“Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告

The PASCAL Visual Object Classes Challenge

Semi-supervised learning (SSL) provides an effective means of leveraging unlabeled data to improve a model's performance. In this paper, we demonstrate the power of a simple combination of two common SSL methods: consistency regularization and pseudo-labeling. Our algorithm, FixMatch, first generates pseudo-labels using the model's predictions on weakly-augmented unlabeled images. For a given image, the pseudo-label is only retained if the model produces a high-confidence prediction. The model is then trained to predict the pseudo-label when fed a strongly-augmented version of the same image. Despite its simplicity, we show that FixMatch achieves state-of-the-art performance across a variety of standard semi-supervised learning benchmarks, including 94.93% accuracy on CIFAR-10 with 250 labels and 88.61% accuracy with 40 -- just 4 labels per class. Since FixMatch bears many similarities to existing SSL methods that achieve worse performance, we carry out an extensive ablation study to tease apart the experimental factors that are most important to FixMatch's success. We make our code available at this https URL.

/pdf/fixmatch-simplifying-semi-supervised-learning-with-12wbyf3fji.pdf

FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence

Unsupervised Domain Adaptation (UDA) makes predictions for the target domain data while manual annotations are only available in the source domain. Previous methods minimize the domain discrepancy neglecting the class information, which may lead to misalignment and poor generalization performance. To address this issue, this paper proposes Contrastive Adaptation Network (CAN) optimizing a new metric which explicitly models the intra-class domain discrepancy and the inter-class domain discrepancy. We design an alternating update strategy for training CAN in an end-to-end manner. Experiments on two real-world benchmarks Office-31 and VisDA-2017 demonstrate that CAN performs favorably against the state-of-the-art methods and produces more discriminative features.

/pdf/contrastive-adaptation-network-for-unsupervised-domain-1uxdeiy0kh.pdf

Contrastive Adaptation Network for Unsupervised Domain Adaptation

Conventional unsupervised domain adaptation (UDA) assumes that training data are sampled from a single domain. This neglects the more practical scenario where training data are collected from multiple sources, requiring multi-source domain adaptation. We make three major contributions towards addressing this problem. First, we collect and annotate by far the largest UDA dataset, called DomainNet, which contains six domains and about 0.6 million images distributed among 345 categories, addressing the gap in data availability for multi-source UDA research. Second, we propose a new deep learning approach, Moment Matching for Multi-Source Domain Adaptation M3SDA, which aims to transfer knowledge learned from multiple labeled source domains to an unlabeled target domain by dynamically aligning moments of their feature distributions. Third, we provide new theoretical insights specifically for moment matching approaches in both single and multiple source domain adaptation. Extensive experiments are conducted to demonstrate the power of our new dataset in benchmarking state-of-the-art multi-source domain adaptation methods, as well as the advantage of our proposed model. Dataset and Code are available at \url{this http URL}.

Moment Matching for Multi-Source Domain Adaptation

This paper explores the use of self-ensembling for visual domain adaptation problems. Our technique is derived from the mean teacher variant (Tarvainen et al., 2017) of temporal ensembling (Laine et al;, 2017), a technique that achieved state of the art results in the area of semi-supervised learning. We introduce a number of modifications to their approach for challenging domain adaptation scenarios and evaluate its effectiveness. Our approach achieves state of the art results in a variety of benchmarks, including our winning entry in the VISDA-2017 visual domain adaptation challenge. In small image benchmarks, our algorithm not only outperforms prior art, but can also achieve accuracy that is close to that of a classifier trained in a supervised fashion.

Self-ensembling for visual domain adaptation

/pdf/self-ensembling-for-visual-domain-adaptation-2k3lagd0yn.pdf

Consistency regularization describes a class of approaches that have yielded ground breaking results in semi-supervised classification problems. Prior work has established the cluster assumption - under which the data distribution consists of uniform class clusters of samples separated by low density regions - as important to its success. We analyze the problem of semantic segmentation and find that its' distribution does not exhibit low density regions separating classes and offer this as an explanation for why semi-supervised segmentation is a challenging problem, with only a few reports of success. We then identify choice of augmentation as key to obtaining reliable performance without such low-density regions. We find that adapted variants of the recently proposed CutOut and CutMix augmentation techniques yield state-of-the-art semi-supervised semantic segmentation results in standard datasets. Furthermore, given its challenging nature we propose that semantic segmentation acts as an effective acid test for evaluating semi-supervised regularizers. Implementation at: this https URL.

Semi-supervised semantic segmentation needs strong, varied perturbations

We present a computer vision tool that analyses video from a CCTV system installed on fishing trawlers to monitor discarded fish catch. The system aims to support expert observers who review the footage and verify numbers, species and sizes of discarded fish. The operational environment presents a significant challenge for these tasks. Fish are processed below deck under fluorescent lights, they are randomly oriented and there are multiple occlusions. The scene is unstructured and complicated by the presence of fishermen processing the catch. We describe an approach to segmenting the scene and counting fish that exploits the $N^4$-Fields algorithm. We performed extensive tests of the algorithm on a data set comprising 443 frames from 6 belts. Results indicate the relative count error (for individual fish) ranges from 2\% to 16\%. We believe this is the first system that is able to handle footage from operational trawlers.

/pdf/convolutional-neural-networks-for-counting-fish-in-fisheries-48ld1tz06w.pdf

Geoffrey French

Papers

Self-ensembling for visual domain adaptation

Self-ensembling for visual domain adaptation

Semi-supervised semantic segmentation needs strong, varied perturbations

Convolutional Neural Networks for Counting Fish in Fisheries Surveillance Video

Self-ensembling for domain adaptation.