An Embarrassingly Simple Approach to Visual Domain Adaptation

Lü, Hao; Shen, Chunhua; Xiao, Yang; Hengel, Anton van den

doi:10.1109/tip.2018.2819503

Cited by 97 publications

(35 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Models learned on the training set may not generalize well to the testing set with significant variations in plant cultivars, illumination changes, and poses. In this case, the idea of domain adaptation may be applied to fill the performance loss (Lu et al, 2017b(Lu et al, , 2018. All evaluation results above suggest the general applicability of TasselNetV2+ in plant counting, especially when only the count value is the output of interest.…”

Section: Further Discussionmentioning

confidence: 89%

TasselNetV2+: A Fast Implementation for High-Throughput Plant Counting From High-Resolution RGB Imagery

Lü

2020

Front. Plant Sci.

Self Cite

View full text Add to dashboard Cite

Plant counting runs through almost every stage of agricultural production from seed breeding, germination, cultivation, fertilization, pollination to yield estimation, and harvesting. With the prevalence of digital cameras, graphics processing units and deep learning-based computer vision technology, plant counting has gradually shifted from traditional manual observation to vision-based automated solutions. One of popular solutions is a state-of-the-art object detection technique called Faster R-CNN where plant counts can be estimated from the number of bounding boxes detected. It has become a standard configuration for many plant counting systems in plant phenotyping. Faster R-CNN, however, is expensive in computation, particularly when dealing with high-resolution images. Unfortunately high-resolution imagery is frequently used in modern plant phenotyping platforms such as unmanned aerial vehicles, engendering inefficient image analysis. Such inefficiency largely limits the throughput of a phenotyping system. The goal of this work hence is to provide an effective and efficient tool for high-throughput plant counting from high-resolution RGB imagery. In contrast to conventional object detection, we encourage another promising paradigm termed object counting where plant counts are directly regressed from images, without detecting bounding boxes. In this work, by profiling the computational bottleneck, we implement a fast version of a state-of-the-art plant counting model TasselNetV2 with several minor yet effective modifications. We also provide insights why these modifications make sense. This fast version, TasselNetV2+, runs an order of magnitude faster than TasselNetV2, achieving around 30 fps on image resolution of 1980 × 1080, while it still retains the same level of counting accuracy. We validate its effectiveness on three plant counting tasks, including wheat ears counting, maize tassels counting, and sorghum heads counting. To encourage the use of this tool, our implementation has been made available online at https://tinyurl.com/TasselNetV2plus.

show abstract

Section: Further Discussionmentioning

confidence: 89%

TasselNetV2+: A Fast Implementation for High-Throughput Plant Counting From High-Resolution RGB Imagery

Lü

2020

Front. Plant Sci.

Self Cite

View full text Add to dashboard Cite

show abstract

“… Domain Irrelevant Class clustering (DICE) [ 38 ]: This method specifically deals with the intra-domain structure for the target domain in addition to other common properties. Linear Discriminant Analysis-inspired Domain Adaptation (LDADA) [ 39 ]: The key insight of this approach is to leverage the discriminative information from the target task, even when the target domain labels are not given. Kernelized Unified Framework for Domain Adaptation (KUFDA) [ 16 ]: This TL method improves the JGSA method by adding the Laplacian regularization term.…”

Section: Methodsmentioning

confidence: 99%

“…Linear Discriminant Analysis-inspired Domain Adaptation (LDADA) [39]: The key insight of this approach is to leverage the discriminative information from the target task, even when the target domain labels are not given.…”

mentioning

confidence: 99%

A Subspace Based Transfer Joint Matching with Laplacian Regularization for Visual Domain Adaptation

