Few-shot image classification has emerged as a key challenge in the field of computer vision, highlighting the capability to rapidly adapt to new tasks with minimal labeled data. Existing methods predominantly rely on image-level features or local descriptors, often overlooking the holistic context surrounding these descriptors. In this work, we introduce a novel approach termed "Local Descriptor with Contextual Augmentation (LDCA)". Specifically, this method bridges the gap between local and global understanding uniquely by leveraging an adaptive global contextual enhancement module. This module incorporates a visual transformer, endowing local descriptors with contextual awareness capabilities, ranging from broad global perspectives to intricate surrounding nuances. By doing so, LDCA transcends traditional descriptor-based approaches, ensuring each local feature is interpreted within its larger visual narrative. Extensive experiments underscore the efficacy of our method, showing a maximal absolute improvement of 20\% over the next-best on fine-grained classification datasets, thus demonstrating significant advancements in few-shot classification tasks.
相關內容
Cylinder pressure-based control is a key enabler for advanced pre-mixed combustion concepts. Besides guaranteeing robust and safe operation, it allows for cylinder pressure and heat release shaping. This requires fast control-oriented combustion models. Over the years, mean-value models have been proposed that can predict combustion measures (e.g., Gross Indicated Mean Effective Pressure, or the crank angle where 50% of the total heat is released) or models that predict the full in-cylinder pressure. However, these models are not able to capture cyclic variations. This is important in the control design for combustion concepts, like Reactivity Controlled Compression Ignition, that can suffer from large cyclic variations. In this study, the in-cylinder pressure and cyclic variation are modelled using a data-based approach. The model combines Principle Component Decomposition and Gaussian Process Regression. A detailed study is performed on the effects of the different hyperparameters and kernel choices. The approach is applicable to any combustion concept, but most valuable for advance combustion concepts with large cyclic variation. The potential of the proposed approach is demonstrated for an Reactivity Controlled Compression Ignition engine running on Diesel and E85. The prediction quality of the evaluated combustion measures has an overall accuracy of 13.5% and 65.5% in mean behaviour and standard deviation, respectively. The peak-pressure rise-rate is traditionally hard to predict, in the proposed model it has an accuracy of 22.7% and 96.4% in mean behaviour and standard deviation, respectively. This Principle Component Decomposition-based approach is an important step towards in-cylinder pressure shaping. The use of Gaussian Process Regression provides important information on cyclic variation and provides next-cycle controls information on safety and performance criteria.
Large language models (LLMs) face a daunting challenge due to the excessive computational and memory requirements of the commonly used Transformer architecture. While state space model (SSM) is a new type of foundational network architecture offering lower computational complexity, their performance has yet to fully rival that of Transformers. This paper introduces DenseSSM, a novel approach to enhance the flow of hidden information between layers in SSMs. By selectively integrating shallowlayer hidden states into deeper layers, DenseSSM retains fine-grained information crucial for the final output. Dense connections enhanced DenseSSM still maintains the training parallelizability and inference efficiency. The proposed method can be widely applicable to various SSM types like RetNet and Mamba. With similar model size, DenseSSM achieves significant improvements, exemplified by DenseRetNet outperforming the original RetNet with up to 5% accuracy improvement on public benchmarks. code is avalaible at //github.com/WailordHe/DenseSSM
Accurate data association is crucial in reducing confusion, such as ID switches and assignment errors, in multi-object tracking (MOT). However, existing advanced methods often overlook the diversity among trajectories and the ambiguity and conflicts present in motion and appearance cues, leading to confusion among detections, trajectories, and associations when performing simple global data association. To address this issue, we propose a simple, versatile, and highly interpretable data association approach called Decomposed Data Association (DDA). DDA decomposes the traditional association problem into multiple sub-problems using a series of non-learning-based modules and selectively addresses the confusion in each sub-problem by incorporating targeted exploitation of new cues. Additionally, we introduce Occlusion-aware Non-Maximum Suppression (ONMS) to retain more occluded detections, thereby increasing opportunities for association with trajectories and indirectly reducing the confusion caused by missed detections. Finally, based on DDA and ONMS, we design a powerful multi-object tracker named DeconfuseTrack, specifically focused on resolving confusion in MOT. Extensive experiments conducted on the MOT17 and MOT20 datasets demonstrate that our proposed DDA and ONMS significantly enhance the performance of several popular trackers. Moreover, DeconfuseTrack achieves state-of-the-art performance on the MOT17 and MOT20 test sets, significantly outperforms the baseline tracker ByteTrack in metrics such as HOTA, IDF1, AssA. This validates that our tracking design effectively reduces confusion caused by simple global association.
The surge in real-time data collection across various industries has underscored the need for advanced anomaly detection in both univariate and multivariate time series data. This paper introduces TransNAS-TSAD, a framework that synergizes the transformer architecture with neural architecture search (NAS), enhanced through NSGA-II algorithm optimization. This approach effectively tackles the complexities of time series data, balancing computational efficiency with detection accuracy. Our evaluation reveals that TransNAS-TSAD surpasses conventional anomaly detection models due to its tailored architectural adaptability and the efficient exploration of complex search spaces, leading to marked improvements in diverse data scenarios. We also introduce the Efficiency-Accuracy-Complexity Score (EACS) as a new metric for assessing model performance, emphasizing the balance between accuracy and computational resources. TransNAS-TSAD sets a new benchmark in time series anomaly detection, offering a versatile, efficient solution for complex real-world applications. This research highlights the TransNAS-TSAD potential across a wide range of industry applications and paves the way for future developments in the field.
