual instructions. Integrating graph generation with these instructions is complex, leading most current methods to use molecular sequences with pre-trained large language models. In response to this challenge, we propose a novel framework, named $\textbf{UTGDiff (Unified Text-Graph Diffusion Model)}$, which utilizes language models for discrete graph diffusion to generate molecular graphs from instructions. UTGDiff features a unified text-graph transformer as the denoising network, derived from pre-trained language models and minimally modified to process graph data through attention bias. Our experimental results demonstrate that UTGDiff consistently outperforms sequence-based baselines in tasks involving instruction-based molecule generation and editing, achieving superior performance with fewer parameters given an equivalent level of pretraining corpus. Our code is availble at https://github.com/ran1812/UTGDiff.
PDF
点此查看论文截图
Kubrick: Multimodal Agent Collaborations for Synthetic Video Generation
Authors:Liu He, Yizhi Song, Hejun Huang, Daniel Aliaga, Xin Zhou
Text-to-video generation has been dominated by end-to-end diffusion-based or autoregressive models. On one hand, those novel models provide plausible versatility, but they are criticized for physical correctness, shading and illumination, camera motion, and temporal consistency. On the other hand, film industry relies on manually-edited Computer-Generated Imagery (CGI) using 3D modeling software. Human-directed 3D synthetic videos and animations address the aforementioned shortcomings, but it is extremely tedious and requires tight collaboration between movie makers and 3D rendering experts. In this paper, we introduce an automatic synthetic video generation pipeline based on Vision Large Language Model (VLM) agent collaborations. Given a natural language description of a video, multiple VLM agents auto-direct various processes of the generation pipeline. They cooperate to create Blender scripts which render a video that best aligns with the given description. Based on film making inspiration and augmented with Blender-based movie making knowledge, the Director agent decomposes the input text-based video description into sub-processes. For each sub-process, the Programmer agent produces Python-based Blender scripts based on customized function composing and API calling. Then, the Reviewer agent, augmented with knowledge of video reviewing, character motion coordinates, and intermediate screenshots uses its compositional reasoning ability to provide feedback to the Programmer agent. The Programmer agent iteratively improves the scripts to yield the best overall video outcome. Our generated videos show better quality than commercial video generation models in 5 metrics on video quality and instruction-following performance. Moreover, our framework outperforms other approaches in a comprehensive user study on quality, consistency, and rationality.
PDF
点此查看论文截图
UniFashion: A Unified Vision-Language Model for Multimodal Fashion Retrieval and Generation
Authors:Xiangyu Zhao, Yuehan Zhang, Wenlong Zhang, Xiao-Ming Wu
The fashion domain encompasses a variety of real-world multimodal tasks, including multimodal retrieval and multimodal generation. The rapid advancements in artificial intelligence generated content, particularly in technologies like large language models for text generation and diffusion models for visual generation, have sparked widespread research interest in applying these multimodal models in the fashion domain. However, tasks involving embeddings, such as image-to-text or text-to-image retrieval, have been largely overlooked from this perspective due to the diverse nature of the multimodal fashion domain. And current research on multi-task single models lack focus on image generation. In this work, we present UniFashion, a unified framework that simultaneously tackles the challenges of multimodal generation and retrieval tasks within the fashion domain, integrating image generation with retrieval tasks and text generation tasks. UniFashion unifies embedding and generative tasks by integrating a diffusion model and LLM, enabling controllable and high-fidelity generation. Our model significantly outperforms previous single-task state-of-the-art models across diverse fashion tasks, and can be readily adapted to manage complex vision-language tasks. This work demonstrates the potential learning synergy between multimodal generation and retrieval, offering a promising direction for future research in the fashion domain. The source code is available at https://github.com/xiangyu-mm/UniFashion.
