arXiv subjects

Junmo Kim

Publications and source records attributed to Junmo Kim.

126 records · Page 7Linked to original sources

arXiv2020

Adjusting Decision Boundary for Class Imbalanced Learning

Training of deep neural networks heavily depends on the data distribution. In particular, the networks easily suffer from class imbalance. The trained networks would recognize the frequent classes better than the infrequent classes. To resolve this problem, existing approaches typically propose novel loss functions to obtain better feature embedding. In this paper, we argue that drawing a better decision boundary is as important as learning better features. Inspired by observations, we investigate how the class imbalance affects the decision boundary and deteriorates the performance. We also investigate the feature distributional discrepancy between training and test time. As a result, we propose a novel, yet simple method for class imbalanced learning. Despite its simplicity, our method shows outstanding performance. In particular, the experimental results show that we can significantly improve the network by scaling the weight vectors, even without additional training process.

cs.CV↗

arXiv2020

Residual Continual Learning

We propose a novel continual learning method called Residual Continual Learning (ResCL). Our method can prevent the catastrophic forgetting phenomenon in sequential learning of multiple tasks, without any source task information except the original network. ResCL reparameterizes network parameters by linearly combining each layer of the original network and a fine-tuned network; therefore, the size of the network does not increase at all. To apply the proposed method to general convolutional neural networks, the effects of batch normalization layers are also considered. By utilizing residual-learning-like reparameterization and a special weight decay loss, the trade-off between source and target performance is effectively controlled. The proposed method exhibits state-of-the-art performance in various continual learning scenarios.

cs.LG↗

arXiv2019

EDAS: Efficient and Differentiable Architecture Search

Transferrable neural architecture search can be viewed as a binary optimization problem where a single optimal path should be selected among candidate paths in each edge within the repeated cell block of the directed a cyclic graph form. Recently, the field of differentiable architecture search attempts to relax the search problem continuously using a one-shot network that combines all the candidate paths in search space. However, when the one-shot network is pruned to the model in the discrete architecture space by the derivation algorithm, performance is significantly degraded to an almost random estimator. To reduce the quantization error from the heavy use of relaxation, we only sample a single edge to relax the corresponding variable and clamp variables in the other edges to zero or one. By this method, there is no performance drop after pruning the one-shot network by derivation algorithm, due to the preservation of the discrete nature of optimization variables during the search. Furthermore, the minimization of relaxation degree allows searching in a deeper network to discover better performance with remarkable search cost reduction (0.125 GPU days) compared to previous methods. By adding several regularization methods that help explore within the search space, we could obtain the network with notable performances on CIFAR-10, CIFAR-100, and ImageNet.

cs.CV↗

arXiv2019

NLNL: Negative Learning for Noisy Labels

Convolutional Neural Networks (CNNs) provide excellent performance when used for image classification. The classical method of training CNNs is by labeling images in a supervised manner as in "input image belongs to this label" (Positive Learning; PL), which is a fast and accurate method if the labels are assigned correctly to all images. However, if inaccurate labels, or noisy labels, exist, training with PL will provide wrong information, thus severely degrading performance. To address this issue, we start with an indirect learning method called Negative Learning (NL), in which the CNNs are trained using a complementary label as in "input image does not belong to this complementary label." Because the chances of selecting a true label as a complementary label are low, NL decreases the risk of providing incorrect information. Furthermore, to improve convergence, we extend our method by adopting PL selectively, termed as Selective Negative Learning and Positive Learning (SelNLPL). PL is used selectively to train upon expected-to-be-clean data, whose choices become possible as NL progresses, thus resulting in superior performance of filtering out noisy data. With simple semi-supervised training technique, our method achieves state-of-the-art accuracy for noisy data classification, proving the superiority of SelNLPL's noisy data filtering ability.

cs.LG↗

arXiv2019

RRNet: Repetition-Reduction Network for Energy Efficient Decoder of Depth Estimation

