AdaCrowd: Unlabeled Scene Adaptation for Crowd Counting
- URL: http://arxiv.org/abs/2010.12141v2
- Date: Tue, 23 Feb 2021 06:05:48 GMT
- Title: AdaCrowd: Unlabeled Scene Adaptation for Crowd Counting
- Authors: Mahesh Kumar Krishna Reddy, Mrigank Rochan, Yiwei Lu, Yang Wang
- Abstract summary: We propose a new problem called unlabeled scene-adaptive crowd counting.
Given a new target scene, we would like to have a crowd counting model specifically adapted to this particular scene.
In this paper, we propose to use one or more unlabeled images from the target scene to perform the adaptation.
- Score: 14.916045549353987
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: We address the problem of image-based crowd counting. In particular, we
propose a new problem called unlabeled scene-adaptive crowd counting. Given a
new target scene, we would like to have a crowd counting model specifically
adapted to this particular scene based on the target data that capture some
information about the new scene. In this paper, we propose to use one or more
unlabeled images from the target scene to perform the adaptation. In comparison
with the existing problem setups (e.g. fully supervised), our proposed problem
setup is closer to the real-world applications of crowd counting systems. We
introduce a novel AdaCrowd framework to solve this problem. Our framework
consists of a crowd counting network and a guiding network. The guiding network
predicts some parameters in the crowd counting network based on the unlabeled
images from a particular scene. This allows our model to adapt to different
target scenes. The experimental results on several challenging benchmark
datasets demonstrate the effectiveness of our proposed approach compared with
other alternative methods. Code is available at
https://github.com/maheshkkumar/adacrowd.
Related papers
- GLACE: Global Local Accelerated Coordinate Encoding [66.87005863868181]
Scene coordinate regression methods are effective in small-scale scenes but face significant challenges in large-scale scenes.
We propose GLACE, which integrates pre-trained global and local encodings and enables SCR to scale to large scenes with only a single small-sized network.
Our method achieves state-of-the-art results on large-scale scenes with a low-map-size model.
arXiv Detail & Related papers (2024-06-06T17:59:50Z) - Robust Zero-Shot Crowd Counting and Localization With Adaptive Resolution SAM [55.93697196726016]
We propose a simple yet effective crowd counting method by utilizing the Segment-Everything-Everywhere Model (SEEM)
We show that SEEM's performance in dense crowd scenes is limited, primarily due to the omission of many persons in high-density areas.
Our proposed method achieves the best unsupervised performance in crowd counting, while also being comparable to some supervised methods.
arXiv Detail & Related papers (2024-02-27T13:55:17Z) - Break-A-Scene: Extracting Multiple Concepts from a Single Image [80.47666266017207]
We introduce the task of textual scene decomposition.
We propose augmenting the input image with masks that indicate the presence of target concepts.
We then present a novel two-phase customization process.
arXiv Detail & Related papers (2023-05-25T17:59:04Z) - Knowing What to Label for Few Shot Microscopy Image Cell Segmentation [15.510258960276083]
In microscopy image cell segmentation, it is common to train a deep neural network on source data, containing different types of microscopy images.
We argue that the random selection of unlabelled training target images to be annotated may not enable an effective fine-tuning process.
Our approach involves a new scoring function to find informative unlabelled target images.
arXiv Detail & Related papers (2022-11-18T14:03:49Z) - Cross-View Cross-Scene Multi-View Crowd Counting [56.83882084112913]
Multi-view crowd counting has been previously proposed to utilize multi-cameras to extend the field-of-view of a single camera.
We propose a cross-view cross-scene (CVCS) multi-view crowd counting paradigm, where the training and testing occur on different scenes with arbitrary camera layouts.
arXiv Detail & Related papers (2022-05-03T15:03:44Z) - Scene-Adaptive Attention Network for Crowd Counting [31.29858034122248]
This paper proposes a scene-adaptive attention network, termed SAANet.
We design a deformable attention in-built Transformer backbone, which learns adaptive feature representations with deformable sampling locations and dynamic attention weights.
We conduct extensive experiments on four challenging crowd counting benchmarks, demonstrating that our method achieves state-of-the-art performance.
arXiv Detail & Related papers (2021-12-31T15:03:17Z) - A Few Guidelines for Incremental Few-Shot Segmentation [57.34237650765928]
Given a pretrained segmentation model and few images containing novel classes, our goal is to learn to segment novel classes while retaining the ability to segment previously seen ones.
We show how the main problems of end-to-end training in this scenario are.
i) the drift of the batch-normalization statistics toward novel classes that we can fix with batch renormalization and.
ii) the forgetting of old classes, that we can fix with regularization strategies.
arXiv Detail & Related papers (2020-11-30T20:45:56Z) - Completely Self-Supervised Crowd Counting via Distribution Matching [92.09218454377395]
We propose a complete self-supervision approach to training models for dense crowd counting.
The only input required to train, apart from a large set of unlabeled crowd images, is the approximate upper limit of the crowd count.
Our method dwells on the idea that natural crowds follow a power law distribution, which could be leveraged to yield error signals for backpropagation.
arXiv Detail & Related papers (2020-09-14T13:20:12Z) - SceneAdapt: Scene-based domain adaptation for semantic segmentation
using adversarial learning [24.37746089471516]
SceneAdapt is a method for scene adaptation of semantic segmentation algorithms based on adversarial learning.
To encourage research on this topic, we made our code available at our web page: https://iplab.dmi.unict.it/ParkSmartSceneAdaptation/.
arXiv Detail & Related papers (2020-06-18T09:43:31Z) - Few-Shot Scene Adaptive Crowd Counting Using Meta-Learning [13.149654626505741]
We consider the problem of few-shot scene adaptive crowd counting.
Given a target camera scene, our goal is to adapt a model to this specific scene with only a few labeled images of that scene.
We accomplish this challenge by taking inspiration from the recently introduced learning-to-learn paradigm in the context of few-shot regime.
arXiv Detail & Related papers (2020-02-01T19:41:26Z)
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.