Diffusion models have demonstrated remarkable and robust abilities in both image and video generation. To achieve greater control over generated results, researchers introduce additional architectures, such as ControlNet, Adapters and ReferenceNet, to integrate conditioning controls. However, current controllable generation methods often require substantial additional computational resources, especially for video generation, and face challenges in training or exhibit weak control. In this paper, we propose ControlNeXt: a powerful and efficient method for controllable image and video generation. We first design a more straightforward and efficient architecture, replacing heavy additional branches with minimal additional cost compared to the base model. Such a concise structure also allows our method to seamlessly integrate with other LoRA weights, enabling style alteration without the need for additional training. As for training, we reduce up to 90% of learnable parameters compared to the alternatives. Furthermore, we propose another method called Cross Normalization (CN) as a replacement for Zero-Convolution' to achieve fast and stable training convergence. We have conducted various experiments with different base models across images and videos, demonstrating the robustness of our method.
相關內容
Text-to-video diffusion models have made remarkable advancements. Driven by their ability to generate temporally coherent videos, research on zero-shot video editing using these fundamental models has expanded rapidly. To enhance editing quality, structural controls are frequently employed in video editing. Among these techniques, cross-attention mask control stands out for its effectiveness and efficiency. However, when cross-attention masks are naively applied to video editing, they can introduce artifacts such as blurring and flickering. Our experiments uncover a critical factor overlooked in previous video editing research: cross-attention masks are not consistently clear but vary with model structure and denoising timestep. To address this issue, we propose the metric Mask Matching Cost (MMC) that quantifies this variability and propose FreeMask, a method for selecting optimal masks tailored to specific video editing tasks. Using MMC-selected masks, we further improve the masked fusion mechanism within comprehensive attention features, e.g., temp, cross, and self-attention modules. Our approach can be seamlessly integrated into existing zero-shot video editing frameworks with better performance, requiring no control assistance or parameter fine-tuning but enabling adaptive decoupling of unedited semantic layouts with mask precision control. Extensive experiments demonstrate that FreeMask achieves superior semantic fidelity, temporal consistency, and editing quality compared to state-of-the-art methods.
The arrival of Sora marks a new era for text-to-video diffusion models, bringing significant advancements in video generation and potential applications. However, Sora, along with other text-to-video diffusion models, is highly reliant on prompts, and there is no publicly available dataset that features a study of text-to-video prompts. In this paper, we introduce VidProM, the first large-scale dataset comprising 1.67 Million unique text-to-Video Prompts from real users. Additionally, this dataset includes 6.69 million videos generated by four state-of-the-art diffusion models, alongside some related data. We initially discuss the curation of this large-scale dataset, a process that is both time-consuming and costly. Subsequently, we underscore the need for a new prompt dataset specifically designed for text-to-video generation by illustrating how VidProM differs from DiffusionDB, a large-scale prompt-gallery dataset for image generation. Our extensive and diverse dataset also opens up many exciting new research areas. For instance, we suggest exploring text-to-video prompt engineering, efficient video generation, and video copy detection for diffusion models to develop better, more efficient, and safer models. The project (including the collected dataset VidProM and related code) is publicly available at //vidprom.github.io under the CC-BY-NC 4.0 License.
Data heterogeneity among Federated Learning (FL) users poses a significant challenge, resulting in reduced global model performance. The community has designed various techniques to tackle this issue, among which Knowledge Distillation (KD)-based techniques are common. While these techniques effectively improve performance under high heterogeneity, they inadvertently cause higher accuracy degradation under model poisoning attacks (known as attack amplification). This paper presents a case study to reveal this critical vulnerability in KD-based FL systems. We show why KD causes this issue through empirical evidence and use it as motivation to design a hybrid distillation technique. We introduce a novel algorithm, Hybrid Knowledge Distillation for Robust and Accurate FL (HYDRA-FL), which reduces the impact of attacks in attack scenarios by offloading some of the KD loss to a shallow layer via an auxiliary classifier. We model HYDRA-FL as a generic framework and adapt it to two KD-based FL algorithms, FedNTD and MOON. Using these two as case studies, we demonstrate that our technique outperforms baselines in attack settings while maintaining comparable performance in benign settings.
Recent advancements in integrating Large Language Models (LLM) with automatic speech recognition (ASR) have performed remarkably in general domains. While supervised fine-tuning (SFT) of all model parameters is often employed to adapt pre-trained LLM-based ASR models to specific domains, it imposes high computational costs and notably reduces their performance in general domains. In this paper, we propose a novel parameter-efficient multi-domain fine-tuning method for adapting pre-trained LLM-based ASR models to multi-accent domains without catastrophic forgetting named \textit{HDMoLE}, which leverages hierarchical routing and dynamic thresholds based on combining low-rank adaptation (LoRA) with the mixer of experts (MoE) and can be generalized to any linear layer. Hierarchical routing establishes a clear correspondence between LoRA experts and accent domains, improving cross-domain collaboration among the LoRA experts. Unlike the static Top-K strategy for activating LoRA experts, dynamic thresholds can adaptively activate varying numbers of LoRA experts at each MoE layer. Experiments on the multi-accent and standard Mandarin datasets demonstrate the efficacy of HDMoLE. Applying HDMoLE to an LLM-based ASR model projector module achieves similar performance to full fine-tuning in the target multi-accent domains while using only 9.6% of the trainable parameters required for full fine-tuning and minimal degradation in the source general domain.
