Abstract:We introduce Presto, a novel video diffusion model designed to generate 15-second videos with long-range coherence and rich content. Extending video generation methods to maintain scenario diversity over long durations presents significant challenges. To address this, we propose a Segmented Cross-Attention (SCA) strategy, which splits hidden states into segments along the temporal dimension, allowing each segment to cross-attend to a corresponding sub-caption. SCA requires no additional parameters, enabling seamless incorporation into current DiT-based architectures. To facilitate high-quality long video generation, we build the LongTake-HD dataset, consisting of 261k content-rich videos with scenario coherence, annotated with an overall video caption and five progressive sub-captions. Experiments show that our Presto achieves 78.5% on the VBench Semantic Score and 100% on the Dynamic Degree, outperforming existing state-of-the-art video generation methods. This demonstrates that our proposed Presto significantly enhances content richness, maintains long-range coherence, and captures intricate textual details. More details are displayed on our project page: https://presto-video.github.io/.
Abstract:Current methods for generating human motion videos rely on extracting pose sequences from reference videos, which restricts flexibility and control. Additionally, due to the limitations of pose detection techniques, the extracted pose sequences can sometimes be inaccurate, leading to low-quality video outputs. We introduce a novel task aimed at generating human motion videos solely from reference images and natural language. This approach offers greater flexibility and ease of use, as text is more accessible than the desired guidance videos. However, training an end-to-end model for this task requires millions of high-quality text and human motion video pairs, which are challenging to obtain. To address this, we propose a new framework called Fleximo, which leverages large-scale pre-trained text-to-3D motion models. This approach is not straightforward, as the text-generated skeletons may not consistently match the scale of the reference image and may lack detailed information. To overcome these challenges, we introduce an anchor point based rescale method and design a skeleton adapter to fill in missing details and bridge the gap between text-to-motion and motion-to-video generation. We also propose a video refinement process to further enhance video quality. A large language model (LLM) is employed to decompose natural language into discrete motion sequences, enabling the generation of motion videos of any desired length. To assess the performance of Fleximo, we introduce a new benchmark called MotionBench, which includes 400 videos across 20 identities and 20 motions. We also propose a new metric, MotionScore, to evaluate the accuracy of motion following. Both qualitative and quantitative results demonstrate that our method outperforms existing text-conditioned image-to-video generation methods. All code and model weights will be made publicly available.
Abstract:Training-free diffusion models have achieved remarkable progress in generating multi-subject consistent images within open-domain scenarios. The key idea of these methods is to incorporate reference subject information within the attention layer. However, existing methods still obtain suboptimal performance when handling numerous subjects. This paper reveals the two primary issues contributing to this deficiency. Firstly, there is undesired interference among different subjects within the target image. Secondly, tokens tend to reference nearby tokens, which reduces the effectiveness of the attention mechanism when there is a significant positional difference between subjects in reference and target images. To address these challenges, we propose a training-free diffusion model with Isolation and Reposition Attention, named IR-Diffusion. Specifically, Isolation Attention ensures that multiple subjects in the target image do not reference each other, effectively eliminating the subject fusion. On the other hand, Reposition Attention involves scaling and repositioning subjects in both reference and target images to the same position within the images. This ensures that subjects in the target image can better reference those in the reference image, thereby maintaining better consistency. Extensive experiments demonstrate that the proposed methods significantly enhance multi-subject consistency, outperforming all existing methods in open-domain scenarios.
Abstract:Previous research on lightweight models has primarily focused on CNNs and Transformer-based designs. CNNs, with their local receptive fields, struggle to capture long-range dependencies, while Transformers, despite their global modeling capabilities, are limited by quadratic computational complexity in high-resolution scenarios. Recently, state-space models have gained popularity in the visual domain due to their linear computational complexity. Despite their low FLOPs, current lightweight Mamba-based models exhibit suboptimal throughput. In this work, we propose the MobileMamba framework, which balances efficiency and performance. We design a three-stage network to enhance inference speed significantly. At a fine-grained level, we introduce the Multi-Receptive Field Feature Interaction(MRFFI) module, comprising the Long-Range Wavelet Transform-Enhanced Mamba(WTE-Mamba), Efficient Multi-Kernel Depthwise Convolution(MK-DeConv), and Eliminate Redundant Identity components. This module integrates multi-receptive field information and enhances high-frequency detail extraction. Additionally, we employ training and testing strategies to further improve performance and efficiency. MobileMamba achieves up to 83.6% on Top-1, surpassing existing state-of-the-art methods which is maximum x21 faster than LocalVim on GPU. Extensive experiments on high-resolution downstream tasks demonstrate that MobileMamba surpasses current efficient models, achieving an optimal balance between speed and accuracy.
Abstract:The success of Large Language Models (LLM) has led researchers to explore Multimodal Large Language Models (MLLM) for unified visual and linguistic understanding. However, the increasing model size and computational complexity of MLLM limit their use in resource-constrained environments. Small-scale MLLM (s-MLLM) aims to retain the capabilities of the large-scale model (l-MLLM) while reducing computational demands, but resulting in a significant decline in performance. To address the aforementioned issues, we propose a novel LLaVA-KD framework to transfer knowledge from l-MLLM to s-MLLM. Specifically, we introduce Multimodal Distillation (MDist) to minimize the divergence between the visual-textual output distributions of l-MLLM and s-MLLM, and Relation Distillation (RDist) to transfer l-MLLM's ability to model correlations between visual features. Additionally, we propose a three-stage training scheme to fully exploit the potential of s-MLLM: 1) Distilled Pre-Training to align visual-textual representations, 2) Supervised Fine-Tuning to equip the model with multimodal understanding, and 3) Distilled Fine-Tuning to further transfer l-MLLM capabilities. Our approach significantly improves performance without altering the small model's architecture. Extensive experiments and ablation studies validate the effectiveness of each proposed component. Code will be available at https://github.com/caiyuxuan1120/LLaVA-KD.