PDF
点此查看论文截图
CaRDiff: Video Salient Object Ranking Chain of Thought Reasoning for Saliency Prediction with Diffusion
Authors:Yunlong Tang, Gen Zhan, Li Yang, Yiting Liao, Chenliang Xu
Video saliency prediction aims to identify the regions in a video that attract human attention and gaze, driven by bottom-up features from the video and top-down processes like memory and cognition. Among these top-down influences, language plays a crucial role in guiding attention by shaping how visual information is interpreted. Existing methods primarily focus on modeling perceptual information while neglecting the reasoning process facilitated by language, where ranking cues are crucial outcomes of this process and practical guidance for saliency prediction. In this paper, we propose CaRDiff (Caption, Rank, and generate with Diffusion), a framework that imitates the process by integrating a multimodal large language model (MLLM), a grounding module, and a diffusion model, to enhance video saliency prediction. Specifically, we introduce a novel prompting method VSOR-CoT (Video Salient Object Ranking Chain of Thought), which utilizes an MLLM with a grounding module to caption video content and infer salient objects along with their rankings and positions. This process derives ranking maps that can be sufficiently leveraged by the diffusion model to decode the saliency maps for the given video accurately. Extensive experiments show the effectiveness of VSOR-CoT in improving the performance of video saliency prediction. The proposed CaRDiff performs better than state-of-the-art models on the MVS dataset and demonstrates cross-dataset capabilities on the DHF1k dataset through zero-shot evaluation.
PDF
点此查看论文截图
FlexEdit: Marrying Free-Shape Masks to VLLM for Flexible Image Editing
Authors:Jue Wang, Yuxiang Lin, Tianshuo Yuan, Zhi-Qi Cheng, Xiaolong Wang, Jiao GH, Wei Chen, Xiaojiang Peng
Combining Vision Large Language Models (VLLMs) with diffusion models offers a powerful method for executing image editing tasks based on human language instructions. However, language instructions alone often fall short in accurately conveying user requirements, particularly when users want to add, replace elements in specific areas of an image. Luckily, masks can effectively indicate the exact locations or elements to be edited, while they require users to precisely draw the shapes at the desired locations, which is highly user-unfriendly. To address this, we propose FlexEdit, an end-to-end image editing method that leverages both free-shape masks and language instructions for Flexible Editing. Our approach employs a VLLM in comprehending the image content, mask, and user instructions. Additionally, we introduce the Mask Enhance Adapter (MEA) that fuses the embeddings of the VLLM with the image data, ensuring a seamless integration of mask information and model output embeddings. Furthermore, we construct FSMI-Edit, a benchmark specifically tailored for free-shape mask, including 8 types of free-shape mask. Extensive experiments show that our method achieves state-of-the-art (SOTA) performance in LLM-based image editing, and our simple prompting technique stands out in its effectiveness. The code and data can be found at https://github.com/A-new-b/flex_edit.
PDF 15 pages, 14 figures
点此查看论文截图
ssProp: Energy-Efficient Training for Convolutional Neural Networks with Scheduled Sparse Back Propagation
Authors:Lujia Zhong, Shuo Huang, Yonggang Shi
Recently, deep learning has made remarkable strides, especially with generative modeling, such as large language models and probabilistic diffusion models. However, training these models often involves significant computational resources, requiring billions of petaFLOPs. This high resource consumption results in substantial energy usage and a large carbon footprint, raising critical environmental concerns. Back-propagation (BP) is a major source of computational expense during training deep learning models. To advance research on energy-efficient training and allow for sparse learning on any machine and device, we propose a general, energy-efficient convolution module that can be seamlessly integrated into any deep learning architecture. Specifically, we introduce channel-wise sparsity with additional gradient selection schedulers during backward based on the assumption that BP is often dense and inefficient, which can lead to over-fitting and high computational consumption. Our experiments demonstrate that our approach reduces 40\% computations while potentially improving model performance, validated on image classification and generation tasks. This reduction can lead to significant energy savings and a lower carbon footprint during the research and development phases of large-scale AI systems. Additionally, our method mitigates over-fitting in a manner distinct from Dropout, allowing it to be combined with Dropout to further enhance model performance and reduce computational resource usage. Extensive experiments validate that our method generalizes to a variety of datasets and tasks and is compatible with a wide range of deep learning architectures and modules. Code is publicly available at https://github.com/lujiazho/ssProp.
PDF Under review
点此查看论文截图
ParGo: Bridging Vision-Language with Partial and Global Views
Authors:An-Lan Wang, Bin Shan, Wei Shi, Kun-Yu Lin, Xiang Fei, Guozhi Tang, Lei Liao, Jingqun Tang, Can Huang, Wei-Shi Zheng
This work presents ParGo, a novel Partial-Global projector designed to connect the vision and language modalities for Multimodal Large Language Models (MLLMs). Unlike previous works that rely on global attention-based projectors, our ParGo bridges the representation gap between the separately pre-trained vision encoders and the LLMs by integrating global and partial views, which alleviates the overemphasis on prominent regions. To facilitate the effective training of ParGo, we collect a large-scale detail-captioned image-text dataset named ParGoCap-1M-PT, consisting of 1 million images paired with high-quality captions. Extensive experiments on several MLLM benchmarks demonstrate the effectiveness of our ParGo, highlighting its superiority in aligning vision and language modalities. Compared to conventional Q-Former projector, our ParGo achieves an improvement of 259.96 in MME benchmark. Furthermore, our experiments reveal that ParGo significantly outperforms other projectors, particularly in tasks that emphasize detail perception ability.
