Search

Weakly-supervised learning approaches have gained significant attention due to their ability to reduce the effort required for human annotations in training neural networks. This paper investigates a framework for weakly-supervised object localization, which aims to train a neural network capable of predicting both the object class and its location using only images and their image-level class labels. The proposed framework consists of a shared feature extractor, a classifier, and a localizer. The localizer predicts pixel-level class probabilities, while the classifier predicts the object class at the image level. Since image-level class labels are insufficient for training the localizer, weakly-supervised object localization methods often encounter challenges in accurately localizing the entire object region. To address this issue, the proposed method incorporates adversarial erasing and pseudo labels to improve localization accuracy. Specifically, novel losses are designed to utilize adversarially erased foreground features and adversarially erased feature maps, reducing dependence on the most discriminative region. Additionally, the proposed method employs pseudo labels to suppress activation values in the background while increasing them in the foreground. The proposed method is applied to two backbone networks (MobileNetV1 and InceptionV3) and is evaluated on three publicly available datasets (ILSVRC-2012, CUB-200-2011, and PASCAL VOC 2012). The experimental results demonstrate that the proposed method outperforms previous state-of-the-art methods across all evaluated metrics., Comment: 15 pages

This work addresses the task of long-term person re-identification. Typically, person re-identification assumes that people do not change their clothes, which limits its applications to short-term scenarios. To overcome this limitation, we investigate long-term person re-identification, which considers both clothes-changing and clothes-consistent scenarios. In this paper, we propose a novel framework that effectively learns and utilizes both global and local information. The proposed framework consists of three streams: global, local body part, and head streams. The global and head streams encode identity-relevant information from an entire image and a cropped image of the head region, respectively. Both streams encode the most distinct, less distinct, and average features using the combinations of adversarial erasing, max pooling, and average pooling. The local body part stream extracts identity-related information for each body part, allowing it to be compared with the same body part from another image. Since body part annotations are not available in re-identification datasets, pseudo-labels are generated using clustering. These labels are then utilized to train a body part segmentation head in the local body part stream. The proposed framework is trained by backpropagating the weighted summation of the identity classification loss, the pair-based loss, and the pseudo body part segmentation loss. To demonstrate the effectiveness of the proposed method, we conducted experiments on three publicly available datasets (Celeb-reID, PRCC, and VC-Clothes). The experimental results demonstrate that the proposed method outperforms the previous state-of-the-art method., Comment: 16 pages

This work addresses the task of class-incremental weakly supervised object localization (CI-WSOL). The goal is to incrementally learn object localization for novel classes using only image-level annotations while retaining the ability to localize previously learned classes. This task is important because annotating bounding boxes for every new incoming data is expensive, although object localization is crucial in various applications. To the best of our knowledge, we are the first to address this task. Thus, we first present a strong baseline method for CI-WSOL by adapting the strategies of class-incremental classifiers to mitigate catastrophic forgetting. These strategies include applying knowledge distillation, maintaining a small data set from previous tasks, and using cosine normalization. We then propose the feature drift compensation network to compensate for the effects of feature drifts on class scores and localization maps. Since updating network parameters to learn new tasks causes feature drifts, compensating for the final outputs is necessary. Finally, we evaluate our proposed method by conducting experiments on two publicly available datasets (ImageNet-100 and CUB-200). The experimental results demonstrate that the proposed method outperforms other baseline methods., Comment: ACM Multimedia 2023

Person re-identification is a problem of identifying individuals across non-overlapping cameras. Although remarkable progress has been made in the re-identification problem, it is still a challenging problem due to appearance variations of the same person as well as other people of similar appearance. Some prior works solved the issues by separating features of positive samples from features of negative ones. However, the performances of existing models considerably depend on the characteristics and statistics of the samples used for training. Thus, we propose a novel framework named sampling independent robust feature representation network (SirNet) that learns disentangled feature embedding from randomly chosen samples. A carefully designed sampling independent maximum discrepancy loss is introduced to model samples of the same person as a cluster. As a result, the proposed framework can generate additional hard negatives/positives using the learned features, which results in better discriminability from other identities. Extensive experimental results on large-scale benchmark datasets verify that the proposed model is more effective than prior state-of-the-art models., Comment: 11 pages, 7 figures, In IEEE Transactions on Image Processing 2022

Assessing image aesthetics is a challenging computer vision task. One reason is that aesthetic preference is highly subjective and may vary significantly among people for certain images. Thus, it is important to properly model and quantify such \textit{subjectivity}, but there has not been much effort to resolve this issue. In this paper, we propose a novel unified probabilistic framework that can model and quantify subjective aesthetic preference based on the subjective logic. In this framework, the rating distribution is modeled as a beta distribution, from which the probabilities of being definitely pleasing, being definitely unpleasing, and being uncertain can be obtained. We use the probability of being uncertain to define an intuitive metric of subjectivity. Furthermore, we present a method to learn deep neural networks for prediction of image aesthetics, which is shown to be effective in improving the performance of subjectivity prediction via experiments. We also present an application scenario where the framework is beneficial for aesthetics-based image recommendation., Comment: 8 pages, 6 figures

In this paper, we propose a dense depth estimation pipeline for multiview 360{\deg} images. The proposed pipeline leverages a spherical camera model that compensates for radial distortion in 360{\deg} images. The key contribution of this paper is the extension of a spherical camera model to multiview by introducing a translation scaling scheme. Moreover, we propose an effective dense depth estimation method by setting virtual depth and minimizing photonic reprojection error. We validate the performance of the proposed pipeline using the images of natural scenes as well as the synthesized dataset for quantitive evaluation. The experimental results verify that the proposed pipeline improves estimation accuracy compared to the current state-of-art dense depth estimation methods., Comment: 16 pages, 11 figures, Applied Intelligence

