Utilizing Grounded SAM for self-supervised frugal camouflaged human detection
- URL: http://arxiv.org/abs/2406.05776v1
- Date: Sun, 9 Jun 2024 13:19:20 GMT
- Title: Utilizing Grounded SAM for self-supervised frugal camouflaged human detection
- Authors: Matthias Pijarowski, Alexander Wolpert, Martin Heckmann, Michael Teutsch,
- Abstract summary: Both self-supervised and frugal learning methods are introduced to the task of Camouflaged Object Detection.
We create a strong baseline using supervised frugal transfer learning for the fine-tuning task.
Our experiments show that we achieve similar performance by pure self-supervision compared to fully supervised frugal learning.
- Score: 43.52281022671451
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Visually detecting camouflaged objects is a hard problem for both humans and computer vision algorithms. Strong similarities between object and background appearance make the task significantly more challenging than traditional object detection or segmentation tasks. Current state-of-the-art models use either convolutional neural networks or vision transformers as feature extractors. They are trained in a fully supervised manner and thus need a large amount of labeled training data. In this paper, both self-supervised and frugal learning methods are introduced to the task of Camouflaged Object Detection (COD). The overall goal is to fine-tune two COD reference methods, namely SINet-V2 and HitNet, pre-trained for camouflaged animal detection to the task of camouflaged human detection. Therefore, we use the public dataset CPD1K that contains camouflaged humans in a forest environment. We create a strong baseline using supervised frugal transfer learning for the fine-tuning task. Then, we analyze three pseudo-labeling approaches to perform the fine-tuning task in a self-supervised manner. Our experiments show that we achieve similar performance by pure self-supervision compared to fully supervised frugal learning.
Related papers
- Seamless Detection: Unifying Salient Object Detection and Camouflaged Object Detection [73.85890512959861]
We propose a task-agnostic framework to unify Salient Object Detection (SOD) and Camouflaged Object Detection (COD)
We design a simple yet effective contextual decoder involving the interval-layer and global context, which achieves an inference speed of 67 fps.
Experiments on public SOD and COD datasets demonstrate the superiority of our proposed framework in both supervised and unsupervised settings.
arXiv Detail & Related papers (2024-12-22T03:25:43Z) - Heuristic Vision Pre-Training with Self-Supervised and Supervised
Multi-Task Learning [0.0]
We propose a novel pre-training framework by adopting both self-supervised and supervised visual pre-text tasks in a multi-task manner.
Results show that our pre-trained models can deliver results on par with or better than state-of-the-art (SOTA) results on multiple visual tasks.
arXiv Detail & Related papers (2023-10-11T14:06:04Z) - Camouflaged Image Synthesis Is All You Need to Boost Camouflaged
Detection [65.8867003376637]
We propose a framework for synthesizing camouflage data to enhance the detection of camouflaged objects in natural scenes.
Our approach employs a generative model to produce realistic camouflage images, which can be used to train existing object detection models.
Our framework outperforms the current state-of-the-art method on three datasets.
arXiv Detail & Related papers (2023-08-13T06:55:05Z) - The Art of Camouflage: Few-Shot Learning for Animal Detection and Segmentation [21.047026366450197]
We address the problem of few-shot learning for camouflaged object detection and segmentation.
We propose FS-CDIS, a framework to efficiently detect and segment camouflaged instances.
Our proposed method achieves state-of-the-art performance on the newly collected dataset.
arXiv Detail & Related papers (2023-04-15T01:33:14Z) - Towards Deeper Understanding of Camouflaged Object Detection [64.81987999832032]
We argue that the binary segmentation setting fails to fully understand the concept of camouflage.
We present the first triple-task learning framework to simultaneously localize, segment and rank camouflaged objects.
arXiv Detail & Related papers (2022-05-23T14:26:18Z) - SEAL: Self-supervised Embodied Active Learning using Exploration and 3D
Consistency [122.18108118190334]
We present a framework called Self- Embodied Embodied Active Learning (SEAL)
It utilizes perception models trained on internet images to learn an active exploration policy.
We and build utilize 3D semantic maps to learn both action and perception in a completely self-supervised manner.
arXiv Detail & Related papers (2021-12-02T06:26:38Z) - Move to See Better: Self-Improving Embodied Object Detection [35.461141354989714]
We propose a method for improving object detection in testing environments.
Our agent collects multi-view data, generates 2D and 3D pseudo-labels, and fine-tunes its detector in a self-supervised manner.
arXiv Detail & Related papers (2020-11-30T19:16:51Z) - Co-training for On-board Deep Object Detection [0.0]
Best performing deep vision-based object detectors are trained in a supervised manner by relying on human-labeled bounding boxes.
Co-training is a semi-supervised learning method for self-labeling objects in unlabeled images.
We show how co-training is a paradigm worth to pursue for alleviating object labeling, working both alone and together with task-agnostic domain adaptation.
arXiv Detail & Related papers (2020-08-12T19:08:59Z) - Self-Supervised Viewpoint Learning From Image Collections [116.56304441362994]
We propose a novel learning framework which incorporates an analysis-by-synthesis paradigm to reconstruct images in a viewpoint aware manner.
We show that our approach performs competitively to fully-supervised approaches for several object categories like human faces, cars, buses, and trains.
arXiv Detail & Related papers (2020-04-03T22:01:41Z)
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.