PDF
点此查看论文截图
Trustworthy, Responsible, and Safe AI: A Comprehensive Architectural Framework for AI Safety with Challenges and Mitigations
Authors:Chen Chen, Ziyao Liu, Weifeng Jiang, Goh Si Qi, KwoK-Yan Lam
AI Safety is an emerging area of critical importance to the safe adoption and deployment of AI systems. With the rapid proliferation of AI and especially with the recent advancement of Generative AI (or GAI), the technology ecosystem behind the design, development, adoption, and deployment of AI systems has drastically changed, broadening the scope of AI Safety to address impacts on public safety and national security. In this paper, we propose a novel architectural framework for understanding and analyzing AI Safety; defining its characteristics from three perspectives: Trustworthy AI, Responsible AI, and Safe AI. We provide an extensive review of current research and advancements in AI safety from these perspectives, highlighting their key challenges and mitigation approaches. Through examples from state-of-the-art technologies, particularly Large Language Models (LLMs), we present innovative mechanism, methodologies, and techniques for designing and testing AI safety. Our goal is to promote advancement in AI safety research, and ultimately enhance people’s trust in digital transformation.
PDF
点此查看论文截图
Open Llama2 Model for the Lithuanian Language
Authors:Artūras Nakvosas, Povilas Daniušis, Vytas Mulevičius
In this paper, we propose and describe the first open Llama2 large language models (LLMs) for the Lithuanian language, including an accompanying question/answer (Q/A) dataset and translations of popular LLM benchmarks. We provide a brief review of open regional LLMs and detailed information on the proposed LLMs and their training process. We also conduct an empirical evaluation, comparing the perplexities of the proposed LLMs with those of other modern open LLMs. In addition, benchmarking the proposed LLMs against language understanding tasks reveals that high-quality pretraining datasets may be essential for achieving models that perform efficiently on these benchmarks. The full realisations of the described LLMs are available in the accompanying open repository~\url{https://huggingface.co/neurotechnology}.
PDF 12 pages, 8 figures, 5 tables
点此查看论文截图
VFM-Det: Towards High-Performance Vehicle Detection via Large Foundation Models
Authors:Wentao Wu, Fanghua Hong, Xiao Wang, Chenglong Li, Jin Tang
Existing vehicle detectors are usually obtained by training a typical detector (e.g., YOLO, RCNN, DETR series) on vehicle images based on a pre-trained backbone (e.g., ResNet, ViT). Some researchers also exploit and enhance the detection performance using pre-trained large foundation models. However, we think these detectors may only get sub-optimal results because the large models they use are not specifically designed for vehicles. In addition, their results heavily rely on visual features, and seldom of they consider the alignment between the vehicle’s semantic information and visual representations. In this work, we propose a new vehicle detection paradigm based on a pre-trained foundation vehicle model (VehicleMAE) and a large language model (T5), termed VFM-Det. It follows the region proposal-based detection framework and the features of each proposal can be enhanced using VehicleMAE. More importantly, we propose a new VAtt2Vec module that predicts the vehicle semantic attributes of these proposals and transforms them into feature vectors to enhance the vision features via contrastive learning. Extensive experiments on three vehicle detection benchmark datasets thoroughly proved the effectiveness of our vehicle detector. Specifically, our model improves the baseline approach by $+5.1\%$, $+6.2\%$ on the $AP{0.5}$, $AP{0.75}$ metrics, respectively, on the Cityscapes dataset.The source code of this work will be released at https://github.com/Event-AHU/VFM-Det.