Web-scale training on paired text-image data is becoming increasingly central to multimodal learning, but is challenged by the highly noisy nature of datasets in the wild. Standard data filtering approaches succeed in removing mismatched text-image pairs, but permit semantically related but highly abstract or subjective text. These approaches lack the fine-grained ability to isolate the most concrete samples that provide the strongest signal for learning in a noisy dataset. In this work, we propose a new metric, image caption concreteness, that evaluates caption text without an image reference to measure its concreteness and relevancy for use in multimodal learning. Our approach leverages strong foundation models for measuring visual-semantic information loss in multimodal representations. We demonstrate that this strongly correlates with human evaluation of concreteness in both single-word and sentence-level texts. Moreover, we show that curation using ICC complements existing approaches: It succeeds in selecting the highest quality samples from multimodal web-scale datasets to allow for efficient training in resource-constrained settings.
Audio-visual saliency prediction can draw support from diverse modality complements, but further performance enhancement is still challenged by customized architectures as well as task-specific loss functions. In recent studies, denoising diffusion models have shown more promising in unifying task frameworks owing to their inherent ability of generalization. Following this motivation, a novel Diffusion architecture for generalized audio-visual Saliency prediction (DiffSal) is proposed in this work, which formulates the prediction problem as a conditional generative task of the saliency map by utilizing input audio and video as the conditions. Based on the spatio-temporal audio-visual features, an extra network Saliency-UNet is designed to perform multi-modal attention modulation for progressive refinement of the ground-truth saliency map from the noisy map. Extensive experiments demonstrate that the proposed DiffSal can achieve excellent performance across six challenging audio-visual benchmarks, with an average relative improvement of 6.3\% over the previous state-of-the-art results by six metrics.
A standard practice in developing image recognition models is to train a model on a specific image resolution and then deploy it. However, in real-world inference, models often encounter images different from the training sets in resolution and/or subject to natural variations such as weather changes, noise types and compression artifacts. While traditional solutions involve training multiple models for different resolutions or input variations, these methods are computationally expensive and thus do not scale in practice. To this end, we propose a novel neural network model, parallel-structured and all-component Fourier neural operator (PAC-FNO), that addresses the problem. Unlike conventional feed-forward neural networks, PAC-FNO operates in the frequency domain, allowing it to handle images of varying resolutions within a single model. We also propose a two-stage algorithm for training PAC-FNO with a minimal modification to the original, downstream model. Moreover, the proposed PAC-FNO is ready to work with existing image recognition models. Extensively evaluating methods with seven image recognition benchmarks, we show that the proposed PAC-FNO improves the performance of existing baseline models on images with various resolutions by up to 77.1% and various types of natural variations in the images at inference.
The attention mechanism has gained significant recognition in the field of computer vision due to its ability to effectively enhance the performance of deep neural networks. However, existing methods often struggle to effectively utilize spatial information or, if they do, they come at the cost of reducing channel dimensions or increasing the complexity of neural networks. In order to address these limitations, this paper introduces an Efficient Local Attention (ELA) method that achieves substantial performance improvements with a simple structure. By analyzing the limitations of the Coordinate Attention method, we identify the lack of generalization ability in Batch Normalization, the adverse effects of dimension reduction on channel attention, and the complexity of attention generation process. To overcome these challenges, we propose the incorporation of 1D convolution and Group Normalization feature enhancement techniques. This approach enables accurate localization of regions of interest by efficiently encoding two 1D positional feature maps without the need for dimension reduction, while allowing for a lightweight implementation. We carefully design three hyperparameters in ELA, resulting in four different versions: ELA-T, ELA-B, ELA-S, and ELA-L, to cater to the specific requirements of different visual tasks such as image classification, object detection and sementic segmentation. ELA can be seamlessly integrated into deep CNN networks such as ResNet, MobileNet, and DeepLab. Extensive evaluations on the ImageNet, MSCOCO, and Pascal VOC datasets demonstrate the superiority of the proposed ELA module over current state-of-the-art methods in all three aforementioned visual tasks.
Recent advancements in diffusion models have significantly enhanced the data synthesis with 2D control. Yet, precise 3D control in street view generation, crucial for 3D perception tasks, remains elusive. Specifically, utilizing Bird's-Eye View (BEV) as the primary condition often leads to challenges in geometry control (e.g., height), affecting the representation of object shapes, occlusion patterns, and road surface elevations, all of which are essential to perception data synthesis, especially for 3D object detection tasks. In this paper, we introduce MagicDrive, a novel street view generation framework, offering diverse 3D geometry controls including camera poses, road maps, and 3D bounding boxes, together with textual descriptions, achieved through tailored encoding strategies. Besides, our design incorporates a cross-view attention module, ensuring consistency across multiple camera views. With MagicDrive, we achieve high-fidelity street-view image & video synthesis that captures nuanced 3D geometry and various scene descriptions, enhancing tasks like BEV segmentation and 3D object detection.
Automatic image captioning has recently approached human-level performance due to the latest advances in computer vision and natural language understanding. However, most of the current models can only generate plain factual descriptions about the content of a given image. However, for human beings, image caption writing is quite flexible and diverse, where additional language dimensions, such as emotion, humor and language styles, are often incorporated to produce diverse, emotional, or appealing captions. In particular, we are interested in generating sentiment-conveying image descriptions, which has received little attention. The main challenge is how to effectively inject sentiments into the generated captions without altering the semantic matching between the visual content and the generated descriptions. In this work, we propose two different models, which employ different schemes for injecting sentiments into image captions. Compared with the few existing approaches, the proposed models are much simpler and yet more effective. The experimental results show that our model outperform the state-of-the-art models in generating sentimental (i.e., sentiment-bearing) image captions. In addition, we can also easily manipulate the model by assigning different sentiments to the testing image to generate captions with the corresponding sentiments.
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