相关论文: Contrast Is All You Need

Large language models (LLMs) are trained on huge amounts of textual data, and concerns have been raised that the limits of such data may soon be reached. A potential solution is to train on synthetic data sampled from LLMs. In this work, we…

Classifying scanned documents is a challenging problem that involves image, layout, and text analysis for document understanding. Nevertheless, for certain benchmark datasets, notably RVL-CDIP, the state of the art is closing in to…

Contrastive learning has demonstrated great effectiveness in representation learning especially for image classification tasks. However, there is still a shortage in the studies targeting regression tasks, and more specifically applications…

The use of pretrained deep neural networks represents an attractive way to achieve strong results with few data available. When specialized in dense problems such as object detection, learning local rather than global information in images…

Graphs are present in many real-world applications, such as financial fraud detection, commercial recommendation, and social network analysis. But given the high cost of graph annotation or labeling, we face a severe graph label-scarcity…

Multimodal models, such as the Contrastive Language-Image Pre-training (CLIP) model, have demonstrated remarkable success in aligning visual and linguistic representations. However, these models exhibit limitations when applied to…

Low-light images often suffer from limited visibility and multiple types of degradation, rendering low-light image enhancement (LIE) a non-trivial task. Some endeavors have been recently made to enhance low-light images using convolutional…

A lot of recent advances in unsupervised feature learning are based on designing features which are invariant under semantic data augmentations. A common way to do this is contrastive learning, which uses positive and negative samples. Some…

Using responses generated by high-performing large language models (LLMs) for instruction tuning has become a widely adopted approach. However, the existing literature overlooks a property of LLM-generated responses: they conflate world…

The learning objective of vision-language approach of CLIP does not effectively account for the noisy many-to-many correspondences found in web-harvested image captioning datasets, which contributes to its compute and data inefficiency. To…

In this paper, we present CLCC, a novel contrastive learning framework for color constancy. Contrastive learning has been applied for learning high-quality visual representations for image classification. One key aspect to yield useful…

The goal of a classification model is to assign the correct labels to data. In most cases, this data is not fully described by the given set of labels. Often a rich set of meaningful concepts exist in the domain that can much more precisely…

Trained classification models can unintentionally lead to biased representations and predictions, which can reinforce societal preconceptions and stereotypes. Existing debiasing methods for classification models, such as adversarial…

Self-supervised instance discrimination is an effective contrastive pretext task to learn feature representations and address limited medical image annotations. The idea is to make features of transformed versions of the same images similar…

Few-shot learning aims to train models that can be generalized to novel classes with only a few samples. Recently, a line of works are proposed to enhance few-shot learning with accessible semantic information from class names. However,…

Collaborative learning enables distributed clients to learn a shared model for prediction while keeping the training data local on each client. However, existing collaborative learning methods require fully-labeled data for training, which…

Feature quality is paramount for classification performance, particularly in few-shot scenarios. Contrastive learning, a widely adopted technique for enhancing feature quality, leverages sample relations to extract intrinsic features that…

The goal of meta-learning is to learn to adapt to a new task with only a few labeled examples. To tackle this problem in NLP, we propose $\textit{in-context tuning}$, which recasts adaptation and prediction as a simple sequence prediction…

To improve the detection accuracy and generalization of steganalysis, this paper proposes the Steganalysis Contrastive Framework (SCF) based on contrastive learning. The SCF improves the feature representation of steganalysis by maximizing…

Noise contrastive learning is a popular technique for unsupervised representation learning. In this approach, a representation is obtained via reduction to supervised learning, where given a notion of semantic similarity, the learner tries…