Recent advances in tuning-free personalized image generation based on diffusion models are impressive. However, to improve subject fidelity, existing methods either retrain the diffusion model or infuse it with dense visual embeddings, both of which suffer from poor generalization and efficiency. Also, these methods falter in multi-subject image generation due to the unconstrained cross-attention mechanism. In this paper, we propose MM-Diff, a unified and tuning-free image personalization framework capable of generating high-fidelity images of both single and multiple subjects in seconds. Specifically, to simultaneously enhance text consistency and subject fidelity, MM-Diff employs a vision encoder to transform the input image into CLS and patch embeddings. CLS embeddings are used on the one hand to augment the text embeddings, and on the other hand together with patch embeddings to derive a small number of detail-rich subject embeddings, both of which are efficiently integrated into the diffusion model through the well-designed multimodal cross-attention mechanism. Additionally, MM-Diff introduces cross-attention map constraints during the training phase, ensuring flexible multi-subject image sampling during inference without any predefined inputs (e.g., layout). Extensive experiments demonstrate the superior performance of MM-Diff over other leading methods.
相關內容
Integration：Integration, the VLSI Journal。
Explanation：集成，VLSI雜志。
Publisher：Elsevier。
SIT：
Text-to-image diffusion models pre-trained on billions of image-text pairs have recently enabled 3D content creation by optimizing a randomly initialized differentiable 3D representation with score distillation. However, the optimization process suffers slow convergence and the resultant 3D models often exhibit two limitations: (a) quality concerns such as missing attributes and distorted shape and texture; (b) extremely low diversity comparing to text-guided image synthesis. In this paper, we show that the conflict between the 3D optimization process and uniform timestep sampling in score distillation is the main reason for these limitations. To resolve this conflict, we propose to prioritize timestep sampling with monotonically non-increasing functions, which aligns the 3D optimization process with the sampling process of diffusion model. Extensive experiments show that our simple redesign significantly improves 3D content creation with faster convergence, better quality and diversity.
As the development of large-scale Generative AI models evolve beyond text (1D) generation to include image (2D) and video (3D) generation, processing spatial and temporal information presents unique challenges to quality, performance, and efficiency. We present the first work towards understanding this new system design space for multi-modal text-to-image (TTI) and text-to-video (TTV) generation models. Current model architecture designs are bifurcated into 2 categories: Diffusion- and Transformer-based models. Our systematic performance characterization on a suite of eight representative TTI/TTV models shows that after state-of-the-art optimization techniques such as Flash Attention are applied, Convolution accounts for up to 44% of execution time for Diffusion-based TTI models, while Linear layers consume up to 49% of execution time for Transformer-based models. We additionally observe that Diffusion-based TTI models resemble the Prefill stage of LLM inference, and benefit from 1.1-2.5x greater speedup from Flash Attention than Transformer-based TTI models that resemble the Decode phase. Since optimizations designed for LLMs do not map directly onto TTI/TTV models, we must conduct a thorough characterization of these workloads to gain insights for new optimization opportunities. In doing so, we define sequence length in the context of TTI/TTV models and observe sequence length can vary up to 4x in Diffusion model inference. We additionally observe temporal aspects of TTV workloads pose unique system bottlenecks, with Temporal Attention accounting for over 60% of total Attention time. Overall, our in-depth system performance characterization is a critical first step towards designing efficient and deployable systems for emerging TTI/TTV workloads.
Text-to-image generative models, especially those based on latent diffusion models (LDMs), have demonstrated outstanding ability in generating high-quality and high-resolution images from textual prompts. With this advancement, various fine-tuning methods have been developed to personalize text-to-image models for specific applications such as artistic style adaptation and human face transfer. However, such advancements have raised copyright concerns, especially when the data are used for personalization without authorization. For example, a malicious user can employ fine-tuning techniques to replicate the style of an artist without consent. In light of this concern, we propose FT-Shield, a watermarking solution tailored for the fine-tuning of text-to-image diffusion models. FT-Shield addresses copyright protection challenges by designing new watermark generation and detection strategies. In particular, it introduces an innovative algorithm for watermark generation. It ensures the seamless transfer of watermarks from training images to generated outputs, facilitating the identification of copyrighted material use. To tackle the variability in fine-tuning methods and their impact on watermark detection, FT-Shield integrates a Mixture of Experts (MoE) approach for watermark detection. Comprehensive experiments validate the effectiveness of our proposed FT-Shield.
