Author name cluster

Jae-Joon Han

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

4 papers

2 author rows

ICML Conference 2021 Conference Paper

Learning Generalized Intersection Over Union for Dense Pixelwise Prediction

Jiaqian Yu
Jingtao Xu
Yiwei Chen
Weiming Li
Qiang Wang 0023
ByungIn Yoo
Jae-Joon Han

Intersection over union (IoU) score, also named Jaccard Index, is one of the most fundamental evaluation methods in machine learning. The original IoU computation cannot provide non-zero gradients and thus cannot be directly optimized by nowadays deep learning methods. Several recent works generalized IoU for bounding box regression, but they are not straightforward to adapt for pixelwise prediction. In particular, the original IoU fails to provide effective gradients for the non-overlapping and location-deviation cases, which results in performance plateau. In this paper, we propose PixIoU, a generalized IoU for pixelwise prediction that is sensitive to the distance for non-overlapping cases and the locations in prediction. We provide proofs that PixIoU holds many nice properties as the original IoU. To optimize the PixIoU, we also propose a loss function that is proved to be submodular, hence we can apply the Lovász functions, the efficient surrogates for submodular functions for learning this loss. Experimental results show consistent performance improvements by learning PixIoU over the original IoU for several different pixelwise prediction tasks on Pascal VOC, VOT-2020 and Cityscapes.

Details

AAAI Conference 2021 Conference Paper

Order Regularization on Ordinal Loss for Head Pose, Age and Gaze Estimation

Tianchu Guo
Hui Zhang
ByungIn Yoo
Yongchao Liu
Youngjun Kwak
Jae-Joon Han

Ordinal loss is widely used in solving regression problems with deep learning technologies. Its basic idea is to convert regression to classification while preserving the natural order. However, the order constraint is enforced only by ordinal label implicitly, leading to the real output values not strictly in order. It causes the network to learn separable feature rather than discriminative feature, and possibly overfit on training set. In this paper, we propose order regularization on ordinal loss, which makes the outputs in order by explicitly constraining the ordinal classifiers in order. The proposed method contains two parts, i. e. similar-weights constraint, which reduces the ineffective space between classifiers, and differential-bias constraint, which enforces the decision planes in order and enhances the discrimination power of the classifiers. Experimental results show that our proposed method boosts the performance of original ordinal loss on various regression problems such as head pose, age, and gaze estimation, with significant error reduction of around 5%. Furthermore, our method outperforms the state of the art on all these tasks, with the performance gain of 14. 4%, 2. 2% and 6. 5% on head pose, age and gaze estimation respectively.

PDF Details

ICML Conference 2020 Conference Paper

Meta Variance Transfer: Learning to Augment from the Others

Seong-Jin Park
Seungju Han 0001
Ji-Won Baek
Insoo Kim
Juhwan Song
Haebeom Lee
Jae-Joon Han
Sung Ju Hwang

Humans have the ability to robustly recognize objects with various factors of variations such as nonrigid transformations, background noises, and changes in lighting conditions. However, training deep learning models generally require huge amount of data instances under diverse variations, to ensure its robustness. To alleviate the need of collecting large amount of data and better learn to generalize with scarce data instances, we propose a novel meta-learning method which learns to transfer factors of variations from one class to another, such that it can improve the classification performance on unseen examples. Transferred variations generate virtual samples that augment the feature space of the target class during training, simulating upcoming query samples with similar variations. By sharing the factors of variations across different classes, the model becomes more robust to variations in the unseen examples and tasks using small number of examples per class. We validate our model on multiple benchmark datasets for few-shot classification and face recognition, on which our model significantly improves the performance of the base model, outperforming relevant baselines.

Details

AAAI Conference 2018 Conference Paper

Residual Encoder Decoder Network and Adaptive Prior for Face Parsing

Tianchu Guo
Youngsung Kim
Hui Zhang
Deheng Qian
ByungIn Yoo
Jingtao Xu
Dongqing Zou
Jae-Joon Han

Face parsing assigns every pixel in a facial image with a semantic label, which could be applied in various applications including face expression recognition, facial beautiﬁcation, affective computing and animation. While lots of progress have been made in this ﬁeld, current state-of-the-art methods still fail to extract real effective feature and restore accurate score map, especially for those facial parts which have large variations of deformation and fairly similar appearance, e. g. mouth, eyes and thin eyebrows. In this paper, we propose a novel pixel-wise face parsing method called Residual Encoder Decoder Network (RED-Net), which combines a feature-rich encoder-decoder framework with adaptive prior mechanism. Our encoder-decoder framework extracts feature with ResNet and decodes the feature by elaborately fusing the residual architectures into deconvolution. This framework learns more effective feature comparing to that learnt by decoding with interpolation or classic deconvolution operations. To overcome the appearance ambiguity between facial parts, an adaptive prior mechanism is proposed in term of the decoder prediction conﬁdence, allowing reﬁning the ﬁnal result. The experimental results on two public databases demonstrate that our method outperforms the state-of-thearts signiﬁcantly, achieving improvements of F-measure from 0. 854 to 0. 905 on the Helen dataset, and pixel accuracy from 95. 12% to 97. 59% on the LFW dataset. In particular, convincing qualitative examples show that our method parses eye, eyebrow and lip regions more accurately.

PDF Details