Related papers: Contrastive Bootstrapping for Label Refinement
In this work, we formulate \textbf{T}ext \textbf{C}lassification as a \textbf{M}atching problem between the text and the labels, and propose a simple yet effective framework named TCM. Compared with previous text classification approaches,…
Recently, representation learning with contrastive learning algorithms has been successfully applied to challenging unlabeled datasets. However, these methods are unable to distinguish important features from unimportant ones under simply…
We study approaches to improve fine-grained short answer Question Answering models by integrating coarse-grained data annotated for paragraph-level relevance and show that coarsely annotated data can bring significant performance gains.…
In this paper, we propose a one-stage online clustering method called Contrastive Clustering (CC) which explicitly performs the instance- and cluster-level contrastive learning. To be specific, for a given dataset, the positive and negative…
In real-world classification tasks, each class often comprises multiple finer-grained "subclasses." As the subclass labels are frequently unavailable, models trained using only the coarser-grained class labels often exhibit highly variable…
Contrastively trained vision-language models have achieved remarkable progress in vision and language representation learning, leading to state-of-the-art models for various downstream multimodal tasks. However, recent research has…
We develop techniques for refining representations for fine-grained classification and segmentation tasks in a self-supervised manner. We find that fine-tuning methods based on instance-discriminative contrastive learning are not as…
Fine-grained entity typing (FET) aims to deduce specific semantic types of the entity mentions in text. Modern methods for FET mainly focus on learning what a certain type looks like. And few works directly model the type differences, that…
Text style transfer is an important task in controllable language generation. Supervised approaches have pushed performance improvement on style-oriented rewriting such as formality conversion. However, challenges remain due to the scarcity…
Conventional object detectors rely on cross-entropy classification, which can be vulnerable to class imbalance and label noise. We propose CLIP-Joint-Detect, a simple and detector-agnostic framework that integrates CLIP-style contrastive…
Reranker models aim to re-rank the passages based on the semantics similarity between the given query and passages, which have recently received more attention due to the wide application of the Retrieval-Augmented Generation. Most previous…
Most self-supervised methods for representation learning leverage a cross-view consistency objective i.e., they maximize the representation similarity of a given image's augmented views. Recent work NNCLR goes beyond the cross-view paradigm…
While clustering is ubiquitously used across science and industry, uncertainty in cluster assignments is rarely quantified with rigorous guarantees. We propose a novel conformal inference framework for clustering that returns confidence…
This paper studies a text classification algorithm based on an improved Transformer to improve the performance and efficiency of the model in text classification tasks. Aiming at the shortcomings of the traditional Transformer model in…
Supervised contrastive learning (SCL) frameworks treat each class as independent and thus consider all classes to be equally important. This neglects the common scenario in which label hierarchy exists, where fine-grained classes under the…
Novel category discovery aims at adapting models trained on known categories to novel categories. Previous works only focus on the scenario where known and novel categories are of the same granularity. In this paper, we investigate a new…
Self-supervised learning has achieved a great success in the representation learning of visual and textual data. However, the current methods are mainly validated on the well-curated datasets, which do not exhibit the real-world long-tailed…
Deep neural networks have shown great success in representation learning. However, when learning with noisy labels (LNL), they can easily overfit and fail to generalize to new data. This paper introduces a simple and effective method, named…
This paper investigates negative sampling for contrastive learning in the context of audio-text retrieval. The strategy for negative sampling refers to selecting negatives (either audio clips or textual descriptions) from a pool of…
The success of deep learning methods in medical image segmentation tasks heavily depends on a large amount of labeled data to supervise the training. On the other hand, the annotation of biomedical images requires domain knowledge and can…