Related papers: Training Domain Specific Models for Energy-Efficie…
While deep learning-based general object detection has made significant strides in recent years, the effectiveness and efficiency of small object detection remain unsatisfactory. This is primarily attributed not only to the limited…
We propose a unified cross-domain transfer learning framework that leverages knowledge from multiple heterogeneous medical imaging datasets to improve performance across segmentation, classification, and object detection tasks. Our approach…
Single-domain generalization is essential for object detection, particularly when training models on a single source domain and evaluating them on unseen target domains. Domain shifts, such as changes in weather, lighting, or scene…
Though deep learning based scene text detection has achieved great progress, well-trained detectors suffer from severe performance degradation for different domains. In general, a tremendous amount of data is indispensable to train the…
In instance-level detection tasks (e.g., object detection), reducing input resolution is an easy option to improve runtime efficiency. However, this option traditionally hurts the detection performance much. This paper focuses on boosting…
Two sampling strategies are investigated to enhance efficiency in training a deep learning object detection model. These sampling strategies are employed under the assumption of Lipschitz continuity of deep learning models. The first…
Image matching and classification methods, as well as synchronous location and mapping, are widely used on embedded and mobile devices. Their most resource-intensive part is the detection and description of the key points of the images. And…
As a general model compression paradigm, feature-based knowledge distillation allows the student model to learn expressive features from the teacher counterpart. In this paper, we mainly focus on designing an effective feature-distillation…
In this study, we investigated the application of the direct sampling method (DSM) to identify small dielectric objects in a limited-aperture inverse scattering problem. Unlike previous studies, we consider the bistatic measurement…
We present a scalable framework designed to craft efficient lightweight models for video object detection utilizing self-training and knowledge distillation techniques. We scrutinize methodologies for the ideal selection of training images…
Domain adaptation, a pivotal branch of transfer learning, aims to enhance the performance of machine learning models when deployed in target domains with distinct data distributions. This is particularly critical for object detection tasks,…
This project aims to develop a robust video surveillance system, which can segment videos into smaller clips based on the detection of activities. It uses CCTV footage, for example, to record only major events-like the appearance of a…
Single-domain generalization for object detection (S-DGOD) seeks to transfer learned representations from a single source domain to unseen target domains. While recent approaches have primarily focused on achieving feature invariance, they…
Cross domain object detection is a realistic and challenging task in the wild. It suffers from performance degradation due to large shift of data distributions and lack of instance-level annotations in the target domain. Existing approaches…
Though feature-alignment based Domain Adaptive Object Detection (DAOD) methods have achieved remarkable progress, they ignore the source bias issue, i.e., the detector tends to acquire more source-specific knowledge, impeding its…
In this research, we analyze the performance of Membership Inference Tests (MINT), focusing on determining whether given data were utilized during the training phase, specifically in the domain of object recognition. Within the area of…
In this work, we address the limitations of denoising diffusion models (DDMs) in image restoration tasks, particularly the shape and color distortions that can compromise image quality. While DDMs have demonstrated a promising performance…
In recent years, current mainstream feature masking distillation methods mainly function by reconstructing selectively masked regions of a student network from the feature maps of a teacher network. In these methods, attention mechanisms…
LiDAR-based 3D object detectors have been largely utilized in various applications, including autonomous vehicles or mobile robots. However, LiDAR-based detectors often fail to adapt well to target domains with different sensor…
Knowledge distillation learns a lightweight student model that mimics a cumbersome teacher. Existing methods regard the knowledge as the feature of each instance or their relations, which is the instance-level knowledge only from the…