相关论文: Granularity-Aware Transfer for Tree Instance Segme…

Knowledge distillation is initially introduced to utilize additional supervision from a single teacher model for the student model training. To boost the student performance, some recent variants attempt to exploit diverse knowledge sources…

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…

LiDAR-based semantic segmentation is a key component for autonomous mobile robots, yet large-scale annotation of LiDAR point clouds is prohibitively expensive and time-consuming. Although simulators can provide labeled synthetic data,…

Knowledge distillation is a popular machine learning technique that aims to transfer knowledge from a large 'teacher' network to a smaller 'student' network and improve the student's performance by training it to emulate the teacher. In…

Neural audio synthesis is an actively researched topic, having yielded a wide range of techniques that leverages machine learning architectures. Google Magenta elaborated a novel approach called Differential Digital Signal Processing (DDSP)…

Molecular dynamics simulations are an integral tool for studying the atomistic behavior of materials under diverse conditions. However, they can be computationally demanding in wall-clock time, especially for large systems, which limits the…

Data-Free Knowledge Distillation (KD) allows knowledge transfer from a trained neural network (teacher) to a more compact one (student) in the absence of original training data. Existing works use a validation set to monitor the accuracy of…

Generalization Performance of Deep Learning models trained using Empirical Risk Minimization can be improved significantly by using Data Augmentation strategies such as simple transformations, or using Mixed Samples. We attempt to…

Recent advances in generative diffusion models have shown a notable inherent understanding of image style and semantics. In this paper, we leverage the self-attention features from pretrained diffusion networks to transfer the visual…

Performance achievable by modern deep learning approaches are directly related to the amount of data used at training time. Unfortunately, the annotation process is notoriously tedious and expensive, especially for pixel-wise tasks like…

Deep learning models exhibit limited generalizability across different domains. Specifically, transferring knowledge from available entangled domain features(source/target domain) and categorical features to new unseen categorical features…

State-of-the-art face recognition networks are often computationally expensive and cannot be used for mobile applications. Training lightweight face recognition models also requires large identity-labeled datasets. Meanwhile, there are…

Knowledge distillation is considered as a training and compression strategy in which two neural networks, namely a teacher and a student, are coupled together during training. The teacher network is supposed to be a trustworthy predictor…

Recent research on knowledge distillation has increasingly focused on logit distillation because of its simplicity, effectiveness, and versatility in model compression. In this paper, we introduce Refined Logit Distillation (RLD) to address…

How to obtain a model with good interpretability and performance has always been an important research topic. In this paper, we propose rectified decision trees (ReDT), a knowledge distillation based decision trees rectification with high…

Recent advancements in text-to-image generation have inspired researchers to generate datasets tailored for perception models using generative models, which prove particularly valuable in scenarios where real-world data is limited. In this…

Contemporary segmentation methods are usually based on deep fully convolutional networks (FCNs). However, the layer-by-layer convolutions with a growing receptive field is not good at capturing long-range contexts such as lane markers in…

Gradient-based attention modeling has been used widely as a way to visualize and understand convolutional neural networks. However, exploiting these visual explanations during the training of generative adversarial networks (GANs) is an…

Synthetic image data generation represents a promising avenue for training deep learning models, particularly in the realm of transfer learning, where obtaining real images within a specific domain can be prohibitively expensive due to…

Recent studies attempted to utilize multilayer perceptrons (MLPs) to solve semisupervised node classification on graphs, by training a student MLP by knowledge distillation from a teacher graph neural network (GNN). While previous studies…