We introduce Repetition-Reduction network (RRNet) for resource-constrained depth estimation, offering significantly improved efficiency in terms of computation, memory and energy consumption. The proposed method is based on repetition-reduction (RR) blocks. The RR blocks consist of the set of repeated convolutions and the residual connection layer that take place of the pointwise reduction layer with linear connection to the decoder. The RRNet help reduce memory usage and power consumption in the residual connections to the decoder layers. RRNet consumes approximately 3.84 times less energy and 3.06 times less meory and is approaximately 2.21 times faster, without increasing the demand on hardware resource relative to the baseline network (Godard et al, CVPR'17), outperforming current state-of-the-art lightweight architectures such as SqueezeNet, ShuffleNet, MobileNet and PyDNet.

cs.CV↗

arXiv2019

Deep generative-contrastive networks for facial expression recognition

As the expressive depth of an emotional face differs with individuals or expressions, recognizing an expression using a single facial image at a moment is difficult. A relative expression of a query face compared to a reference face might alleviate this difficulty. In this paper, we propose to utilize contrastive representation that embeds a distinctive expressive factor for a discriminative purpose. The contrastive representation is calculated at the embedding layer of deep networks by comparing a given (query) image with the reference image. We attempt to utilize a generative reference image that is estimated based on the given image. Consequently, we deploy deep neural networks that embed a combination of a generative model, a contrastive model, and a discriminative model with an end-to-end training manner. In our proposed networks, we attempt to disentangle a facial expressive factor in two steps including learning of a generator network and a contrastive encoder network. We conducted extensive experiments on publicly available face expression databases (CK+, MMI, Oulu-CASIA, and in-the-wild databases) that have been widely adopted in the recent literatures. The proposed method outperforms the known state-of-the art methods in terms of the recognition accuracy.

cs.CV↗

arXiv2019

Learning Not to Learn: Training Deep Neural Networks with Biased Data

We propose a novel regularization algorithm to train deep neural networks, in which data at training time is severely biased. Since a neural network efficiently learns data distribution, a network is likely to learn the bias information to categorize input data. It leads to poor performance at test time, if the bias is, in fact, irrelevant to the categorization. In this paper, we formulate a regularization loss based on mutual information between feature embedding and bias. Based on the idea of minimizing this mutual information, we propose an iterative algorithm to unlearn the bias information. We employ an additional network to predict the bias distribution and train the network adversarially against the feature embedding network. At the end of learning, the bias prediction network is not able to predict the bias not because it is poorly trained, but because the feature embedding network successfully unlearns the bias information. We also demonstrate quantitative and qualitative experimental results which show that our algorithm effectively removes the bias information from feature embedding.

cs.CV↗

arXiv2019

Integrating Multiple Receptive Fields through Grouped Active Convolution

Convolutional networks have achieved great success in various vision tasks. This is mainly due to a considerable amount of research on network structure. In this study, instead of focusing on architectures, we focused on the convolution unit itself. The existing convolution unit has a fixed shape and is limited to observing restricted receptive fields. In earlier work, we proposed the active convolution unit (ACU), which can freely define its shape and learn by itself. In this paper, we provide a detailed analysis of the previously proposed unit and show that it is an efficient representation of a sparse weight convolution. Furthermore, we extend an ACU to a grouped ACU, which can observe multiple receptive fields in one layer. We found that the performance of a naive grouped convolution is degraded by increasing the number of groups; however, the proposed unit retains the accuracy even though the number of parameters decreases. Based on this result, we suggest a depthwise ACU, and various experiments have shown that our unit is efficient and can replace the existing convolutions.

cs.CV↗

arXiv2018

Constructing Fast Network through Deconstruction of Convolution

Convolutional neural networks have achieved great success in various vision tasks; however, they incur heavy resource costs. By using deeper and wider networks, network accuracy can be improved rapidly. However, in an environment with limited resources (e.g., mobile applications), heavy networks may not be usable. This study shows that naive convolution can be deconstructed into a shift operation and pointwise convolution. To cope with various convolutions, we propose a new shift operation called active shift layer (ASL) that formulates the amount of shift as a learnable function with shift parameters. This new layer can be optimized end-to-end through backpropagation and it can provide optimal shift values. Finally, we apply this layer to a light and fast network that surpasses existing state-of-the-art networks.

