Federated Learning (FL) enables multiple machines to collaboratively train a machine learning model without sharing of private training data. Yet, especially for heterogeneous models, a key bottleneck remains the tran...
详细信息
ISBN:
(纸本)9798350365474
Federated Learning (FL) enables multiple machines to collaboratively train a machine learning model without sharing of private training data. Yet, especially for heterogeneous models, a key bottleneck remains the transfer of knowledge gained from each client model with the server. One popular method, FedDF, uses distillation to tackle this task with the use of a common, shared dataset on which predictions are exchanged. However, in many contexts such a dataset might be difficult to acquire due to privacy and the clients might not allow for storage of a large shared dataset. To this end, in this paper, we introduce a new method that improves this knowledge distillation method to only rely on a single shared image between clients and server. In particular, we propose a novel adaptive dataset pruning algorithm that selects the most informative crops generated from only a single image. With this, we show that federated learning with distillation under a limited shared dataset budget works better by using a single image compared to multiple individual ones. Finally, we extend our approach to allow for training heterogeneous client architectures by incorporating a non-uniform distillation schedule and client-model mirroring on the server side.
Anomaly Detection is a relevant problem in numerous real-world applications, especially when dealing with images. However, little attention has been paid to the issue of changes over time in the input data distributio...
详细信息
ISBN:
(纸本)9798350365474
Anomaly Detection is a relevant problem in numerous real-world applications, especially when dealing with images. However, little attention has been paid to the issue of changes over time in the input data distribution, which may cause a significant decrease in performance. In this study, we investigate the problem of Pixel-Level Anomaly Detection in the Continual Learning setting, where new data arrives over time and the goal is to perform well on new and old data. We implement several state-of-the-art techniques to solve the Anomaly Detection problem in the classic setting and adapt them to work in the Continual Learning setting. To validate the approaches, we use a real-world dataset of images with pixel-based anomalies to provide a reliable benchmark and serve as a foundation for further advancements in the field. We provide a comprehensive analysis, discussing which Anomaly Detection methods and which families of approaches seem more suitable for the Continual Learning setting.
Capturing and preserving motion semantics is essential to motion retargeting between animation characters. However, most of the previous works neglect the semantic information or rely on human-designed joint-level rep...
详细信息
ISBN:
(纸本)9798350353013;9798350353006
Capturing and preserving motion semantics is essential to motion retargeting between animation characters. However, most of the previous works neglect the semantic information or rely on human-designed joint-level representations. Here, we present a novel Semantics-aware Motion reTargeting (SMT) method with the advantage of vision-language models to extract and maintain meaningful motion semantics. We utilize a differentiable module to render 3D motions. Then the high-level motion semantics are incorporated into the motion retargeting process by feeding the vision-language model with the rendered images and aligning the extracted semantic embeddings. To ensure the preservation of fine-grained motion details and high-level semantics, we adopt a two-stage pipeline consisting of skeleton-aware pre-training and fine-tuning with semantics and geometry constraints. Experimental results show the effectiveness of the proposed method in producing high-quality motion retargeting results while accurately preserving motion semantics. Project page can be found at https://***/view/smtnet.
The increasing demand for computational photography and imaging on mobile platforms has led to the widespread development and integration of advanced image sensors with novel algorithms in camera systems. However, the...
详细信息
ISBN:
(纸本)9798350365474
The increasing demand for computational photography and imaging on mobile platforms has led to the widespread development and integration of advanced image sensors with novel algorithms in camera systems. However, the scarcity of high-quality data for research and the rare opportunity for in-depth exchange of views from industry and academia constrain the development of mobile intelligent photography and imaging (MIPI). Building on the achievements of the previous MIPI Workshops held at ECCV 2022 and CVPR 2023, we introduce our third MIPI challenge including three tracks focusing on novel image sensors and imaging algorithms. In this paper, we summarize and review the Nighttime Flare Removal track on MIPI 2024. In total, 170 participants were successfully registered, and 14 teams submitted results in the final testing phase. The developed solutions in this challenge achieved state-of-the-art performance on Nighttime Flare Removal. More details of this challenge and the link to the dataset can be found at https://***/MIPI2024.
Monocular depth estimation is a fundamental computervision task. Recovering 3D depth from a single image is geometrically ill-posed and requires scene understanding, so it is not surprising that the rise of deep lear...
详细信息
ISBN:
(纸本)9798350353006
Monocular depth estimation is a fundamental computervision task. Recovering 3D depth from a single image is geometrically ill-posed and requires scene understanding, so it is not surprising that the rise of deep learning has led to a breakthrough. The impressive progress of monocular depth estimators has mirrored the growth in model capacity, from relatively modest CNNs to large Transformer architectures. Still, monocular depth estimators tend to struggle when presented with images with unfamiliar content and layout, since their knowledge of the visual world is restricted by the data seen during training, and challenged by zero-shot generalization to new domains. This motivates us to explore whether the extensive priors captured in recent generative diffusion models can enable better, more generalizable depth estimation. We introduce Marigold, a method for affine-invariant monocular depth estimation that is derived from Stable Diffusion and retains its rich prior knowledge. The estimator can be fine-tuned in a couple of days on a single GPU using only synthetic training data. It delivers state-of-the-art performance across a wide range of datasets, including over 20% performance gains in specific cases. Project page: https://***.
Utilizing multi-view inputs to synthesize novel-view images, Neural Radiance Fields (NeRF) have emerged as a popular research topic in 3D vision. In this work, we introduce a Generalizable Semantic Neural Radiance Fie...
