Leaf Segmentation and Counting with Deep Learning: on Model Certainty, Test-Time Augmentation, Trade-Offs

• URL: http://arxiv.org/abs/2012.11486v1
• Date: Mon, 21 Dec 2020 17:00:05 GMT
• Title: Leaf Segmentation and Counting with Deep Learning: on Model Certainty, Test-Time Augmentation, Trade-Offs
• Authors: Douglas Pinto Sampaio Gomes, Lihong Zheng
• Abstract summary: Deep supervised learning has been prevalent in recent works proposing better performing models at segmenting and counting leaves. Despite good efforts from research groups, one of the main challenges for proposing better methods is still the limitation of labelled data availability.
• Score: 2.984934409689467
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Plant phenotyping tasks such as leaf segmentation and counting are fundamental to the study of phenotypic traits. Since it is well-suited for these tasks, deep supervised learning has been prevalent in recent works proposing better performing models at segmenting and counting leaves. Despite good efforts from research groups, one of the main challenges for proposing better methods is still the limitation of labelled data availability. The main efforts of the field seem to be augmenting existing limited data sets, and some aspects of the modelling process have been under-discussed. This paper explores such topics and present experiments that led to the development of the best-performing method in the Leaf Segmentation Challenge and in another external data set of Komatsuna plants. The model has competitive performance while been arguably simpler than other recently proposed ones. The experiments also brought insights such as the fact that model cardinality and test-time augmentation may have strong applications in object segmentation of single class and high occlusion, and regarding the data distribution of recently proposed data sets for benchmarking.

