Related papers: Evolving Knowledge Mining for Class Incremental Se…
To facilitate the evolution of edge intelligence in ever-changing environments, we study on-device incremental learning constrained in limited computation resource in this paper. Current on-device training methods just focus on efficient…
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…
A learning management system streamlines the management of the teaching process in a centralized place, recording, tracking, and reporting the delivery of educational courses and student performance. Educational knowledge discovery from…
Conventional machine learning methods are predominantly designed to predict outcomes based on a single data type. However, practical applications may encompass data of diverse types, such as text, images, and audio. We introduce…
The state-of-the-art recommendation systems have shifted the attention to efficient recommendation, e.g., on-device recommendation, under memory constraints. To this end, the existing methods either focused on the lightweight embeddings for…
Deep Research agents predominantly optimize search policies to maximize retrieval probability. However, we identify a critical bottleneck: the retrieval-utilization gap, where models fail to use gold evidence even after it is retrieved, due…
Fine-tuning pre-trained language models, particularly large language models, demands extensive computing resources and can result in varying performance outcomes across different domains and datasets. This paper examines the approach of…
In recent years, deep neural networks have achieved remarkable accuracy in computer vision tasks. With inference time being a crucial factor, particularly in dense prediction tasks such as semantic segmentation, knowledge distillation has…
Achieving backward compatibility when rolling out new models can highly reduce costs or even bypass feature re-encoding of existing gallery images for in-production visual retrieval systems. Previous related works usually leverage losses…
Modern semantic segmentation frameworks usually combine low-level and high-level features from pre-trained backbone convolutional models to boost performance. In this paper, we first point out that a simple fusion of low-level and…
Class Incremental Semantic Segmentation~(CISS), within Incremental Learning for semantic segmentation, targets segmenting new categories while reducing the catastrophic forgetting on the old categories.Besides, background shifting, where…
Incremental Learning is well known machine learning approach wherein the weights of the learned model are dynamically and gradually updated to generalize on new unseen data without forgetting the existing knowledge. Incremental learning…
Non-exemplar class incremental learning aims to learn both the new and old tasks without accessing any training data from the past. This strict restriction enlarges the difficulty of alleviating catastrophic forgetting since all techniques…
Few-Shot Class-Incremental Learning (FSCIL) faces a critical challenge: balancing the retention of prior knowledge with the acquisition of new classes. Existing methods either freeze the backbone to prevent catastrophic forgetting,…
Both accuracy and efficiency are of significant importance to the task of semantic segmentation. Existing deep FCNs suffer from heavy computations due to a series of high-resolution feature maps for preserving the detailed knowledge in…
Multi-teacher knowledge distillation (KD), a more effective technique than traditional single-teacher methods, transfers knowledge from expert teachers to a compact student model using logit or feature matching. However, most existing…
Class incremental learning consists in training discriminative models to classify an increasing number of classes over time. However, doing so using only the newly added class data leads to the known problem of catastrophic forgetting of…
Commonsense knowledge (CSK) about concepts and their properties is useful for AI applications such as robust chatbots. Prior works like ConceptNet, TupleKB and others compiled large CSK collections, but are restricted in their…
Efficient deployment of deep neural networks on resource-constrained devices demands advanced compression techniques that preserve accuracy and interoperability. This paper proposes a machine learning framework that augments Knowledge…
Large-scale contrastive learning models can learn very informative sentence embeddings, but are hard to serve online due to the huge model size. Therefore, they often play the role of "teacher", transferring abilities to small "student"…