Related papers: Eliminate Deviation with Deviation for Data Augmen…
Colorization is an ambiguous problem, with multiple viable colorizations for a single grey-level image. However, previous methods only produce the single most probable colorization. Our goal is to model the diversity intrinsic to the…
Recently, unsupervised image-to-image translation methods based on contrastive learning have achieved state-of-the-art results in many tasks. However, in the previous works, the negatives are sampled from the input image itself, which…
Deploying reinforcement learning policies in the real world requires adapting to time-varying environments. We study this problem in the contextual Markov Decision Process (cMDP) framework, where a family of environments is indexed by a…
Most advanced unsupervised anomaly detection (UAD) methods rely on modeling feature representations of frozen encoder networks pre-trained on large-scale datasets, e.g. ImageNet. However, the features extracted from the encoders that are…
In this paper, we focus on developing knowledge distillation (KD) for compact 3D detectors. We observe that off-the-shelf KD methods manifest their efficacy only when the teacher model and student counterpart share similar intermediate…
We present a new supervised image classification method applicable to a broad class of image deformation models. The method makes use of the previously described Radon Cumulative Distribution Transform (R-CDT) for image data, whose…
Knowledge Distillation (KD) is a promising approach for unsupervised Anomaly Detection (AD). However, the student network's over-generalization often diminishes the crucial representation differences between teacher and student in anomalous…
Discriminative features play an important role in image and object classification and also in other fields of research such as semi-supervised learning, fine-grained classification, out of distribution detection. Inspired by Linear…
Data augmentation is often used to enlarge datasets with synthetic samples generated in accordance with the underlying data distribution. To enable a wider range of augmentations, we explore negative data augmentation strategies (NDA)that…
In this paper, we introduce a novel data augmentation technique that combines the advantages of style augmentation and random erasing by selectively replacing image subregions with style-transferred patches. Our approach first applies a…
Recent advances in unsupervised domain adaptation (UDA) techniques have witnessed great success in cross-domain computer vision tasks, enhancing the generalization ability of data-driven deep learning architectures by bridging the domain…
Single-Domain Generalized Object Detection~(S-DGOD) aims to train an object detector on a single source domain while generalizing well to diverse unseen target domains, making it suitable for multimedia applications that involve various…
Existing domain generalization aims to learn a generalizable model to perform well even on unseen domains. For many real-world machine learning applications, the data distribution often shifts gradually along domain indices. For example, a…
Unsupervised domain adaptive person re-identification (Re-ID) methods alleviate the burden of data annotation through generating pseudo supervision messages. However, real-world Re-ID systems, with continuously accumulating data streams,…
Recent studies have used unsupervised domain adaptive object detection (UDAOD) methods to bridge the domain gap in remote sensing (RS) images. However, UDAOD methods typically assume that the source domain data can be accessed during the…
Detecting Out-of-Domain (OOD) or unknown intents from user queries is essential in a task-oriented dialog system. A key challenge of OOD detection is to learn discriminative semantic features. Traditional cross-entropy loss only focuses on…
RGB-D salient object detection (SOD) demonstrates its superiority on detecting in complex environments due to the additional depth information introduced in the data. Inevitably, an independent stream is introduced to extract features from…
The performance of a deep neural network is highly dependent on its training, and finding better local optimal solutions is the goal of many optimization algorithms. However, existing optimization algorithms show a preference for descent…
One pivot challenge for image anomaly (AD) detection is to learn discriminative information only from normal class training images. Most image reconstruction based AD methods rely on the discriminative capability of reconstruction error.…
Deep learning models learn to fit training data while they are highly expected to generalize well to testing data. Most works aim at finding such models by creatively designing architectures and fine-tuning parameters. To adapt to…