cs.CV↗

arXiv2017

Less-forgetful Learning for Domain Expansion in Deep Neural Networks

Expanding the domain that deep neural network has already learned without accessing old domain data is a challenging task because deep neural networks forget previously learned information when learning new data from a new domain. In this paper, we propose a less-forgetful learning method for the domain expansion scenario. While existing domain adaptation techniques solely focused on adapting to new domains, the proposed technique focuses on working well with both old and new domains without needing to know whether the input is from the old or new domain. First, we present two naive approaches which will be problematic, then we provide a new method using two proposed properties for less-forgetful learning. Finally, we prove the effectiveness of our method through experiments on image classification tasks. All datasets used in the paper, will be released on our website for someone's follow-up study.

cs.LG↗

arXiv2017

Why Do Deep Neural Networks Still Not Recognize These Images?: A Qualitative Analysis on Failure Cases of ImageNet Classification

In a recent decade, ImageNet has become the most notable and powerful benchmark database in computer vision and machine learning community. As ImageNet has emerged as a representative benchmark for evaluating the performance of novel deep learning models, its evaluation tends to include only quantitative measures such as error rate, rather than qualitative analysis. Thus, there are few studies that analyze the failure cases of deep learning models in ImageNet, though there are numerous works analyzing the networks themselves and visualizing them. In this abstract, we qualitatively analyze the failure cases of ImageNet classification results from recent deep learning model, and categorize these cases according to the certain image patterns. Through this failure analysis, we believe that it can be discovered what the final challenges are in ImageNet database, which the current deep learning model is still vulnerable to.

cs.CV↗

arXiv2017

Deep Pyramidal Residual Networks

Deep convolutional neural networks (DCNNs) have shown remarkable performance in image classification tasks in recent years. Generally, deep neural network architectures are stacks consisting of a large number of convolutional layers, and they perform downsampling along the spatial dimension via pooling to reduce memory usage. Concurrently, the feature map dimension (i.e., the number of channels) is sharply increased at downsampling locations, which is essential to ensure effective performance because it increases the diversity of high-level attributes. This also applies to residual networks and is very closely related to their performance. In this research, instead of sharply increasing the feature map dimension at units that perform downsampling, we gradually increase the feature map dimension at all units to involve as many locations as possible. This design, which is discussed in depth together with our new insights, has proven to be an effective means of improving generalization ability. Furthermore, we propose a novel residual unit capable of further improving the classification accuracy with our new network architecture. Experiments on benchmark CIFAR-10, CIFAR-100, and ImageNet datasets have shown that our network architecture has superior generalization ability compared to the original residual networks. Code is available at https://github.com/jhkim89/PyramidNet}

cs.CV↗

arXiv2017

Active Convolution: Learning the Shape of Convolution for Image Classification

In recent years, deep learning has achieved great success in many computer vision applications. Convolutional neural networks (CNNs) have lately emerged as a major approach to image classification. Most research on CNNs thus far has focused on developing architectures such as the Inception and residual networks. The convolution layer is the core of the CNN, but few studies have addressed the convolution unit itself. In this paper, we introduce a convolution unit called the active convolution unit (ACU). A new convolution has no fixed shape, because of which we can define any form of convolution. Its shape can be learned through backpropagation during training. Our proposed unit has a few advantages. First, the ACU is a generalization of convolution; it can define not only all conventional convolutions, but also convolutions with fractional pixel coordinates. We can freely change the shape of the convolution, which provides greater freedom to form CNN structures. Second, the shape of the convolution is learned while training and there is no need to tune it by hand. Third, the ACU can learn better than a conventional unit, where we obtained the improvement simply by changing the conventional convolution to an ACU. We tested our proposed method on plain and residual networks, and the results showed significant improvement using our method on various datasets and architectures in comparison with the baseline.

