CODEN: combined optimization-based decomposition and learning-based enhancement network for Retinex-based brightness and contrast enhancement.

In this paper, we present a novel low-light image enhancement method by combining optimization-based decomposition and enhancement network for simultaneously enhancing brightness and contrast. The proposed method works in two steps including Retinex decomposition and illumination enhancement, and can be trained in an end-to-end manner. The first step separates the low-light image into illumination and reflectance components based on the Retinex model. Specifically, it performs model-based optimization followed by learning for edge-preserved illumination smoothing and detail-preserved reflectance denoising. In the second step, the illumination output from the first step, together with its gamma corrected and histogram equalized versions, serves as input to illumination enhancement network (IEN) including residual squeeze and excitation blocks (RSEBs). Extensive experiments prove that our method shows better performance compared with state-of-the-art low-light enhancement methods in the sense of both objective and subjective measures.

Photo-Realistic Image Dehazing and Verifying Networks via Complementary Adversarial Learning.

Physical model-based dehazing methods cannot, in general, avoid environmental variables and undesired artifacts such as non-collected illuminance, halo and saturation since it is difficult to accurately estimate the amount of the illuminance, light transmission and airlight. Furthermore, the haze model estimation process requires very high computational complexity. To solve this problem by directly estimating the radiance of the haze images, we present a novel dehazing and verifying network (DVNet). In the dehazing procedure, we enhanced the clean images by using a correction network (CNet), which uses the ground truth to learn the haze network. Haze images are then restored through a haze network (HNet). Furthermore, a verifying method verifies the error of both CNet and HNet using a self-supervised learning method. Finally, the proposed complementary adversarial learning method can produce results more naturally. Note that the proposed discriminator and generators (HNet & CNet) can be learned via an unpaired dataset. Overall, the proposed DVNet can generate a better dehazed result than state-of-the-art approaches under various hazy conditions. Experimental results show that the DVNet outperforms state-of-the-art dehazing methods in most cases.

Gated Dehazing Network via Least Square Adversarial Learning.

In a hazy environment, visibility is reduced and objects are difficult to identify. For this reason, many dehazing techniques have been proposed to remove the haze. Especially, in the case of the atmospheric scattering model estimation-based method, there is a problem of distortion when inaccurate models are estimated. We present a novel residual-based dehazing network model to overcome the performance limitation in an atmospheric scattering model-based method. More specifically, the proposed model adopted the gate fusion network that generates the dehazed results using a residual operator. To further reduce the divergence between the clean and dehazed images, the proposed discriminator distinguishes dehazed results and clean images, and then reduces the statistical difference via adversarial learning. To verify each element of the proposed model, we hierarchically performed the haze removal process in an ablation study. Experimental results show that the proposed method outperformed state-of-the-art approaches in terms of peak signal-to-noise ratio (PSNR), structural similarity index measure (SSIM), international commission on illumination cie delta e 2000 (CIEDE2000), and mean squared error (MSE). It also gives subjectively high-quality images without color distortion or undesired artifacts for both synthetic and real-world hazy images.

SNS-CF: Siamese Network with Spatially Semantic Correlation Features for Object Tracking.

Recent advances in object tracking based on deep Siamese networks shifted the attention away from correlation filters. However, the Siamese network alone does not have as high accuracy as state-of-the-art correlation filter-based trackers, whereas correlation filter-based trackers alone have a frame update problem. In this paper, we present a Siamese network with spatially semantic correlation features (SNS-CF) for accurate, robust object tracking. To deal with various types of features spread in many regions of the input image frame, the proposed SNS-CF consists of-(1) a Siamese feature extractor, (2) a spatially semantic feature extractor, and (3) an adaptive correlation filter. To the best of authors knowledge, the proposed SNS-CF is the first attempt to fuse the Siamese network and the correlation filter to provide high frame rate, real-time visual tracking with a favorable tracking performance to the state-of-the-art methods in multiple benchmarks.

Uniformity Attentive Learning-Based Siamese Network for Person Re-Identification.

Person re-identification (Re-ID) has a problem that makes learning difficult such as misalignment and occlusion. To solve these problems, it is important to focus on robust features in intra-class variation. Existing attention-based Re-ID methods focus only on common features without considering distinctive features. In this paper, we present a novel attentive learning-based Siamese network for person Re-ID. Unlike existing methods, we designed an attention module and attention loss using the properties of the Siamese network to concentrate attention on common and distinctive features. The attention module consists of channel attention to select important channels and encoder-decoder attention to observe the whole body shape. We modified the triplet loss into an attention loss, called uniformity loss. The uniformity loss generates a unique attention map, which focuses on both common and discriminative features. Extensive experiments show that the proposed network compares favorably to the state-of-the-art methods on three large-scale benchmarks including Market-1501, CUHK03 and DukeMTMC-ReID datasets.

Deep Binary Classification via Multi-Resolution Network and Stochastic Orthogonality for Subcompact Vehicle Recognition.

To encourage people to save energy, subcompact cars have several benefits of discount on parking or toll road charge. However, manual classification of the subcompact car is highly labor intensive. To solve this problem, automatic vehicle classification systems are good candidates. Since a general pattern-based classification technique can not successfully recognize the ambiguous features of a vehicle, we present a new multi-resolution convolutional neural network (CNN) and stochastic orthogonal learning method to train the network. We first extract the region of a bonnet in the vehicle image. Next, both extracted and input image are engaged to low and high resolution layers in the CNN model. The proposed network is then optimized based on stochastic orthogonality. We also built a novel subcompact vehicle dataset that will be open for a public use. Experimental results show that the proposed model outperforms state-of-the-art approaches in term of accuracy, which means that the proposed method can efficiently classify the ambiguous features between subcompact and non-subcompact vehicles.

Real-Time Visual Tracking with Variational Structure Attention Network.

Online training framework based on discriminative correlation filters for visual tracking has recently shown significant improvement in both accuracy and speed. However, correlation filter-base discriminative approaches have a common problem of tracking performance degradation when the local structure of a target is distorted by the boundary effect problem. The shape distortion of the target is mainly caused by the circulant structure in the Fourier domain processing, and it makes the correlation filter learn distorted training samples. In this paper, we present a structure-attention network to preserve the target structure from the structure distortion caused by the boundary effect. More specifically, we adopt a variational auto-encoder as a structure-attention network to make various and representative target structures. We also proposed two denoising criteria using a novel reconstruction loss for variational auto-encoding framework to capture more robust structures even under the boundary condition. Through the proposed structure-attention framework, discriminative correlation filters can learn robust structure information of targets during online training with an enhanced discriminating performance and adaptability. Experimental results on major visual tracking benchmark datasets show that the proposed method produces a better or comparable performance compared with the state-of-the-art tracking methods with a real-time processing speed of more than 80 frames per second.