Related papers: SynCo: Synthetic Hard Negatives for Contrastive Vi…

Contrastive self-supervised learning has attracted significant research attention recently. It learns effective visual representations from unlabeled data by embedding augmented views of the same image close to each other while pushing away…

Though offering amazing contextualized token-level representations, current pre-trained language models actually take less attention on acquiring sentence-level representation during its self-supervised pre-training. If self-supervised…

Deep learning with noisy labels is an interesting challenge in weakly supervised learning. Despite their significant learning capacity, CNNs have a tendency to overfit in the presence of samples with noisy labels. Alleviating this issue,…

Vision-language (VL) models often exhibit a limited understanding of complex expressions of visual objects (e.g., attributes, shapes, and their relations), given complex and diverse language queries. Traditional approaches attempt to…

Recent masked image modeling (MIM) has received much attention in self-supervised learning (SSL), which requires the target model to recover the masked part of the input image. Although MIM-based pre-training methods achieve new…

Speaker verification can be formulated as a representation learning task, where speaker-discriminative embeddings are extracted from utterances of variable lengths. Momentum Contrast (MoCo) is a recently proposed unsupervised representation…

Human observers can learn to recognize new categories of images from a handful of examples, yet doing so with artificial ones remains an open challenge. We hypothesize that data-efficient recognition is enabled by representations which make…

Contrastive learning (CL) has recently emerged as an effective approach to learning representation in a range of downstream tasks. Central to this approach is the selection of positive (similar) and negative (dissimilar) sets to provide the…

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…

Classifying and segmenting patterns from a limited number of examples is a significant challenge in remote sensing and earth observation due to the difficulty in acquiring accurately labeled data in large quantities. Previous studies have…

Contrastive representation learning has been recently proved to be very efficient for self-supervised training. These methods have been successfully used to train encoders which perform comparably to supervised training on downstream…

Heterogeneous graph neural networks (HGNNs) as an emerging technique have shown superior capacity of dealing with heterogeneous information network (HIN). However, most HGNNs follow a semi-supervised learning manner, which notably limits…

Contrastive self-supervised learning (CSL) based on instance discrimination typically attracts positive samples while repelling negatives to learn representations with pre-defined binary self-supervision. However, vanilla CSL is inadequate…

We present a new technique for learning visual-semantic embeddings for cross-modal retrieval. Inspired by hard negative mining, the use of hard negatives in structured prediction, and ranking loss functions, we introduce a simple change to…

Single-frame infrared small target (SIRST) detection aims to recognize small targets from clutter backgrounds. Recently, convolutional neural networks have achieved significant advantages in general object detection. With the development of…

We introduce a novel Pseudo-Negative Regularization (PNR) framework for effective continual self-supervised learning (CSSL). Our PNR leverages pseudo-negatives obtained through model-based augmentation in a way that newly learned…

Contrastive image-text models such as CLIP form the building blocks of many state-of-the-art systems. While they excel at recognizing common generic concepts, they still struggle on fine-grained entities which are rare, or even absent from…

This paper presents SimCLR: a simple framework for contrastive learning of visual representations. We simplify recently proposed contrastive self-supervised learning algorithms without requiring specialized architectures or a memory bank.…

Supervised contrastive learning (SupCon) is widely used to shape representations, but has seen limited targeted study for audio deepfake detection. Existing work typically combines contrastive terms with broader pipelines; however, the…

As large language models (LLMs) are rapidly advancing and achieving near-human capabilities on specific tasks, aligning them with human values is becoming more urgent. In scenarios where LLMs outperform humans, we face a weak-to-strong…