Recently, MBConv blocks, initially designed for efficiency in resource-limited settings and later adapted for cutting-edge image classification performances, have demonstrated significant potential in image classification tasks. Despite their success, their application in semantic segmentation has remained relatively unexplored. This paper introduces a novel adaptation of MBConv blocks specifically tailored for semantic segmentation. Our modification stems from the insight that semantic segmentation requires the extraction of more detailed spatial information than image classification. We argue that to effectively perform multi-scale semantic segmentation, each branch of a U-Net architecture, regardless of its resolution, should possess equivalent segmentation capabilities. By implementing these changes, our approach achieves impressive mean Intersection over Union (IoU) scores of 84.5% and 84.0% on the Cityscapes test and validation datasets, respectively, demonstrating the efficacy of our proposed modifications in enhancing semantic segmentation performance.
相關內容
The advent of 3D Gaussian Splatting (3DGS) has revolutionized 3D editing, offering efficient, high-fidelity rendering and enabling precise local manipulations. Currently, diffusion-based 2D editing models are harnessed to modify multi-view rendered images, which then guide the editing of 3DGS models. However, this approach faces a critical issue of multi-view inconsistency, where the guidance images exhibit significant discrepancies across views, leading to mode collapse and visual artifacts of 3DGS. To this end, we introduce View-consistent Editing (VcEdit), a novel framework that seamlessly incorporates 3DGS into image editing processes, ensuring multi-view consistency in edited guidance images and effectively mitigating mode collapse issues. VcEdit employs two innovative consistency modules: the Cross-attention Consistency Module and the Editing Consistency Module, both designed to reduce inconsistencies in edited images. By incorporating these consistency modules into an iterative pattern, VcEdit proficiently resolves the issue of multi-view inconsistency, facilitating high-quality 3DGS editing across a diverse range of scenes.
Autonomous target tracking with quadrotors has wide applications in many scenarios, such as cinematographic follow-up shooting or suspect chasing. Target motion prediction is necessary when designing the tracking planner. However, the widely used constant velocity or constant rotation assumption can not fully capture the dynamics of the target. The tracker may fail when the target happens to move aggressively, such as sudden turn or deceleration. In this paper, we propose an intention-aware planner by additionally considering the intention of the target to enhance safety and robustness in aerial tracking applications. Firstly, a designated intention prediction method is proposed, which combines a user-defined potential assessment function and a state observation function. A reachable region is generated to specifically evaluate the turning intentions. Then we design an intention-driven hybrid A* method to predict the future possible positions for the target. Finally, an intention-aware optimization approach is designed to generate a spatial-temporal optimal trajectory, allowing the tracker to perceive unexpected situations from the target. Benchmark comparisons and real-world experiments are conducted to validate the performance of our method.
With diverse presentation forgery methods emerging continually, detecting the authenticity of images has drawn growing attention. Although existing methods have achieved impressive accuracy in training dataset detection, they still perform poorly in the unseen domain and suffer from forgery of irrelevant information such as background and identity, affecting generalizability. To solve this problem, we proposed a novel framework Selective Domain-Invariant Feature (SDIF), which reduces the sensitivity to face forgery by fusing content features and styles. Specifically, we first use a Farthest-Point Sampling (FPS) training strategy to construct a task-relevant style sample representation space for fusing with content features. Then, we propose a dynamic feature extraction module to generate features with diverse styles to improve the performance and effectiveness of the feature extractor. Finally, a domain separation strategy is used to retain domain-related features to help distinguish between real and fake faces. Both qualitative and quantitative results in existing benchmarks and proposals demonstrate the effectiveness of our approach.
Despite significant advancements in image customization with diffusion models, current methods still have several limitations: 1) unintended changes in non-target areas when regenerating the entire image; 2) guidance solely by a reference image or text descriptions; and 3) time-consuming fine-tuning, which limits their practical application. In response, we introduce a tuning-free framework for simultaneous text-image-guided image customization, enabling precise editing of specific image regions within seconds. Our approach preserves the semantic features of the reference image subject while allowing modification of detailed attributes based on text descriptions. To achieve this, we propose an innovative attention blending strategy that blends self-attention features in the UNet decoder during the denoising process. To our knowledge, this is the first tuning-free method that concurrently utilizes text and image guidance for image customization in specific regions. Our approach outperforms previous methods in both human and quantitative evaluations, providing an efficient solution for various practical applications, such as image synthesis, design, and creative photography.
Identifying highlight moments of raw video materials is crucial for improving the efficiency of editing videos that are pervasive on internet platforms. However, the extensive work of manually labeling footage has created obstacles to applying supervised methods to videos of unseen categories. The absence of an audio modality that contains valuable cues for highlight detection in many videos also makes it difficult to use multimodal strategies. In this paper, we propose a novel model with cross-modal perception for unsupervised highlight detection. The proposed model learns representations with visual-audio level semantics from image-audio pair data via a self-reconstruction task. To achieve unsupervised highlight detection, we investigate the latent representations of the network and propose the representation activation sequence learning (RASL) module with k-point contrastive learning to learn significant representation activations. To connect the visual modality with the audio modality, we use the symmetric contrastive learning (SCL) module to learn the paired visual and audio representations. Furthermore, an auxiliary task of masked feature vector sequence (FVS) reconstruction is simultaneously conducted during pretraining for representation enhancement. During inference, the cross-modal pretrained model can generate representations with paired visual-audio semantics given only the visual modality. The RASL module is used to output the highlight scores. The experimental results show that the proposed framework achieves superior performance compared to other state-of-the-art approaches.