Sanodiya

Yao

2020

Sensors

View full text Add to dashboard Cite

In a real-world application, the images taken by different cameras with different conditions often incur illumination variation, low-resolution, different poses, blur, etc., which leads to a large distribution difference or gap between training (source) and test (target) images. This distribution gap is challenging for many primitive machine learning classification and clustering algorithms such as k-Nearest Neighbor (k-NN) and k-means. In order to minimize this distribution gap, we propose a novel Subspace based Transfer Joint Matching with Laplacian Regularization (STJML) method for visual domain adaptation by jointly matching the features and re-weighting the instances across different domains. Specifically, the proposed STJML-based method includes four key components: (1) considering subspaces of both domains; (2) instance re-weighting; (3) it simultaneously reduces the domain shift in both marginal distribution and conditional distribution between the source domain and the target domain; (4) preserving the original similarity of data points by using Laplacian regularization. Experiments on three popular real-world domain adaptation problem datasets demonstrate a significant performance improvement of our proposed method over published state-of-the-art primitive and domain adaptation methods.

show abstract

“…The performance of the proposed DASGA method is compared to the domain adaptation methods Heterogeneous Domain Adaptation using Manifold Alignment (DAMA) [32], Easy Adapt++ (EA++) [23], Subspace Alignment (SA) [2], Geodesic Flow Kernel for Unsupervised Domain Adaptation (GFK) [3], Scatter Component Analysis (SCA) [40], LDA-Inspired Domain Adaptation (LDADA) [46], Joint Geometrical and Statistical Alignment (JGSA) [31]; as well as the baseline classifiers Support Vector Machine (SVM), Nearest-Neighbor classification (NN), and the graph-based Semi-Supervised Learning with Gaussian fields (SSL) algorithm [13]. The baseline classifiers SVM and NN are eval- uated under the "source+target" setting using the labeled samples from both the source and the target domains for training, and the SSL algorithm is used in the "target only" setting, which give the best results.…”

Section: Evaluation Of the Algorithm Performancementioning

confidence: 99%

“…The performance gap between DASGA and the other methods is larger in Synthetic dataset-2, which is a more challenging data set due to the relatively high distribution variance. Among the domain adaptation methods, DAMA [32] and LDADA [46] give the closest performance to the proposed DASGA method. The approach in both of these methods is to learn supervised projections, which is relatively successful in this synthetic data set consisting of normally distributed data.…”

Section: Experiments On Synthetic Data Setsmentioning

confidence: 99%

Domain Adaptation on Graphs by Learning Aligned Graph Bases

Pilanci

Vural

2022

IEEE Trans. Knowl. Data Eng.

View full text Add to dashboard Cite

A common assumption in semi-supervised learning with graph models is that the class label function varies smoothly on the data graph, resulting in the rather strict prior that the label function has low-frequency content. Meanwhile, in many classification problems, the label function may vary abruptly in certain graph regions, resulting in high-frequency components. Although the semi-supervised estimation of class labels is an ill-posed problem in general, in several applications it is possible to find a source graph on which the label function has similar frequency content to that on the target graph where the actual classification problem is defined. In this paper, we propose a method for domain adaptation on graphs motivated by these observations. Our algorithm is based on learning the spectrum of the label function in a source graph with many labeled nodes, and transferring the information of the spectrum to the target graph with fewer labeled nodes. While the frequency content of the class label function can be identified through the graph Fourier transform, it is not easy to transfer the Fourier coefficients directly between the two graphs, since no one-to-one match exists between the Fourier basis vectors of independently constructed graphs in the domain adaptation setting. We solve this problem by learning a transformation between the Fourier bases of the two graphs that flexibly "aligns" them. The unknown class label function on the target graph is then reconstructed such that its spectrum matches that on the source graph while also ensuring the consistency with the available labels. The proposed method is tested in the classification of image, online product review, and social network data sets. Comparative experiments suggest that the proposed algorithm performs better than recent domain adaptation methods in the literature in most settings.

show abstract

An Embarrassingly Simple Approach to Visual Domain Adaptation

Cited by 97 publications

References 35 publications

TasselNetV2+: A Fast Implementation for High-Throughput Plant Counting From High-Resolution RGB Imagery

TasselNetV2+: A Fast Implementation for High-Throughput Plant Counting From High-Resolution RGB Imagery

A Subspace Based Transfer Joint Matching with Laplacian Regularization for Visual Domain Adaptation

Domain Adaptation on Graphs by Learning Aligned Graph Bases

Contact Info

Product

Resources

About