User experience in real-time video applications requires continuously adjusting video encoding bitrates to match available network capacity, which hinges on accurate bandwidth estimation (BWE). However, network heterogeneity prevents a one-size-fits-all solution to BWE, motivating the demand for personalized approaches. Although personalizing BWE algorithms offers benefits such as improved adaptability to individual network conditions, it faces the challenge of data drift -- where estimators degrade over time due to evolving network environments. To address this, we introduce Ivy, a novel method for BWE that leverages offline metalearning to tackle data drift and maximize end-user Quality of Experience (QoE). Our key insight is that dynamically selecting the most suitable BWE algorithm for current network conditions allows for more effective adaption to changing environments. Ivy is trained entirely offline using Implicit Q-learning, enabling it to learn from individual network conditions without a single, live videoconferencing interaction, thereby reducing deployment complexity and making Ivy more practical for real-world personalization. We implemented our method in a popular videoconferencing application and demonstrated that Ivy can enhance QoE by 5.9% to 11.2% over individual BWE algorithms and by 6.3% to 11.4% compared to existing online meta heuristics.
The advent of edge computing has made real-time intelligent video analytics feasible. Previous works, based on traditional model architecture (e.g., CNN, RNN, etc.), employ various strategies to filter out non-region-of-interest content to minimize bandwidth and computation consumption but show inferior performance in adverse environments. Recently, visual foundation models based on transformers have shown great performance in adverse environments due to their amazing generalization capability. However, they require a large amount of computation power, which limits their applications in real-time intelligent video analytics. In this paper, we find visual foundation models like Vision Transformer (ViT) also have a dedicated acceleration mechanism for video analytics. To this end, we introduce Arena, an end-to-end edge-assisted video inference acceleration system based on ViT. We leverage the capability of ViT that can be accelerated through token pruning by only offloading and feeding Patches-of-Interest to the downstream models. Additionally, we design an adaptive keyframe inference switching algorithm tailored to different videos, capable of adapting to the current video content to jointly optimize accuracy and bandwidth. Through extensive experiments, our findings reveal that Arena can boost inference speeds by up to 1.58\(\times\) and 1.82\(\times\) on average while consuming only 47\% and 31\% of the bandwidth, respectively, all with high inference accuracy.
Diffusion models (DMs) have shown great potential for high-quality image synthesis. However, when it comes to producing images with complex scenes, how to properly describe both image global structures and object details remains a challenging task. In this paper, we present Frido, a Feature Pyramid Diffusion model performing a multi-scale coarse-to-fine denoising process for image synthesis. Our model decomposes an input image into scale-dependent vector quantized features, followed by a coarse-to-fine gating for producing image output. During the above multi-scale representation learning stage, additional input conditions like text, scene graph, or image layout can be further exploited. Thus, Frido can be also applied for conditional or cross-modality image synthesis. We conduct extensive experiments over various unconditioned and conditional image generation tasks, ranging from text-to-image synthesis, layout-to-image, scene-graph-to-image, to label-to-image. More specifically, we achieved state-of-the-art FID scores on five benchmarks, namely layout-to-image on COCO and OpenImages, scene-graph-to-image on COCO and Visual Genome, and label-to-image on COCO. Code is available at //github.com/davidhalladay/Frido.
Existing knowledge graph (KG) embedding models have primarily focused on static KGs. However, real-world KGs do not remain static, but rather evolve and grow in tandem with the development of KG applications. Consequently, new facts and previously unseen entities and relations continually emerge, necessitating an embedding model that can quickly learn and transfer new knowledge through growth. Motivated by this, we delve into an expanding field of KG embedding in this paper, i.e., lifelong KG embedding. We consider knowledge transfer and retention of the learning on growing snapshots of a KG without having to learn embeddings from scratch. The proposed model includes a masked KG autoencoder for embedding learning and update, with an embedding transfer strategy to inject the learned knowledge into the new entity and relation embeddings, and an embedding regularization method to avoid catastrophic forgetting. To investigate the impacts of different aspects of KG growth, we construct four datasets to evaluate the performance of lifelong KG embedding. Experimental results show that the proposed model outperforms the state-of-the-art inductive and lifelong embedding baselines.
Multi-agent influence diagrams (MAIDs) are a popular form of graphical model that, for certain classes of games, have been shown to offer key complexity and explainability advantages over traditional extensive form game (EFG) representations. In this paper, we extend previous work on MAIDs by introducing the concept of a MAID subgame, as well as subgame perfect and trembling hand perfect equilibrium refinements. We then prove several equivalence results between MAIDs and EFGs. Finally, we describe an open source implementation for reasoning about MAIDs and computing their equilibria.
Interest point descriptors have fueled progress on almost every problem in computer vision. Recent advances in deep neural networks have enabled task-specific learned descriptors that outperform hand-crafted descriptors on many problems. We demonstrate that commonly used metric learning approaches do not optimally leverage the feature hierarchies learned in a Convolutional Neural Network (CNN), especially when applied to the task of geometric feature matching. While a metric loss applied to the deepest layer of a CNN, is often expected to yield ideal features irrespective of the task, in fact the growing receptive field as well as striding effects cause shallower features to be better at high precision matching tasks. We leverage this insight together with explicit supervision at multiple levels of the feature hierarchy for better regularization, to learn more effective descriptors in the context of geometric matching tasks. Further, we propose to use activation maps at different layers of a CNN, as an effective and principled replacement for the multi-resolution image pyramids often used for matching tasks. We propose concrete CNN architectures employing these ideas, and evaluate them on multiple datasets for 2D and 3D geometric matching as well as optical flow, demonstrating state-of-the-art results and generalization across datasets.
小貼士
登錄享
相關主題
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191