We present JOG, a framework that facilitates developing Java JIT peephole optimizations alongside JIT tests. JOG enables developers to write a pattern, in Java itself, that specifies desired code transformations by writing code before and after the optimization, as well as any necessary preconditions. Such patterns can be written in the same way that tests of the optimization are already written in OpenJDK. JOG translates each pattern into C/C++ code that can be integrated as a JIT optimization pass. JOG also generates Java tests for optimizations from patterns. Furthermore, JOG can automatically detect possible shadow relation between a pair of optimizations where the effect of the shadowed optimization is overridden by another. Our evaluation shows that JOG makes it easier to write readable JIT optimizations alongside tests without decreasing the effectiveness of JIT optimizations. We wrote 162 patterns, including 68 existing optimizations in OpenJDK, 92 new optimizations adapted from LLVM, and two new optimizations that we proposed. We opened eight pull requests (PRs) for OpenJDK, including six for new optimizations, one on removing shadowed optimizations, and one for newly generated JIT tests; seven PRs have already been integrated into the master branch of OpenJDK.
The disaggregated time-series data for Consumer Price Index often exhibits frequent instances of exact zero price changes, stemming from measurement errors inherent in the data collection process. However, the currently prominent stochastic volatility model of trend inflation is designed for aggregate measures of price inflation, where exact zero price changes rarely occur. We propose a zero-inflated stochastic volatility model applicable to such nonstationary real-valued multivariate time-series data with exact zeros, by a Bayesian dynamic generalized linear model that jointly specifies the dynamic zero-generating process. We also provide an efficient custom Gibbs sampler that leverages the P\'olya-Gamma augmentation. Applying the model to disaggregated Japanese Consumer Price Index data, we find that the zero-inflated model provides more sensible and informative estimates of time-varying trend and volatility. Through an out-of-sample forecasting exercise, we find that the zero-inflated model provides improved point forecasts when zero-inflation is prominent, and better coverage of interval forecasts of the non-zero data by the non-zero distributional component.
Recent advancements in subject-driven image generation have made significant strides. However, current methods still fall short in diverse application scenarios, as they require test-time tuning and cannot accept interleaved multi-image and text input. These limitations keep them far from the ultimate goal of "image as a foreign language in image generation." This paper presents Kosmos-G, a model that leverages the advanced multimodal perception capabilities of Multimodal Large Language Models (MLLMs) to tackle the aforementioned challenge. Our approach aligns the output space of MLLM with CLIP using the textual modality as an anchor and performs compositional instruction tuning on curated data. Kosmos-G demonstrates an impressive capability of zero-shot subject-driven generation with interleaved multi-image and text input. Notably, the score distillation instruction tuning requires no modifications to the image decoder. This allows for a seamless substitution of CLIP and effortless integration with a myriad of U-Net techniques ranging from fine-grained controls to personalized image decoder variants. We posit Kosmos-G as an initial attempt towards the goal of "image as a foreign language in image generation." The code can be found at //aka.ms/Kosmos-G
Video captioning is a challenging task that requires a deep understanding of visual scenes. State-of-the-art methods generate captions using either scene-level or object-level information but without explicitly modeling object interactions. Thus, they often fail to make visually grounded predictions, and are sensitive to spurious correlations. In this paper, we propose a novel spatio-temporal graph model for video captioning that exploits object interactions in space and time. Our model builds interpretable links and is able to provide explicit visual grounding. To avoid unstable performance caused by the variable number of objects, we further propose an object-aware knowledge distillation mechanism, in which local object information is used to regularize global scene features. We demonstrate the efficacy of our approach through extensive experiments on two benchmarks, showing our approach yields competitive performance with interpretable predictions.
Recent advancements in deep neural networks for graph-structured data have led to state-of-the-art performance on recommender system benchmarks. However, making these methods practical and scalable to web-scale recommendation tasks with billions of items and hundreds of millions of users remains a challenge. Here we describe a large-scale deep recommendation engine that we developed and deployed at Pinterest. We develop a data-efficient Graph Convolutional Network (GCN) algorithm PinSage, which combines efficient random walks and graph convolutions to generate embeddings of nodes (i.e., items) that incorporate both graph structure as well as node feature information. Compared to prior GCN approaches, we develop a novel method based on highly efficient random walks to structure the convolutions and design a novel training strategy that relies on harder-and-harder training examples to improve robustness and convergence of the model. We also develop an efficient MapReduce model inference algorithm to generate embeddings using a trained model. We deploy PinSage at Pinterest and train it on 7.5 billion examples on a graph with 3 billion nodes representing pins and boards, and 18 billion edges. According to offline metrics, user studies and A/B tests, PinSage generates higher-quality recommendations than comparable deep learning and graph-based alternatives. To our knowledge, this is the largest application of deep graph embeddings to date and paves the way for a new generation of web-scale recommender systems based on graph convolutional architectures.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191