相关论文: CEKD:Cross Ensemble Knowledge Distillation for Aug…

Knowledge Distillation (KD) has been validated as an effective model compression technique for learning compact object detectors. Existing state-of-the-art KD methods for object detection are mostly based on feature imitation. In this…

Traditional dataset distillation primarily focuses on image representation while often overlooking the important role of labels. In this study, we introduce Label-Augmented Dataset Distillation (LADD), a new dataset distillation framework…

Collecting fine-grained labels usually requires expert-level domain knowledge and is prohibitive to scale up. In this paper, we propose Attribute Mix, a data augmentation strategy at attribute level to expand the fine-grained samples. The…

Medical image annotation is constrained by privacy concerns and labor-intensive labeling, significantly limiting the performance and generalization of segmentation models. While mask-controllable diffusion models excel in synthesis, they…

Knowledge distillation has been used to transfer knowledge learned by a sophisticated model (teacher) to a simpler model (student). This technique is widely used to compress model complexity. However, in most applications the compressed…

Fine-grained image labels are desirable for many computer vision applications, such as visual search or mobile AI assistant. These applications rely on image classification models that can produce hundreds of thousands (e.g. 100K) of…

Continual learning, involving sequential training on diverse tasks, often faces catastrophic forgetting. While knowledge distillation-based approaches exhibit notable success in preventing forgetting, we pinpoint a limitation in their…

Ensembling is a successful technique to improve the performance of machine learning (ML) models. Conf-Ensemble is an adaptation to Boosting to create ensembles based on model confidence instead of model errors to better classify difficult…

Predicting future vehicle purchases among existing owners presents a critical challenge due to extreme class imbalance (<0.5% positive rate) and complex behavioral patterns. We propose REMEDI (Relative feature Enhanced Meta-learning with…

Remote sensing (RS) image scene classification task faces many challenges due to the interference from different characteristics of different geographical elements. To solve this problem, we propose a multi-branch ensemble network to…

Automated multi-label chest X-rays (CXR) image classification has achieved substantial progress in clinical diagnosis via utilizing sophisticated deep learning approaches. However, most deep models have high computational demands, which…

We propose a novel knowledge distillation approach, CustomKD, that effectively leverages large vision foundation models (LVFMs) to enhance the performance of edge models (e.g., MobileNetV3). Despite recent advancements in LVFMs, such as…

Recent advances in knowledge distillation have emphasized the importance of decoupling different knowledge components. While existing methods utilize momentum mechanisms to separate task-oriented and distillation gradients, they overlook…

Real-world datasets for deep learning frequently suffer from the co-occurring challenges of class imbalance and label noise, hindering model performance. While methods exist for each issue, effectively combining them is non-trivial, as…

In person re-identification (re-ID), the key task is feature representation, which is used to compute distance or similarity in prediction. Person re-ID achieves great improvement when deep learning methods are introduced to tackle this…

Most dataset distillation methods struggle to accommodate large-scale datasets due to their substantial computational and memory requirements. Recent research has begun to explore scalable disentanglement methods. However, there are still…

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…

Ensembling is a universally useful approach to boost the performance of machine learning models. However, individual models in an ensemble were traditionally trained independently in separate stages without information access about the…

Knowledge distillation (KD) is the de facto standard for compressing large-scale models into smaller ones. Prior works have explored ever more complex KD strategies involving different objective functions, teacher-ensembles, and weight…

We introduce a simple yet effective distillation framework that is able to boost the vanilla ResNet-50 to 80%+ Top-1 accuracy on ImageNet without tricks. We construct such a framework through analyzing the problems in the existing…