Recent few-shot action recognition (FSAR) methods achieve promising performance by performing semantic matching on learned discriminative features. However, most FSAR methods focus on single-scale (e.g., frame-level, segment-level, \etc) feature alignment, which ignores that human actions with the same semantic may appear at different velocities. To this end, we develop a novel Multi-Velocity Progressive-alignment (MVP-Shot) framework to progressively learn and align semantic-related action features at multi-velocity levels. Concretely, a Multi-Velocity Feature Alignment (MVFA) module is designed to measure the similarity between features from support and query videos with different velocity scales and then merge all similarity scores in a residual fashion. To avoid the multiple velocity features deviating from the underlying motion semantic, our proposed Progressive Semantic-Tailored Interaction (PSTI) module injects velocity-tailored text information into the video feature via feature interaction on channel and temporal domains at different velocities. The above two modules compensate for each other to predict query categories more accurately under the few-shot settings. Experimental results show our method outperforms current state-of-the-art methods on multiple standard few-shot benchmarks (i.e., HMDB51, UCF101, Kinetics, and SSv2-small).
Speech-to-text services aim to transcribe input audio as accurately as possible. They increasingly play a role in everyday life, for example in personal voice assistants or in customer-company interactions. We evaluate Open AI's Whisper, a state-of-the-art automated speech recognition service outperforming industry competitors, as of 2023. While many of Whisper's transcriptions were highly accurate, we find that roughly 1\% of audio transcriptions contained entire hallucinated phrases or sentences which did not exist in any form in the underlying audio. We thematically analyze the Whisper-hallucinated content, finding that 38\% of hallucinations include explicit harms such as perpetuating violence, making up inaccurate associations, or implying false authority. We then study why hallucinations occur by observing the disparities in hallucination rates between speakers with aphasia (who have a lowered ability to express themselves using speech and voice) and a control group. We find that hallucinations disproportionately occur for individuals who speak with longer shares of non-vocal durations -- a common symptom of aphasia. We call on industry practitioners to ameliorate these language-model-based hallucinations in Whisper, and to raise awareness of potential biases amplified by hallucinations in downstream applications of speech-to-text models.
The recent years have witnessed a great array of large multimodal models (LMMs) to effectively solve single-image vision language tasks. However, their abilities to solve multi-image visual language tasks is yet to be improved. The existing multi-image LMMs (e.g. OpenFlamingo, Emu, Idefics, etc) mostly gain their multi-image ability through pre-training on hundreds of millions of noisy interleaved image-text data from web, which is neither efficient nor effective. In this paper, we aim at building strong multi-image LMMs via instruction tuning with academic-level resources. Therefore, we meticulously construct Mantis-Instruct containing 721K instances from 14 multi-image datasets. We design Mantis-Instruct to cover different multi-image skills like co-reference, reasoning, comparing, temporal understanding. We combine Mantis-Instruct with several single-image visual-language datasets to train our model Mantis to handle any interleaved image-text inputs. We evaluate the trained Mantis on five multi-image benchmarks and eight single-image benchmarks. Though only requiring academic-level resources (i.e. 36 hours on 16xA100-40G), Mantis-8B can achieve state-of-the-art performance on all the multi-image benchmarks and beats the existing best multi-image LMM Idefics2-8B by an average of 9 absolute points. We observe that Mantis performs equivalently well on the held-in and held-out evaluation benchmarks. We further evaluate Mantis on single-image benchmarks and demonstrate that Mantis can maintain a strong single-image performance on par with CogVLM and Emu2. Our results are particularly encouraging as it shows that low-cost instruction tuning is indeed much more effective than intensive pre-training in terms of building multi-image LMMs.
