相关论文: Contrastive Knowledge Amalgamation for Unsupervise…

Continual Learning (CL) empowers AI models to continuously learn from sequential task streams. Recently, parameter-efficient fine-tuning (PEFT)-based CL methods have garnered increasing attention due to their superior performance. They…

Recently, contrastive learning has risen to be a promising approach for large-scale self-supervised learning. However, theoretical understanding of how it works is still unclear. In this paper, we propose a new guarantee on the downstream…

In this paper, we explore a new knowledge-amalgamation problem, termed Federated Selective Aggregation (FedSA). The goal of FedSA is to train a student model for a new task with the help of several decentralized teachers, whose pre-training…

Contrastive learning has achieved great success in self-supervised visual representation learning, but existing approaches mostly ignored spatial information which is often crucial for visual representation. This paper presents…

Recent empirical works have successfully used unlabeled data to learn feature representations that are broadly useful in downstream classification tasks. Several of these methods are reminiscent of the well-known word2vec embedding…

Recently, deep learning models have achieved great success in computer vision applications, relying on large-scale class-balanced datasets. However, imbalanced class distributions still limit the wide applicability of these models due to…

Recognizing objects in low-resolution images is a challenging task due to the lack of informative details. Recent studies have shown that knowledge distillation approaches can effectively transfer knowledge from a high-resolution teacher…

In practical applications of human pose estimation, low-resolution inputs frequently occur, and existing state-of-the-art models perform poorly with low-resolution images. This work focuses on boosting the performance of low-resolution…

Contrastive learning (CL) methods effectively learn data representations in a self-supervision manner, where the encoder contrasts each positive sample over multiple negative samples via a one-vs-many softmax cross-entropy loss. By…

General Continual Learning (GCL) aims at learning from non independent and identically distributed stream data without catastrophic forgetting of the old tasks that don't rely on task boundaries during both training and testing stages. We…

Contrastive learning, a dominant self-supervised technique, emphasizes similarity in representations between augmentations of the same input and dissimilarity for different ones. Although low contrastive loss often correlates with high…

Contrastive learning is a well-established paradigm in representation learning. The standard framework of contrastive learning minimizes the distance between "similar" instances and maximizes the distance between dissimilar ones in the…

Contrastive learning (CL) has emerged as a powerful technique for representation learning, with or without label supervision. However, supervised CL is prone to collapsing representations of subclasses within a class by not capturing all…

Contrastive Learning (CL) is a recent representation learning approach, which encourages inter-class separability and intra-class compactness in learned image representations. Since medical images often contain multiple semantic classes in…

Multi-view representation learning has developed rapidly over the past decades and has been applied in many fields. However, most previous works assumed that each view is complete and aligned. This leads to an inevitable deterioration in…

Knowledge graph embedding (KGE) aims at learning powerful representations to benefit various artificial intelligence applications. Meanwhile, contrastive learning has been widely leveraged in graph learning as an effective mechanism to…

In this work, we propose CLUDA, a simple, yet novel method for performing unsupervised domain adaptation (UDA) for semantic segmentation by incorporating contrastive losses into a student-teacher learning paradigm, that makes use of…

Knowledge distillation (KD) is an efficient framework for compressing large-scale pre-trained language models. Recent years have seen a surge of research aiming to improve KD by leveraging Contrastive Learning, Intermediate Layer…

Humans can recognize an image as an instance of a general concept, beyond simply identifying its objects and their relationships. In this paper, we investigate 1. The extent to which VLMs have this concept abstraction capacity, and 2.…

An increasing number of well-trained deep networks have been released online by researchers and developers, enabling the community to reuse them in a plug-and-play way without accessing the training annotations. However, due to the large…