This work addresses the task of electric vehicle (EV) charging inlet detection for autonomous EV charging robots. Recently, automated EV charging systems have received huge attention to improve users' experience and to efficiently utilize charging infrastructures and parking lots. However, most related works have focused on system design, robot control, planning, and manipulation. Towards robust EV charging inlet detection, we propose a new dataset (EVCI dataset) and a novel data augmentation method that is based on image-to-image translation where typical image-to-image translation methods synthesize a new image in a different domain given an image. To the best of our knowledge, the EVCI dataset is the first EV charging inlet dataset. For the data augmentation method, we focus on being able to control synthesized images' captured environments (e.g., time, lighting) in an intuitive way. To achieve this, we first propose the environment guide vector that humans can intuitively interpret. We then propose a novel image-to-image translation network that translates a given image towards the environment described by the vector. Accordingly, it aims to synthesize a new image that has the same content as the given image while looking like captured in the provided environment by the environment guide vector. Lastly, we train a detection method using the augmented dataset. Through experiments on the EVCI dataset, we demonstrate that the proposed method outperforms the state-of-the-art methods. We also show that the proposed method is able to control synthesized images using an image and environment guide vectors., Comment: 8 pages

Color filter array is spatial multiplexing of pixel-sized filters placed over pixel detectors in camera sensors. The state-of-the-art lossless coding techniques of raw sensor data captured by such sensors leverage spatial or cross-color correlation using lifting schemes. In this paper, we propose a lifting-based lossless white balance algorithm. When applied to the raw sensor data, the spatial bandwidth of the implied chrominance signals decreases. We propose to use this white balance as a pre-processing step to lossless CFA subsampled image/video compression, improving the overall coding efficiency of the raw sensor data.

Our main objective is to develop a novel deep learning-based algorithm for automatic segmentation of prostate zone and to evaluate the proposed algorithm on an additional independent testing data in comparison with inter-reader consistency between two experts. With IRB approval and HIPAA compliance, we designed a novel convolutional neural network (CNN) for automatic segmentation of the prostatic transition zone (TZ) and peripheral zone (PZ) on T2-weighted (T2w) MRI. The total study cohort included 359 patients from two sources; 313 from a deidentified publicly available dataset (SPIE-AAPM-NCI PROSTATEX challenge) and 46 from a large U.S. tertiary referral center with 3T MRI (external testing dataset (ETD)). The TZ and PZ contours were manually annotated by research fellows, supervised by genitourinary (GU) radiologists. The model was developed using 250 patients and tested internally using the remaining 63 patients from the PROSTATEX (internal testing dataset (ITD)) and tested again (n=46) externally using the ETD. The Dice Similarity Coefficient (DSC) was used to evaluate the segmentation performance. DSCs for PZ and TZ were 0.74 and 0.86 in the ITD respectively. In the ETD, DSCs for PZ and TZ were 0.74 and 0.792, respectively. The inter-reader consistency (Expert 2 vs. Expert 1) were 0.71 (PZ) and 0.75 (TZ). This novel DL algorithm enabled automatic segmentation of PZ and TZ with high accuracy on both ITD and ETD without a performance difference for PZ and less than 10% TZ difference. In the ETD, the proposed method can be comparable to experts in the segmentation of prostate zones., Comment: Has been accepted by IEEE Access

In this work, we present the depth-adaptive deep neural network using a depth map for semantic segmentation. Typical deep neural networks receive inputs at the predetermined locations regardless of the distance from the camera. This fixed receptive field presents a challenge to generalize the features of objects at various distances in neural networks. Specifically, the predetermined receptive fields are too small at a short distance, and vice versa. To overcome this challenge, we develop a neural network which is able to adapt the receptive field not only for each layer but also for each neuron at the spatial location. To adjust the receptive field, we propose the depth-adaptive multiscale (DaM) convolution layer consisting of the adaptive perception neuron and the in-layer multiscale neuron. The adaptive perception neuron is to adjust the receptive field at each spatial location using the corresponding depth information. The in-layer multiscale neuron is to apply the different size of the receptive field at each feature space to learn features at multiple scales. The proposed DaM convolution is applied to two fully convolutional neural networks. We demonstrate the effectiveness of the proposed neural networks on the publicly available RGB-D dataset for semantic segmentation and the novel hand segmentation dataset for hand-object interaction. The experimental results show that the proposed method outperforms the state-of-the-art methods without any additional layers or pre/post-processing., Comment: IEEE Transactions on Multimedia, 2018

Real-time hand articulations tracking is important for many applications such as interacting with virtual / augmented reality devices or tablets. However, most of existing algorithms highly rely on expensive and high power-consuming GPUs to achieve real-time processing. Consequently, these systems are inappropriate for mobile and wearable devices. In this paper, we propose an efficient hand tracking system which does not require high performance GPUs. In our system, we track hand articulations by minimizing discrepancy between depth map from sensor and computer-generated hand model. We also initialize hand pose at each frame using finger detection and classification. Our contributions are: (a) propose adaptive hand model to consider different hand shapes of users without generating personalized hand model; (b) improve the highly efficient frame initialization for robust tracking and automatic initialization; (c) propose hierarchical random sampling of pixels from each depth map to improve tracking accuracy while limiting required computations. To the best of our knowledge, it is the first system that achieves both automatic hand model adjustment and real-time tracking without using GPUs., Comment: Advances in Visual Computing: 11th International Symposium on Visual Computing (ISVC'15)