Related papers: Fast Multi-Resolution Transformer Fine-tuning for …
This research presents a fine-grained human evaluation to compare the Transformer and recurrent approaches to neural machine translation (MT), on the translation direction English-to-Chinese. To this end, we develop an error taxonomy…
This paper investigates an under-explored but important problem: given a collection of pre-trained neural networks, predicting their performance on each multi-modal task without fine-tuning them, such as image recognition, referring,…
Extreme multi-label classification (XMLC) refers to the task of tagging instances with small subsets of relevant labels coming from an extremely large set of all possible labels. Recently, XMLC has been widely applied to diverse web…
Adapter-based parameter-efficient transfer learning has achieved exciting results in vision-language models. Traditional adapter methods often require training or fine-tuning, facing challenges such as insufficient samples or resource…
Recent advancements in information retrieval have highlighted the potential of integrating visual and textual information, yet effective reranking for image-text documents remains challenging due to the modality gap and scarcity of aligned…
Multi-label classification (MLC) problems are becoming increasingly popular in the context of medical imaging. This has in part been driven by the fact that acquiring annotations for MLC is far less burdensome than for semantic segmentation…
We study multilabel classification of chest X-rays and present a simple, strong pipeline built on SE-ResNeXt101 $(32 \times 4d)$. The backbone is finetuned for 14 thoracic findings with a sigmoid head, trained using Multilabel Iterative…
Transformers have achieved great success in a wide variety of natural language processing (NLP) tasks due to the attention mechanism, which assigns an importance score for every word relative to other words in a sequence. However, these…
Medical imaging, particularly X-ray analysis, often involves detecting multiple conditions simultaneously within a single scan, making multi-label classification crucial for real-world clinical applications. We present the Medical X-ray…
Multi-label learning draws great interests in many real world applications. It is a highly costly task to assign many labels by the oracle for one instance. Meanwhile, it is also hard to build a good model without diagnosing discriminative…
Medical Image Hierarchical Multi-Label Classification (MI-HMC) is of paramount importance in modern healthcare, presenting two significant challenges: data imbalance and \textit{hierarchy constraint}. Existing solutions involve complex…
SemEval-2024 Task 8 introduces the challenge of identifying machine-generated texts from diverse Large Language Models (LLMs) in various languages and domains. The task comprises three subtasks: binary classification in monolingual and…
Multi-task learning in text classification leverages implicit correlations among related tasks to extract common features and yield performance gains. However, most previous works treat labels of each task as independent and meaningless…
Several methods have been proposed for classifying long textual documents using Transformers. However, there is a lack of consensus on a benchmark to enable a fair comparison among different approaches. In this paper, we provide a…
Many important classification problems in the real-world consist of a large number of closely related categories in a hierarchical structure or taxonomy. Hierarchical multi-label text classification (HMTC) with higher accuracy over large…
Mixup-based augmentation has been found to be effective for generalizing models during training, especially for Vision Transformers (ViTs) since they can easily overfit. However, previous mixup-based methods have an underlying prior…
Long-tailed multi-label visual recognition (LTML) task is a highly challenging task due to the label co-occurrence and imbalanced data distribution. In this work, we propose a unified framework for LTML, namely prompt tuning with…
We present systematic efforts in building long-context multilingual text representation model (TRM) and reranker from scratch for text retrieval. We first introduce a text encoder (base size) enhanced with RoPE and unpadding, pre-trained in…
Multi-label text classification (MLTC) aims to assign multiple labels to each sample in the dataset. The labels usually have internal correlations. However, traditional methods tend to ignore the correlations between labels. In order to…
Extreme multi-label text classification utilizes the label hierarchy to partition extreme labels into multiple label groups, turning the task into simple multi-group multi-label classification tasks. Current research encodes labels as a…