Abstract:Significant advancements have been made in the field of video generation, with the open-source community contributing a wealth of research papers and tools for training high-quality models. However, despite these efforts, the available information and resources remain insufficient for achieving commercial-level performance. In this report, we open the black box and introduce $\textbf{Allegro}$, an advanced video generation model that excels in both quality and temporal consistency. We also highlight the current limitations in the field and present a comprehensive methodology for training high-performance, commercial-level video generation models, addressing key aspects such as data, model architecture, training pipeline, and evaluation. Our user study shows that Allegro surpasses existing open-source models and most commercial models, ranking just behind Hailuo and Kling. Code: https://github.com/rhymes-ai/Allegro , Model: https://huggingface.co/rhymes-ai/Allegro , Gallery: https://rhymes.ai/allegro_gallery .
Abstract:Reconstruction-based methods have significantly advanced modern unsupervised anomaly detection. However, the strong capacity of neural networks often violates the underlying assumptions by reconstructing abnormal samples well. To alleviate this issue, we present a simple yet effective reconstruction framework named Attention-Guided Pertuation Network (AGPNet), which learns to add perturbation noise with an attention mask, for accurate unsupervised anomaly detection. Specifically, it consists of two branches, \ie, a plain reconstruction branch and an auxiliary attention-based perturbation branch. The reconstruction branch is simply a plain reconstruction network that learns to reconstruct normal samples, while the auxiliary branch aims to produce attention masks to guide the noise perturbation process for normal samples from easy to hard. By doing so, we are expecting to synthesize hard yet more informative anomalies for training, which enable the reconstruction branch to learn important inherent normal patterns both comprehensively and efficiently. Extensive experiments are conducted on three popular benchmarks covering MVTec-AD, VisA, and MVTec-3D, and show that our framework obtains leading anomaly detection performance under various setups including few-shot, one-class, and multi-class setups.
Abstract:Visual anomaly detection aims to identify anomalous regions in images through unsupervised learning paradigms, with increasing application demand and value in fields such as industrial inspection and medical lesion detection. Despite significant progress in recent years, there is a lack of comprehensive benchmarks to adequately evaluate the performance of various mainstream methods across different datasets under the practical multi-class setting. The absence of standardized experimental setups can lead to potential biases in training epochs, resolution, and metric results, resulting in erroneous conclusions. This paper addresses this issue by proposing a comprehensive visual anomaly detection benchmark, \textbf{\textit{ADer}}, which is a modular framework that is highly extensible for new methods. The benchmark includes multiple datasets from industrial and medical domains, implementing fifteen state-of-the-art methods and nine comprehensive metrics. Additionally, we have open-sourced the GPU-assisted \href{https://pypi.org/project/ADEval}{ADEval} package to address the slow evaluation problem of metrics like time-consuming mAU-PRO on large-scale data, significantly reducing evaluation time by more than \textit{1000-fold}. Through extensive experimental results, we objectively reveal the strengths and weaknesses of different methods and provide insights into the challenges and future directions of multi-class visual anomaly detection. We hope that \textbf{\textit{ADer}} will become a valuable resource for researchers and practitioners in the field, promoting the development of more robust and generalizable anomaly detection systems. Full codes have been attached in Appendix and open-sourced at \url{https://github.com/zhangzjn/ader}.
Abstract:Multi-timestep simulation of brain-inspired Spiking Neural Networks (SNNs) boost memory requirements during training and increase inference energy cost. Current training methods cannot simultaneously solve both training and inference dilemmas. This work proposes a novel Temporal Reversible architecture for SNNs (T-RevSNN) to jointly address the training and inference challenges by altering the forward propagation of SNNs. We turn off the temporal dynamics of most spiking neurons and design multi-level temporal reversible interactions at temporal turn-on spiking neurons, resulting in a $O(L)$ training memory. Combined with the temporal reversible nature, we redesign the input encoding and network organization of SNNs to achieve $O(1)$ inference energy cost. Then, we finely adjust the internal units and residual connections of the basic SNN block to ensure the effectiveness of sparse temporal information interaction. T-RevSNN achieves excellent accuracy on ImageNet, while the memory efficiency, training time acceleration, and inference energy efficiency can be significantly improved by $8.6 \times$, $2.0 \times$, and $1.6 \times$, respectively. This work is expected to break the technical bottleneck of significantly increasing memory cost and training time for large-scale SNNs while maintaining high performance and low inference energy cost. Source code and models are available at: https://github.com/BICLab/T-RevSNN.
Abstract:Recently, large vision and language models have shown their success when adapting them to many downstream tasks. In this paper, we present a unified framework named CLIP-ADA for Anomaly Detection by Adapting a pre-trained CLIP model. To this end, we make two important improvements: 1) To acquire unified anomaly detection across industrial images of multiple categories, we introduce the learnable prompt and propose to associate it with abnormal patterns through self-supervised learning. 2) To fully exploit the representation power of CLIP, we introduce an anomaly region refinement strategy to refine the localization quality. During testing, the anomalies are localized by directly calculating the similarity between the representation of the learnable prompt and the image. Comprehensive experiments demonstrate the superiority of our framework, e.g., we achieve the state-of-the-art 97.5/55.6 and 89.3/33.1 on MVTec-AD and VisA for anomaly detection and localization. In addition, the proposed method also achieves encouraging performance with marginal training data, which is more challenging.