DODA: Diffusion for Object-detection Domain Adaptation in Agriculture
- URL: http://arxiv.org/abs/2403.18334v1
- Date: Wed, 27 Mar 2024 08:16:33 GMT
- Title: DODA: Diffusion for Object-detection Domain Adaptation in Agriculture
- Authors: Shuai Xiang, Pieter M. Blok, James Burridge, Haozhou Wang, Wei Guo,
- Abstract summary: We propose DODA, a data synthesizer that can generate high-quality object detection data for new domains in agriculture.
Specifically, we improve the controllability of layout-to-image through encoding layout as an image, thereby improving the quality of labels.
- Score: 4.549305421261851
- License: http://creativecommons.org/licenses/by-nc-sa/4.0/
- Abstract: The diverse and high-quality content generated by recent generative models demonstrates the great potential of using synthetic data to train downstream models. However, in vision, especially in objection detection, related areas are not fully explored, the synthetic images are merely used to balance the long tails of existing datasets, and the accuracy of the generated labels is low, the full potential of generative models has not been exploited. In this paper, we propose DODA, a data synthesizer that can generate high-quality object detection data for new domains in agriculture. Specifically, we improve the controllability of layout-to-image through encoding layout as an image, thereby improving the quality of labels, and use a visual encoder to provide visual clues for the diffusion model to decouple visual features from the diffusion model, and empowering the model the ability to generate data in new domains. On the Global Wheat Head Detection (GWHD) Dataset, which is the largest dataset in agriculture and contains diverse domains, using the data synthesized by DODA improves the performance of the object detector by 12.74-17.76 AP$_{50}$ in the domain that was significantly shifted from the training data.
Related papers
- Regularized Training with Generated Datasets for Name-Only Transfer of Vision-Language Models [36.59260354292177]
Recent advancements in text-to-image generation have inspired researchers to generate datasets tailored for perception models using generative models.
We aim to fine-tune vision-language models to a specific classification model without access to any real images.
Despite the high fidelity of generated images, we observed a significant performance degradation when fine-tuning the model using the generated datasets.
arXiv Detail & Related papers (2024-06-08T10:43:49Z) - ADLDA: A Method to Reduce the Harm of Data Distribution Shift in Data Augmentation [11.887799310374174]
This study introduces a novel data augmentation technique, ADLDA, aimed at mitigating the negative impact of data distribution shifts.
Experimental results demonstrate that ADLDA significantly enhances model performance across multiple datasets.
arXiv Detail & Related papers (2024-05-11T03:20:35Z) - DetDiffusion: Synergizing Generative and Perceptive Models for Enhanced Data Generation and Perception [78.26734070960886]
Current perceptive models heavily depend on resource-intensive datasets.
We introduce perception-aware loss (P.A. loss) through segmentation, improving both quality and controllability.
Our method customizes data augmentation by extracting and utilizing perception-aware attribute (P.A. Attr) during generation.
arXiv Detail & Related papers (2024-03-20T04:58:03Z) - DreamDA: Generative Data Augmentation with Diffusion Models [68.22440150419003]
This paper proposes a new classification-oriented framework DreamDA.
DreamDA generates diverse samples that adhere to the original data distribution by considering training images in the original data as seeds.
In addition, since the labels of the generated data may not align with the labels of their corresponding seed images, we introduce a self-training paradigm for generating pseudo labels.
arXiv Detail & Related papers (2024-03-19T15:04:35Z) - GenFace: A Large-Scale Fine-Grained Face Forgery Benchmark and Cross
Appearance-Edge Learning [49.93362169016503]
The rapid advancement of photorealistic generators has reached a critical juncture where the discrepancy between authentic and manipulated images is increasingly indistinguishable.
Although there have been a number of publicly available face forgery datasets, the forgery faces are mostly generated using GAN-based synthesis technology.
We propose a large-scale, diverse, and fine-grained high-fidelity dataset, namely GenFace, to facilitate the advancement of deepfake detection.
arXiv Detail & Related papers (2024-02-03T03:13:50Z) - SODA: Bottleneck Diffusion Models for Representation Learning [75.7331354734152]
We introduce SODA, a self-supervised diffusion model, designed for representation learning.
The model incorporates an image encoder, which distills a source view into a compact representation, that guides the generation of related novel views.
We show that by imposing a tight bottleneck between the encoder and a denoising decoder, we can turn diffusion models into strong representation learners.
arXiv Detail & Related papers (2023-11-29T18:53:34Z) - UAV-Sim: NeRF-based Synthetic Data Generation for UAV-based Perception [62.71374902455154]
We leverage recent advancements in neural rendering to improve static and dynamic novelview UAV-based image rendering.
We demonstrate a considerable performance boost when a state-of-the-art detection model is optimized primarily on hybrid sets of real and synthetic data.
arXiv Detail & Related papers (2023-10-25T00:20:37Z) - SPAC-Net: Synthetic Pose-aware Animal ControlNet for Enhanced Pose
Estimation [19.035988285379116]
We present a new approach called Synthetic Pose-aware Animal ControlNet (SPAC-Net)
We leverage the plausible pose data generated by the Variational Auto-Encoder (VAE)-based data generation pipeline to generate synthetic data with pose labels closer to real data.
In addition, we propose the Bi-ControlNet structure to separately detect the HED boundary of animals and backgrounds, improving the precision and stability of the generated data.
arXiv Detail & Related papers (2023-05-29T01:56:42Z) - Generative Modeling Helps Weak Supervision (and Vice Versa) [87.62271390571837]
We propose a model fusing weak supervision and generative adversarial networks.
It captures discrete variables in the data alongside the weak supervision derived label estimate.
It is the first approach to enable data augmentation through weakly supervised synthetic images and pseudolabels.
arXiv Detail & Related papers (2022-03-22T20:24:21Z)
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.