Large Vision-Language models (VLMs) have demonstrated strong reasoning capabilities in tasks requiring a fine-grained understanding of literal images and text, such as visual question-answering or visual entailment. However, there has been little exploration of these models' capabilities when presented with images and captions containing figurative phenomena such as metaphors or humor, the meaning of which is often implicit. To close this gap, we propose a new task and a high-quality dataset: Visual Figurative Language Understanding with Textual Explanations (V-FLUTE). We frame the visual figurative language understanding problem as an explainable visual entailment task, where the model has to predict whether the image (premise) entails a claim (hypothesis) and justify the predicted label with a textual explanation. Using a human-AI collaboration framework, we build a high-quality dataset, V-FLUTE, that contains 6,027 <image, claim, label, explanation> instances spanning five diverse multimodal figurative phenomena: metaphors, similes, idioms, sarcasm, and humor. The figurative phenomena can be present either in the image, the caption, or both. We further conduct both automatic and human evaluations to assess current VLMs' capabilities in understanding figurative phenomena.
Data-Free Meta-Learning (DFML) aims to extract knowledge from a collection of pre-trained models without requiring the original data, presenting practical benefits in contexts constrained by data privacy concerns. Current DFML methods primarily focus on the data recovery from these pre-trained models. However, they suffer from slow recovery speed and overlook gaps inherent in heterogeneous pre-trained models. In response to these challenges, we introduce the Faster and Better Data-Free Meta-Learning (FREE) framework, which contains: (i) a meta-generator for rapidly recovering training tasks from pre-trained models; and (ii) a meta-learner for generalizing to new unseen tasks. Specifically, within the module Faster Inversion via Meta-Generator, each pre-trained model is perceived as a distinct task. The meta-generator can rapidly adapt to a specific task in just five steps, significantly accelerating the data recovery. Furthermore, we propose Better Generalization via Meta-Learner and introduce an implicit gradient alignment algorithm to optimize the meta-learner. This is achieved as aligned gradient directions alleviate potential conflicts among tasks from heterogeneous pre-trained models. Empirical experiments on multiple benchmarks affirm the superiority of our approach, marking a notable speed-up (20$\times$) and performance enhancement (1.42\% $\sim$ 4.78\%) in comparison to the state-of-the-art.
In many visual systems, visual tracking often bases on RGB image sequences, in which some targets are invalid in low-light conditions, and tracking performance is thus affected significantly. Introducing other modalities such as depth and infrared data is an effective way to handle imaging limitations of individual sources, but multi-modal imaging platforms usually require elaborate designs and cannot be applied in many real-world applications at present. Near-infrared (NIR) imaging becomes an essential part of many surveillance cameras, whose imaging is switchable between RGB and NIR based on the light intensity. These two modalities are heterogeneous with very different visual properties and thus bring big challenges for visual tracking. However, existing works have not studied this challenging problem. In this work, we address the cross-modal object tracking problem and contribute a new video dataset, including 654 cross-modal image sequences with over 481K frames in total, and the average video length is more than 735 frames. To promote the research and development of cross-modal object tracking, we propose a new algorithm, which learns the modality-aware target representation to mitigate the appearance gap between RGB and NIR modalities in the tracking process. It is plug-and-play and could thus be flexibly embedded into different tracking frameworks. Extensive experiments on the dataset are conducted, and we demonstrate the effectiveness of the proposed algorithm in two representative tracking frameworks against 17 state-of-the-art tracking methods. We will release the dataset for free academic usage, dataset download link and code will be released soon.
Images can convey rich semantics and induce various emotions in viewers. Recently, with the rapid advancement of emotional intelligence and the explosive growth of visual data, extensive research efforts have been dedicated to affective image content analysis (AICA). In this survey, we will comprehensively review the development of AICA in the recent two decades, especially focusing on the state-of-the-art methods with respect to three main challenges -- the affective gap, perception subjectivity, and label noise and absence. We begin with an introduction to the key emotion representation models that have been widely employed in AICA and description of available datasets for performing evaluation with quantitative comparison of label noise and dataset bias. We then summarize and compare the representative approaches on (1) emotion feature extraction, including both handcrafted and deep features, (2) learning methods on dominant emotion recognition, personalized emotion prediction, emotion distribution learning, and learning from noisy data or few labels, and (3) AICA based applications. Finally, we discuss some challenges and promising research directions in the future, such as image content and context understanding, group emotion clustering, and viewer-image interaction.
小貼士
登錄享
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191