Related papers

• Specialization after Generalization: Towards Understanding Test-Time Training in Foundation Models [64.02612380298228]
  Recent studies have explored the idea of continuing to train a model at test-time for a given task, known as test-time training (TTT)<n>We propose a model in which TTT achieves a substantially smaller in-distribution test error than global training.<n>We empirically validate our model's key assumptions by training a sparse autoencoder on ImageNet.
  arXiv  Detail & Related papers  (2025-09-29T09:24:52Z)
• Efficient Long-Tail Learning in Latent Space by sampling Synthetic Data [1.9290392443571385]
  Imbalanced classification datasets pose significant challenges in machine learning.<n>We propose a novel framework that leverages the rich semantic latent space of Vision Foundation Models to generate synthetic data and train a simple linear classifier.<n>Our method sets a new state-of-the-art for the CIFAR-100-LT benchmark and demonstrates strong performance on the Places-LT benchmark.
  arXiv  Detail & Related papers  (2025-09-19T10:52:31Z)
• GLiDRE: Generalist Lightweight model for Document-level Relation Extraction [1.8628821924525962]
  We introduce GLiDRE, a new compact model for document-level relation extraction, designed to work efficiently in both supervised and few-shot settings.<n> Experiments in both low-resource supervised training and few-shot meta-learning benchmarks show that our approach outperforms existing methods in data-constrained scenarios.<n>Our code will be publicly available.
  arXiv  Detail & Related papers  (2025-08-01T16:33:13Z)
• A Coreset Selection of Coreset Selection Literature: Introduction and Recent Advances [8.319613769928331]
  Coreset selection targets the challenge of finding a small, representative subset of a large dataset that preserves essential patterns for effective machine learning.<n>This survey presents a more comprehensive view by unifying three major lines of coreset research into a single taxonomy.<n>We present subfields often overlooked by existing work, including submodular formulations, bilevel optimization, and recent progress in pseudo-labeling for unlabeled datasets.
  arXiv  Detail & Related papers  (2025-05-23T12:18:34Z)
• How Hard is this Test Set? NLI Characterization by Exploiting Training Dynamics [49.9329723199239]
  We propose a method for the automated creation of a challenging test set without relying on the manual construction of artificial and unrealistic examples. We categorize the test set of popular NLI datasets into three difficulty levels by leveraging methods that exploit training dynamics. When our characterization method is applied to the training set, models trained with only a fraction of the data achieve comparable performance to those trained on the full dataset.
  arXiv  Detail & Related papers  (2024-10-04T13:39:21Z)
• Rejection Sampling IMLE: Designing Priors for Better Few-Shot Image Synthesis [7.234618871984921]
  An emerging area of research aims to learn deep generative models with limited training data. We propose RS-IMLE, a novel approach that changes the prior distribution used for training. This leads to substantially higher quality image generation compared to existing GAN and IMLE-based methods.
  arXiv  Detail & Related papers  (2024-09-26T00:19:42Z)
• Corpus Considerations for Annotator Modeling and Scaling [9.263562546969695]
  We show that the commonly used user token model consistently outperforms more complex models. Our findings shed light on the relationship between corpus statistics and annotator modeling performance.
  arXiv  Detail & Related papers  (2024-04-02T22:27:24Z)
• A Survey on Data Selection for Language Models [148.300726396877]
  Data selection methods aim to determine which data points to include in a training dataset. Deep learning is mostly driven by empirical evidence and experimentation on large-scale data is expensive. Few organizations have the resources for extensive data selection research.
  arXiv  Detail & Related papers  (2024-02-26T18:54:35Z)
• Fantastic Gains and Where to Find Them: On the Existence and Prospect of General Knowledge Transfer between Any Pretrained Model [74.62272538148245]
  We show that for arbitrary pairings of pretrained models, one model extracts significant data context unavailable in the other. We investigate if it is possible to transfer such "complementary" knowledge from one model to another without performance degradation.
  arXiv  Detail & Related papers  (2023-10-26T17:59:46Z)
• Exploring the Impact of Instruction Data Scaling on Large Language Models: An Empirical Study on Real-World Use Cases [17.431381376675432]
  In this paper we explore the performance of large language models based on instruction tuning across different scales of instruction data. With Bloomz-7B1-mt as the base model, the results show that merely increasing the amount of instruction data leads to continuous improvement in tasks such as open-ended generation. We propose potential future research directions such as effectively selecting high-quality training data, scaling base models and training methods specialized for hard tasks.
  arXiv  Detail & Related papers  (2023-03-26T14:49:37Z)
• Data Augmentation techniques in time series domain: A survey and taxonomy [0.20971479389679332]
  Deep neural networks used to work with time series heavily depend on the size and consistency of the datasets used in training. This work systematically reviews the current state-of-the-art in the area to provide an overview of all available algorithms. The ultimate aim of this study is to provide a summary of the evolution and performance of areas that produce better results to guide future researchers in this field.
  arXiv  Detail & Related papers  (2022-06-25T17:09:00Z)
• Robust Task-Oriented Dialogue Generation with Contrastive Pre-training and Adversarial Filtering [17.7709632238066]
  Data artifacts incentivize machine learning models to learn non-transferable generalizations. We investigate whether popular datasets such as MultiWOZ contain such data artifacts. We propose a contrastive learning based framework to encourage the model to ignore these cues and focus on learning generalisable patterns.
  arXiv  Detail & Related papers  (2022-05-20T03:13:02Z)
• On the Efficacy of Adversarial Data Collection for Question Answering: Results from a Large-Scale Randomized Study [65.17429512679695]
  In adversarial data collection (ADC), a human workforce interacts with a model in real time, attempting to produce examples that elicit incorrect predictions. Despite ADC's intuitive appeal, it remains unclear when training on adversarial datasets produces more robust models.
  arXiv  Detail & Related papers  (2021-06-02T00:48:33Z)
• Regularizing Generative Adversarial Networks under Limited Data [88.57330330305535]
  This work proposes a regularization approach for training robust GAN models on limited data. We show a connection between the regularized loss and an f-divergence called LeCam-divergence, which we find is more robust under limited training data.
  arXiv  Detail & Related papers  (2021-04-07T17:59:06Z)
• The Devil is in Classification: A Simple Framework for Long-tail Object Detection and Instance Segmentation [93.17367076148348]
  We investigate performance drop of the state-of-the-art two-stage instance segmentation model Mask R-CNN on the recent long-tail LVIS dataset. We unveil that a major cause is the inaccurate classification of object proposals. We propose a simple calibration framework to more effectively alleviate classification head bias with a bi-level class balanced sampling approach.
  arXiv  Detail & Related papers  (2020-07-23T12:49:07Z)

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.