PDF In Peer Review
点此查看论文截图
DOMAINEVAL: An Auto-Constructed Benchmark for Multi-Domain Code Generation
Authors:Qiming Zhu, Jialun Cao, Yaojie Lu, Hongyu Lin, Xianpei Han, Le Sun, Shing-Chi Cheung
Code benchmarks such as HumanEval are widely adopted to evaluate the capabilities of Large Language Models (LLMs), providing insights into their strengths and weaknesses. However, current benchmarks primarily exercise LLMs’ capability on common coding tasks (e.g., bubble sort, greatest common divisor), leaving domain-specific coding tasks (e.g., computation, system, cryptography) unexplored. To fill this gap, we propose a multi-domain code benchmark, DOMAINEVAL, designed to evaluate LLMs’ coding capabilities thoroughly. Our pipeline works in a fully automated manner, enabling a push-bottom construction from code repositories into formatted subjects under study. Interesting findings are observed by evaluating 12 representative LLMs against DOMAINEVAL. We notice that LLMs are generally good at computation tasks while falling short on cryptography and system coding tasks. The performance gap can be as much as 68.94% (80.94% - 12.0%) in some LLMs. We also observe that generating more samples can increase the overall performance of LLMs, while the domain bias may even increase. The contributions of this study include a code generation benchmark dataset DOMAINEVAL, encompassing six popular domains, a fully automated pipeline for constructing code benchmarks, and an identification of the limitations of LLMs in code generation tasks based on their performance on DOMAINEVAL, providing directions for future research improvements. The leaderboard is available at https://domaineval.github.io/.
PDF
点此查看论文截图
Foundational Model for Electron Micrograph Analysis: Instruction-Tuning Small-Scale Language-and-Vision Assistant for Enterprise Adoption
Authors:Sakhinana Sagar Srinivas, Chidaksh Ravuru, Geethan Sannidhi, Venkataramana Runkana
Semiconductor imaging and analysis are critical yet understudied in deep learning, limiting our ability for precise control and optimization in semiconductor manufacturing. We introduce a small-scale multimodal framework for analyzing semiconductor electron microscopy images (MAEMI) through vision-language instruction tuning. We generate a customized instruction-following dataset using large multimodal models on microscopic image analysis. We perform knowledge transfer from larger to smaller models through knowledge distillation, resulting in improved accuracy of smaller models on visual question answering (VQA) tasks. This approach eliminates the need for expensive, human expert-annotated datasets for microscopic image analysis tasks. Enterprises can further finetune MAEMI on their intellectual data, enhancing privacy and performance on low-cost consumer hardware. Our experiments show that MAEMI outperforms traditional methods, adapts to data distribution shifts, and supports high-throughput screening.
PDF Our paper is published at ICML 2024 Workshop ML for Life and Material Science: From Theory to Industry Applications, Vienna, Austria
点此查看论文截图
MME-RealWorld: Could Your Multimodal LLM Challenge High-Resolution Real-World Scenarios that are Difficult for Humans?
Authors:Yi-Fan Zhang, Huanyu Zhang, Haochen Tian, Chaoyou Fu, Shuangqing Zhang, Junfei Wu, Feng Li, Kun Wang, Qingsong Wen, Zhang Zhang, Liang Wang, Rong Jin, Tieniu Tan
Comprehensive evaluation of Multimodal Large Language Models (MLLMs) has recently garnered widespread attention in the research community. However, we observe that existing benchmarks present several common barriers that make it difficult to measure the significant challenges that models face in the real world, including: 1) small data scale leads to a large performance variance; 2) reliance on model-based annotations results in restricted data quality; 3) insufficient task difficulty, especially caused by the limited image resolution. To tackle these issues, we introduce MME-RealWorld. Specifically, we collect more than $300$K images from public datasets and the Internet, filtering $13,366$ high-quality images for annotation. This involves the efforts of professional $25$ annotators and $7$ experts in MLLMs, contributing to $29,429$ question-answer pairs that cover $43$ subtasks across $5$ real-world scenarios, extremely challenging even for humans. As far as we know, MME-RealWorld is the largest manually annotated benchmark to date, featuring the highest resolution and a targeted focus on real-world applications. We further conduct a thorough evaluation involving $28$ prominent MLLMs, such as GPT-4o, Gemini 1.5 Pro, and Claude 3.5 Sonnet. Our results show that even the most advanced models struggle with our benchmarks, where none of them reach $60\%$ accuracy. The challenges of perceiving high-resolution images and understanding complex real-world scenarios remain urgent issues to be addressed. The data and evaluation code are released at https://mme-realworld.github.io/ .
PDF Project Page: $\href{https://mme-realworld.github.io/}{\text{https://mme-realworld.github.io/}}$
点此查看论文截图