详细信息
ISBN:
(纸本)9798350353006
Utilizing multi-view inputs to synthesize novel-view images, Neural Radiance Fields (NeRF) have emerged as a popular research topic in 3D vision. In this work, we introduce a Generalizable Semantic Neural Radiance Fields ( GSNeRF), which uniquely takes image semantics into the synthesis process so that both novel view image and the associated semantic maps can be produced for unseen scenes. Our GSNeRF is composed of two stages: Semantic GeoReasoning and Depth-Guided Visual rendering. The former is able to observe multi- view image inputs to extract semantic and geometry features from a scene. Guided by the resulting image geometry information, the latter performs both image and semantic rendering with improved performances. Our experiments not only confirm that GSNeRF performs favorably against prior works on both novel-view image and semantic segmentation synthesis but the effectiveness of our sampling strategy for visual rendering is further verified.
Understanding human social behaviour is crucial in computervision and robotics. Micro-level observations like individual actions fall short, necessitating a comprehensive approach that considers individual behaviour,...
详细信息
ISBN:
(纸本)9798350353006
Understanding human social behaviour is crucial in computervision and robotics. Micro-level observations like individual actions fall short, necessitating a comprehensive approach that considers individual behaviour, intra-group dynamics, and social group levels for a thorough understanding. To address dataset limitations, this paper introduces JRDB-Social, an extension of JRDB [2]. Designed to fill gaps in human understanding across diverse indoor and outdoor social contexts, JRDB-Social provides annotations at three levels: individual attributes, intra-group interactions, and social group context. This dataset aims to enhance our grasp of human social dynamics for robotic applications. Utilizing the recent cutting-edge multi-modal large language models, we evaluated our benchmark to explore their capacity to decipher social human behaviour.
This study investigates the integration of vision language models (VLM) to enhance the classification of situations within rugby match broadcasts. The importance of accurately identifying situations in sports videos i...
详细信息
ISBN:
(纸本)9798350365474
This study investigates the integration of vision language models (VLM) to enhance the classification of situations within rugby match broadcasts. The importance of accurately identifying situations in sports videos is emphasized for understanding game dynamics and facilitating downstream tasks like performance evaluation and injury prevention. Utilizing a dataset comprising 18, 000 labeled images extracted at 0.2-second intervals from 100 minutes of rugby match broadcasts, scene classification tasks including contact plays (scrums, mauls, rucks, tackles, lineouts), rucks, tackles, lineouts, and multiclass classification were performed. The study aims to validate the utility of VLM outputs in improving classification performance compared to using solely image data. Experimental results demonstrate substantial performance improvements across all tasks with the incorporation of VLM outputs. Our analysis of prompts suggests that, when provided with appropriate contextual information through natural language, VLMs can effectively capture the context of a given image. The findings of our study indicate that leveraging VLMs in the domain of sports analysis holds promise for developing image processing models capable of incorpolating the tacit knowledge encoded within language models, as well as information conveyed through natural language descriptions.
In this paper, we explore the cross-modal adaptation of pre-trained vision Transformers (ViTs) for the audio-visual domain by incorporating a limited set of trainable parameters. To this end, we propose a Spatial-Temp...
详细信息
ISBN:
(纸本)9798350365474
In this paper, we explore the cross-modal adaptation of pre-trained vision Transformers (ViTs) for the audio-visual domain by incorporating a limited set of trainable parameters. To this end, we propose a Spatial-Temporal-Global Cross-Modal Adaptation (STG-CMA) to gradually equip the frozen ViTs with the capability for learning audio-visual representation, consisting of the modality-specific temporal adaptation for temporal reasoning of each modality, the cross-modal spatial adaptation for refining the spatial information with the cue from counterpart modality, and the cross-modal global adaptation for global interaction between audio and visual modalities. Our STG-CMA presents a meaningful finding that only leveraging the shared pre-trained image model with inserted lightweight adapters is enough for spatial-temporal modeling and feature interaction of audio-visual modality. Extensive experiments indicate that our STG-CMA achieves state-of-the-art performance on various audio-visual understanding tasks including AVE, AVS, and AVQA while containing significantly reduced tunable parameters. The code is available at https://***/kaiw7/STG-CMA.
Although soft prompt tuning is effective in efficiently adapting vision-Language (V&L) models for downstream tasks, it shows limitations in dealing with distribution shifts. We address this issue with Attribute-Gu...
详细信息
ISBN:
(纸本)9798350353006
Although soft prompt tuning is effective in efficiently adapting vision-Language (V&L) models for downstream tasks, it shows limitations in dealing with distribution shifts. We address this issue with Attribute-Guided Prompt Tuning (ArGue), making three key contributions. 1) In contrast to the conventional approach of directly appending soft prompts preceding class names, we align the model with primitive visual attributes generated by Large Language Models (LLMs). We posit that a model's ability to express high confidence in these attributes signifies its capacity to discern the correct class rationales. 2) We introduce attribute sampling to eliminate disadvantageous attributes, thus only semantically meaningful attributes are preserved. 3) We propose negative prompting, explicitly enumerating class-agnostic attributes to activate spurious correlations and encourage the model to generate highly orthogonal probability distributions in relation to these negative features. In experiments, our method significantly outperforms current state-of-the-art prompt tuning methods on both novel class prediction and out-of-distribution generalization tasks. The code is available https://***/Liam-Tian/ArGue.
暂无评论