Related papers: Multi-view Contrastive Learning for Online Knowled…
The teacher-free online Knowledge Distillation (KD) aims to train an ensemble of multiple student models collaboratively and distill knowledge from each other. Although existing online KD methods achieve desirable performance, they often…
Online Continual Learning (OCL) addresses the problem of training neural networks on a continuous data stream where multiple classification tasks emerge in sequence. In contrast to offline Continual Learning, data can be seen only once in…
We present a collaborative learning method called Mutual Contrastive Learning (MCL) for general visual representation learning. The core idea of MCL is to perform mutual interaction and transfer of contrastive distributions among a cohort…
Knowledge distillation (KD) has become an important technique for model compression and knowledge transfer. In this work, we first perform a comprehensive analysis of the knowledge transferred by different KD methods. We demonstrate that…
Self-supervised learning (SSL) has made remarkable progress in visual representation learning. Some studies combine SSL with knowledge distillation (SSL-KD) to boost the representation learning performance of small models. In this study, we…
Unsupervised out-of-distribution (OOD) Detection aims to separate the samples falling outside the distribution of training data without label information. Among numerous branches, contrastive learning has shown its excellent capability of…
Feature maps contain rich information about image intensity and spatial correlation. However, previous online knowledge distillation methods only utilize the class probabilities. Thus in this paper, we propose an online knowledge…
Multi-modal contrastive learning (MMCL) has recently garnered considerable interest due to its superior performance in visual tasks, achieved by embedding multi-modal data, such as visual-language pairs. However, there still lack…
Several methods of knowledge distillation have been developed for neural network compression. While they all use the KL divergence loss to align the soft outputs of the student model more closely with that of the teacher, the various…
In previous studies on knowledge distillation, the significance of logit distillation has frequently been overlooked. To revitalize logit distillation, we present a novel perspective by reconsidering its computation based on the semantic…
Knowledge distillation (KD) is an effective model compression technique where a compact student network is taught to mimic the behavior of a complex and highly trained teacher network. In contrast, Mutual Learning (ML) provides an…
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…
Knowledge distillation is a mainstream algorithm in model compression by transferring knowledge from the larger model (teacher) to the smaller model (student) to improve the performance of student. Despite many efforts, existing methods…
The gap in representations between image and video makes Image-to-Video Re-identification (I2V Re-ID) challenging, and recent works formulate this problem as a knowledge distillation (KD) process. In this paper, we propose a mutual…
In this paper, we propose a simple yet effective contrastive knowledge distillation framework that achieves sample-wise logit alignment while preserving semantic consistency. Conventional knowledge distillation approaches exhibit…
Advancements in technologies related to working with omics data require novel computation methods to fully leverage information and help develop a better understanding of human diseases. This paper studies the effects of introducing graph…
Unsupervised learning of disease subtypes from multi-omics data presents a significant opportunity for advancing personalized medicine. We introduce OmicsCL, a modular contrastive learning framework that jointly embeds heterogeneous omics…
This paper proposes a scalable and straightforward pre-training paradigm for efficient visual conceptual representation called occluded image contrastive learning (OCL). Our OCL approach is simple: we randomly mask patches to generate…
Knowledge distillation is an effective technique for pre-trained language model compression. However, existing methods only focus on the knowledge distribution among layers, which may cause the loss of fine-grained information in the…
Knowledge distillation (KD) is an effective model compression method that can transfer the internal capabilities of large language models (LLMs) to smaller ones. However, the multi-modal probability distribution predicted by teacher LLMs…