相关论文: LightMC: A Dynamic and Efficient Multiclass Decomp…

Multi-task learning (MTL) aims at solving multiple related tasks simultaneously and has experienced rapid growth in recent years. However, MTL models often suffer from performance degeneration with negative transfer due to learning several…

Distributed learning methods have gained substantial momentum in recent years, with communication overhead often emerging as a critical bottleneck. Gradient compression techniques alleviate communication costs but involve an inherent…

This paper presents VisMCA, an interactive visual analytics system that supports deepening understanding in ML results, augmenting users' capabilities in correcting misclassification, and providing an analysis of underlying patterns, in…

To address the limitations of existing open-vocabulary object recognition methods, specifically high system complexity, substantial training costs, and limited generalization, this paper proposes a novel Open-Vocabulary Object Recognition…

Precise beam based measurement and correction of magnetic optics is essential for the successful operation of accelerators. The LOCO algorithm is a proven and reliable tool, which in some situations can be improved by using a broader class…

Continual learning (CL) in vision-language models (VLMs) faces significant challenges in improving task adaptation and avoiding catastrophic forgetting. Existing methods usually have heavy inference burden or rely on external knowledge,…

Vision-language models (VLMs), such as CLIP, have demonstrated exceptional generalization capabilities and can quickly adapt to downstream tasks through prompt fine-tuning. Unfortunately, in classification tasks involving non-training…

The balance between convergence and diversity is a key issue of evolutionary multi-objective optimization. The recently proposed stable matching-based selection provides a new perspective to handle this balance under the framework of…

Divide-and-conquer-based (DC-based) evolutionary algorithms (EAs) have achieved notable success in dealing with large-scale optimization problems (LSOPs). However, the appealing performance of this type of algorithms generally requires a…

We introduce a cutting-edge video compression framework tailored for the age of ubiquitous video data, uniquely designed to serve machine learning applications. Unlike traditional compression methods that prioritize human visual perception,…

Multi-view clustering (MVC), which aims to separate the multi-view data into distinct clusters in an unsupervised manner, is a fundamental yet challenging task. To enhance its applicability in real-world scenarios, this paper addresses a…

In ECOC framework, the ternary coding strategy is widely deployed in coding process. It relabels classes with {"-1,0,1" }, where -1/1 means to assign the corresponding classes to the negative/positive group, and label 0 leads to ignore the…

Video-LLMs face a fundamental tension in long-video reasoning: static, sparse frame sampling either dilutes evidence across task-irrelevant segments at significant cost or misses fine-grained temporal semantics altogether. We propose a…

This paper proposes an easy-to-use method for one-class classification: Repeated Element-wise Folding (REF). The algorithm consists of repeatedly standardizing and applying an element-wise folding operation on the one-class training data.…

In this paper, we propose a novel multi-view clustering model, named Dual-space Co-training Large-scale Multi-view Clustering (DSCMC). The main objective of our approach is to enhance the clustering performance by leveraging co-training in…

Multimodal learning enhances the performance of various machine learning tasks by leveraging complementary information across different modalities. However, existing methods often learn multimodal representations that retain substantial…

Existing studies typically investigate domain shift and category shift as independent problems, however, in real-world scenarios, the two types of shifts often occur simultaneously and interact, leading to significant degradation in…

Previous Online Knowledge Distillation (OKD) often carries out mutually exchanging probability distributions, but neglects the useful representational knowledge. We therefore propose Multi-view Contrastive Learning (MCL) for OKD to…

Entropy coding is widely used in typical learned image compression (LIC) that converts latents into a compact bitstream. However, entropy coding is typically sequential and becomes the coding latency bottleneck. To overcome it, we present…

This paper proposes an alternative algorithm for multichannel variational autoencoder (MVAE), a recently proposed multichannel source separation approach. While MVAE is notable in its impressive source separation performance, the…