Related papers: PHI-S: Distribution Balancing for Label-Free Multi…
Vision foundation models trained via multi-teacher distillation offer a promising path toward unified visual representations, yet the learning dynamics and data efficiency of such approaches remain underexplored. In this paper, we…
Model merging has emerged as a lightweight alternative to joint multi-task learning (MTL), yet the generalization properties of merged models remain largely unexplored. Establishing such theoretical guarantees is non-trivial, as the merging…
Recent years have witnessed dramatically improvements in the knowledge distillation, which can generate a compact student model for better efficiency while retaining the model effectiveness of the teacher model. Previous studies find that:…
Representation learning has been evolving from traditional supervised training to Contrastive Learning (CL) and Masked Image Modeling (MIM). Previous works have demonstrated their pros and cons in specific scenarios, i.e., CL and supervised…
Previous graph neural networks (GNNs) usually assume that the graph data is with clean labels for representation learning, but it is not true in real applications. In this paper, we propose a new multi-teacher distillation method based on…
In this paper, we study the problem of unifying knowledge from a set of classifiers with different architectures and target classes into a single classifier, given only a generic set of unlabelled data. We call this problem Unifying…
Recent recommender systems have shown remarkable performance by using an ensemble of heterogeneous models. However, it is exceedingly costly because it requires resources and inference latency proportional to the number of models, which…
Multilingual models have been widely used for cross-lingual transfer to low-resource languages. However, the performance on these languages is hindered by their underrepresentation in the pretraining data. To alleviate this problem, we…
Whole slide images, with their gigapixel-scale panoramas of tissue samples, are pivotal for precise disease diagnosis. However, their analysis is hindered by immense data size and scarce annotations. Existing MIL methods face challenges due…
Deep learning for Information Retrieval (IR) requires a large amount of high-quality query-document relevance labels, but such labels are inherently sparse. Label smoothing redistributes some observed probability mass over unobserved…
Transferring knowledge from a cross-encoder teacher via Knowledge Distillation (KD) has become a standard paradigm for training retrieval models. While existing studies have largely focused on mining hard negatives to improve…
Label assignment in object detection aims to assign targets, foreground or background, to sampled regions in an image. Unlike labeling for image classification, this problem is not well defined due to the object's bounding box. In this…
This study proposes a knowledge distillation algorithm based on large language models and feature alignment, aiming to effectively transfer the knowledge of large pre-trained models into lightweight student models, thereby reducing…
Recently, contrastive learning has achieved great results in self-supervised learning, where the main idea is to push two augmentations of an image (positive pairs) closer compared to other random images (negative pairs). We argue that not…
The development of computer vision solutions for gigapixel images in digital pathology is hampered by significant computational limitations due to the large size of whole slide images. In particular, digitizing biopsies at high resolutions…
Rehearsal is a critical component for class-incremental continual learning, yet it requires a substantial memory budget. Our work investigates whether we can significantly reduce this memory budget by leveraging unlabeled data from an…
Metric learning projects samples into an embedded space, where similarities and dissimilarities are quantified based on their learned representations. However, existing methods often rely on label-guided representation learning, where…
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…
Knowledge Distillation (KD) has been one of the most popu-lar methods to learn a compact model. However, it still suffers from highdemand in time and computational resources caused by sequential train-ing pipeline. Furthermore, the soft…
Label propagation aims to iteratively diffuse the label information from labeled examples to unlabeled examples over a similarity graph. Current label propagation algorithms cannot consistently yield satisfactory performance due to two…