相关论文: TSCM: A Teacher-Student Model for Vision Place Rec…

The outpouring of various pre-trained models empowers knowledge distillation by providing abundant teacher resources, but there lacks a developed mechanism to utilize these teachers adequately. With a massive model repository composed of…

Knowledge distillation from pretrained visual representation models offers an effective approach to improve small, task-specific production models. However, the effectiveness of such knowledge transfer drops significantly when distilling…

Advances in self-distillation have shown that when knowledge is distilled from a teacher to a student using the same deep learning (DL) architecture, the student performance can surpass the teacher particularly when the network is…

In recent years, there has been a great deal of research in developing end-to-end speech recognition models, which enable simplifying the traditional pipeline and achieving promising results. Despite their remarkable performance…

Representation knowledge distillation aims at transferring rich information from one model to another. Common approaches for representation distillation mainly focus on the direct minimization of distance metrics between the models'…

Large Foundation Models like Dust3r can produce high quality outputs such as pointmaps, camera intrinsics, and depth estimation, given stereo-image pairs as input. However, the application of these outputs on tasks like Visual Localization…

Knowledge Distillation (KD) aims at improving the performance of a low-capacity student model by inheriting knowledge from a high-capacity teacher model. Previous KD methods typically train a student by minimizing a task-related loss and…

Traditional visual place recognition (VPR) methods generally use frame-based cameras, which is easy to fail due to dramatic illumination changes or fast motions. In this paper, we propose an end-to-end visual place recognition network for…

Knowledge distillation enhances the performance of compact student networks by transferring knowledge from more powerful teacher networks without introducing additional parameters. In the feature space, local regions within an individual…

Recently, research efforts have been concentrated on revealing how pre-trained model makes a difference in neural network performance. Self-supervision and semi-supervised learning technologies have been extensively explored by the…

Recently, there have been significant improvements in the accuracy of CNN models for semantic segmentation. However, these models are often heavy and suffer from low inference speed, which limits their practical application. To address this…

Striking a balance between precision and efficiency presents a prominent challenge in the bird's-eye-view (BEV) 3D object detection. Although previous camera-based BEV methods achieved remarkable performance by incorporating long-term…

Visual Place Recognition (VPR) in mobile robotics enables robots to localize themselves by recognizing previously visited locations using visual data. While the reliability of VPR methods has been extensively studied under conditions such…

Knowledge Distillation (KD) utilizes training data as a transfer set to transfer knowledge from a complex network (Teacher) to a smaller network (Student). Several works have recently identified many scenarios where the training data may…

Visual Place Recognition (VPR) enables systems to identify previously visited locations within a map, a fundamental task for autonomous navigation. Prior works have developed VPR solutions using event cameras, which asynchronously measure…

Visual place recognition (VPR) is a robot's ability to determine whether a place was visited before using visual data. While conventional hand-crafted methods for VPR fail under extreme environmental appearance changes, those based on…

Visual Place Recognition (VPR) is an important component in both computer vision and robotics applications, thanks to its ability to determine whether a place has been visited and where specifically. A major challenge in VPR is to handle…

Knowledge distillation from large language models (LLMs) assumes that the teacher's output distribution is a high-quality training signal. On reasoning tasks, this assumption is frequently violated. A model's intermediate representations…

Robust visual place recognition (VPR) requires scene representations that are invariant to various environmental challenges such as seasonal changes and variations due to ambient lighting conditions during day and night. Moreover, a…

Human pose is a useful feature for fine-grained sports action understanding. However, pose estimators are often unreliable when run on sports video due to domain shift and factors such as motion blur and occlusions. This leads to poor…