Camera clustering for scalable stream-based active distillation

• URL: http://arxiv.org/abs/2404.10411v1
• Date: Tue, 16 Apr 2024 09:28:54 GMT
• Title: Camera clustering for scalable stream-based active distillation
• Authors: Dani Manjah, Davide Cacciarelli, Christophe De Vleeschouwer, Benoit Macq,
• Abstract summary: We present a scalable framework designed to craft efficient lightweight models for video object detection. We scrutinize methodologies for the ideal selection of training images from video streams and the efficacy of model sharing across numerous cameras.
• Score: 12.730493079013456
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We present a scalable framework designed to craft efficient lightweight models for video object detection utilizing self-training and knowledge distillation techniques. We scrutinize methodologies for the ideal selection of training images from video streams and the efficacy of model sharing across numerous cameras. By advocating for a camera clustering methodology, we aim to diminish the requisite number of models for training while augmenting the distillation dataset. The findings affirm that proper camera clustering notably amplifies the accuracy of distilled models, eclipsing the methodologies that employ distinct models for each camera or a universal model trained on the aggregate camera data.

Related papers

• Latent-Reframe: Enabling Camera Control for Video Diffusion Model without Training [51.851390459940646]
  We introduce Latent-Reframe, which enables camera control in a pre-trained video diffusion model without fine-tuning. Latent-Reframe operates during the sampling stage, maintaining efficiency while preserving the original model distribution. Our approach reframes the latent code of video frames to align with the input camera trajectory through time-aware point clouds.
  arXiv  Detail & Related papers  (2024-12-08T18:59:54Z)
• Redundancy-Aware Camera Selection for Indoor Scene Neural Rendering [54.468355408388675]
  We build a similarity matrix that incorporates both the spatial diversity of the cameras and the semantic variation of the images. We apply a diversity-based sampling algorithm to optimize the camera selection. We also develop a new dataset, IndoorTraj, which includes long and complex camera movements captured by humans in virtual indoor environments.
  arXiv  Detail & Related papers  (2024-09-11T08:36:49Z)
• Reinforcing Pre-trained Models Using Counterfactual Images [54.26310919385808]
  This paper proposes a novel framework to reinforce classification models using language-guided generated counterfactual images. We identify model weaknesses by testing the model using the counterfactual image dataset. We employ the counterfactual images as an augmented dataset to fine-tune and reinforce the classification model.
  arXiv  Detail & Related papers  (2024-06-19T08:07:14Z)
• ZeroSmooth: Training-free Diffuser Adaptation for High Frame Rate Video Generation [81.90265212988844]
  We propose a training-free video method for generative video models in a plug-and-play manner. We transform a video model into a self-cascaded video diffusion model with the designed hidden state correction modules. Our training-free method is even comparable to trained models supported by huge compute resources and large-scale datasets.
  arXiv  Detail & Related papers  (2024-06-03T00:31:13Z)
• Adversarial Augmentation Training Makes Action Recognition Models More Robust to Realistic Video Distribution Shifts [13.752169303624147]
  Action recognition models often lack robustness when faced with natural distribution shifts between training and test data. We propose two novel evaluation methods to assess model resilience to such distribution disparity. We experimentally demonstrate the superior performance of the proposed adversarial augmentation approach over baselines across three state-of-the-art action recognition models.
  arXiv  Detail & Related papers  (2024-01-21T05:50:39Z)
• Improving Image Clustering through Sample Ranking and Its Application to remote--sensing images [14.531733039462058]
  We propose a novel method by first ranking samples within each cluster based on the confidence in their belonging to the current cluster. For ranking the samples, we developed a method for computing the likelihood of samples belonging to the current clusters based on whether they are situated in densely populated neighborhoods. We show that our method can be effectively applied to remote-sensing images.
  arXiv  Detail & Related papers  (2022-09-26T12:10:02Z)
• Revisiting Classifier: Transferring Vision-Language Models for Video Recognition [102.93524173258487]
  Transferring knowledge from task-agnostic pre-trained deep models for downstream tasks is an important topic in computer vision research. In this study, we focus on transferring knowledge for video classification tasks. We utilize the well-pretrained language model to generate good semantic target for efficient transferring learning.
  arXiv  Detail & Related papers  (2022-07-04T10:00:47Z)
• Self-Supervised Camera Self-Calibration from Video [34.35533943247917]
  We propose a learning algorithm to regress per-sequence calibration parameters using an efficient family of general camera models. Our procedure achieves self-calibration results with sub-pixel reprojection error, outperforming other learning-based methods.
  arXiv  Detail & Related papers  (2021-12-06T19:42:05Z)
• MEAL: Manifold Embedding-based Active Learning [0.0]
  Active learning helps learning from small amounts of data by suggesting the most promising samples for labeling. We propose a new pool-based method for active learning, which proposes promising image regions, in each acquisition step. We find that our active learning method achieves better performance on CamVid compared to other methods, while on Cityscapes, the performance lift was negligible.
  arXiv  Detail & Related papers  (2021-06-22T15:22:56Z)
• ARVo: Learning All-Range Volumetric Correspondence for Video Deblurring [92.40655035360729]
  Video deblurring models exploit consecutive frames to remove blurs from camera shakes and object motions. We propose a novel implicit method to learn spatial correspondence among blurry frames in the feature space. Our proposed method is evaluated on the widely-adopted DVD dataset, along with a newly collected High-Frame-Rate (1000 fps) dataset for Video Deblurring.
  arXiv  Detail & Related papers  (2021-03-07T04:33:13Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.