Related papers: Lightweight Transducer Based on Frame-Level Criter…

To address the issues of limited samples, time-consuming feature design, and low accuracy in detection and classification of breast cancer pathological images, a breast cancer image classification model algorithm combining deep learning and…

This paper introduces a novel in-context learning (ICL) framework, inspired by large language models (LLMs), for soft-input soft-output channel equalization in coded multiple-input multiple-output (MIMO) systems. The proposed approach…

Sequence labeling is a fundamental problem in machine learning, natural language processing and many other fields. A classic approach to sequence labeling is linear chain conditional random fields (CRFs). When combined with neural network…

Labeled sequence transduction is a task of transforming one sequence into another sequence that satisfies desiderata specified by a set of labels. In this paper we propose multi-space variational encoder-decoders, a new model for labeled…

We propose the Limited Multi-Label (LML) projection layer as a new primitive operation for end-to-end learning systems. The LML layer provides a probabilistic way of modeling multi-label predictions limited to having exactly k labels. We…

With the booming of Large Language Models (LLMs), prompt-learning has become a promising method mainly researched in various research areas. Recently, many attempts based on prompt-learning have been made to improve the performance of text…

Convolution neural network models are widely used in image classification tasks. However, the running time of such models is so long that it is not the conforming to the strict real-time requirement of mobile devices. In order to optimize…

Few-shot learning (FSL) is popular due to its ability to adapt to novel classes. Compared with inductive few-shot learning, transductive models typically perform better as they leverage all samples of the query set. The two existing classes…

Weakly supervised semantic segmentation (WSSS) must learn dense masks from noisy, under-specified cues. We revisit the SegFormer decoder and show that three small, synergistic changes make weak supervision markedly more effective-without…

Network embedding is a highly effective method to learn low-dimensional node vector representations with original network structures being well preserved. However, existing network embedding algorithms are mostly developed for a single…

Supervised learning usually requires a large amount of labelled data. However, attaining ground-truth labels is costly for many tasks. Alternatively, weakly supervised methods learn with cheap weak signals that only approximately label some…

A fundamental question in applying In-Context Learning (ICL) for tabular data classification is how to determine the ideal number of demonstrations in the prompt. This work addresses this challenge by presenting an algorithm to…

Datasets with noisy labels are a common occurrence in practical applications of classification methods. We propose a simple probabilistic method for training deep classifiers under input-dependent (heteroscedastic) label noise. We assume an…

Inspired by the remarkable zero-shot generalization capacity of vision-language pre-trained model, we seek to leverage the supervision from CLIP model to alleviate the burden of data labeling. However, such supervision inevitably contains…

The acquisition of labels for supervised learning can be expensive. To improve the sample efficiency of neural network regression, we study active learning methods that adaptively select batches of unlabeled data for labeling. We present a…

The classification of short texts is a common subtask in Information Retrieval (IR). Recent advances in graph machine learning have led to interest in graph-based approaches for low resource scenarios, showing promise in such settings.…

We present Multi-Scale Label Dependence Relation Networks (MSDN), a novel approach to multi-label classification (MLC) using 1-dimensional convolution kernels to learn label dependencies at multi-scale. Modern multi-label classifiers have…

We consider learning to optimize a classification metric defined by a black-box function of the confusion matrix. Such black-box learning settings are ubiquitous, for example, when the learner only has query access to the metric of…

Vision-language models (VLMs) can learn high-quality representations from a large-scale training dataset of image-text pairs. Prompt learning is a popular approach to fine-tuning VLM to adapt them to downstream tasks. Despite the satisfying…

Here we study the problem of learning labels for large text corpora where each text can be assigned a variable number of labels. The problem might seem trivial when the label dimensionality is small and can be easily solved using a series…