cs.CV↗

arXiv2017

Mimicking Ensemble Learning with Deep Branched Networks

This paper proposes a branched residual network for image classification. It is known that high-level features of deep neural network are more representative than lower-level features. By sharing the low-level features, the network can allocate more memory to high-level features. The upper layers of our proposed network are branched, so that it mimics the ensemble learning. By mimicking ensemble learning with single network, we have achieved better performance on ImageNet classification task.

cs.CV↗

arXiv2016

Less-forgetting Learning in Deep Neural Networks

A catastrophic forgetting problem makes deep neural networks forget the previously learned information, when learning data collected in new environments, such as by different sensors or in different light conditions. This paper presents a new method for alleviating the catastrophic forgetting problem. Unlike previous research, our method does not use any information from the source domain. Surprisingly, our method is very effective to forget less of the information in the source domain, and we show the effectiveness of our method using several experiments. Furthermore, we observed that the forgetting problem occurs between mini-batches when performing general training processes using stochastic gradient descent methods, and this problem is one of the factors that degrades generalization performance of the network. We also try to solve this problem using the proposed method. Finally, we show our less-forgetting learning method is also helpful to improve the performance of deep neural networks in terms of recognition rates.

cs.LG↗

arXiv2016

HARRISON: A Benchmark on HAshtag Recommendation for Real-world Images in Social Networks

Simple, short, and compact hashtags cover a wide range of information on social networks. Although many works in the field of natural language processing (NLP) have demonstrated the importance of hashtag recommendation, hashtag recommendation for images has barely been studied. In this paper, we introduce the HARRISON dataset, a benchmark on hashtag recommendation for real world images in social networks. The HARRISON dataset is a realistic dataset, composed of 57,383 photos from Instagram and an average of 4.5 associated hashtags for each photo. To evaluate our dataset, we design a baseline framework consisting of visual feature extractor based on convolutional neural network (CNN) and multi-label classifier based on neural network. Based on this framework, two single feature-based models, object-based and scene-based model, and an integrated model of them are evaluated on the HARRISON dataset. Our dataset shows that hashtag recommendation task requires a wide and contextual understanding of the situation conveyed in the image. As far as we know, this work is the first vision-only attempt at hashtag recommendation for real world images in social networks. We expect this benchmark to accelerate the advancement of hashtag recommendation.

cs.CV↗

arXiv2016

Deep Saliency with Encoded Low level Distance Map and High Level Features

Recent advances in saliency detection have utilized deep learning to obtain high level features to detect salient regions in a scene. These advances have demonstrated superior results over previous works that utilize hand-crafted low level features for saliency detection. In this paper, we demonstrate that hand-crafted features can provide complementary information to enhance performance of saliency detection that utilizes only high level features. Our method utilizes both high level and low level features for saliency detection under a unified deep learning framework. The high level features are extracted using the VGG-net, and the low level features are compared with other parts of an image to form a low level distance map. The low level distance map is then encoded using a convolutional neural network(CNN) with multiple 1X1 convolutional and ReLU layers. We concatenate the encoded low level distance map and the high level features, and connect them to a fully connected neural network classifier to evaluate the saliency of a query region. Our experiments show that our method can further improve the performance of state-of-the-art deep learning-based saliency detection methods.

cs.CV↗

arXiv2015

Deep Temporal Appearance-Geometry Network for Facial Expression Recognition

Temporal information can provide useful features for recognizing facial expressions. However, to manually design useful features requires a lot of effort. In this paper, to reduce this effort, a deep learning technique which is regarded as a tool to automatically extract useful features from raw data, is adopted. Our deep network is based on two different models. The first deep network extracts temporal geometry features from temporal facial landmark points, while the other deep network extracts temporal appearance features from image sequences . These two models are combined in order to boost the performance of the facial expression recognition. Through several experiments, we showed that the two models cooperate with each other. As a result, we achieved superior performance to other state-of-the-art methods in CK+ and Oulu-CASIA databases. Furthermore, one of the main contributions of this paper is that our deep network catches the facial action points automatically.

cs.CV↗