Related papers: Patch-Level Contrasting without Patch Corresponden…
Learning scientific document representations can be substantially improved through contrastive learning objectives, where the challenge lies in creating positive and negative training samples that encode the desired similarity semantics.…
This paper focuses on two crucial issues in domain-adaptive lane detection, i.e., how to effectively learn discriminative features and transfer knowledge across domains. Existing lane detection methods usually exploit a pixel-wise…
We present a new self-supervised paradigm on point cloud sequence understanding. Inspired by the discriminative and generative self-supervised methods, we design two tasks, namely point cloud sequence based Contrastive Prediction and…
The pursuit of learning robust representations without human supervision is a longstanding challenge. The recent advancements in self-supervised contrastive learning approaches have demonstrated high performance across various…
The state-of-the-art unsupervised contrastive visual representation learning methods that have emerged recently (SimCLR, MoCo, SwAV) all make use of data augmentations in order to construct a pretext task of instant discrimination…
Recent progress in contrastive learning has revolutionized unsupervised representation learning. Concretely, multiple views (augmentations) from the same image are encouraged to map to the similar embeddings, while views from different…
CLIP (Contrastive Language-Image Pre-training) uses contrastive learning from noise image-text pairs to excel at recognizing a wide array of candidates, yet its focus on broad associations hinders the precision in distinguishing subtle…
The recent advances in representation learning inspire us to take on the challenging problem of unsupervised image classification tasks in a principled way. We propose ContraCluster, an unsupervised image classification method that combines…
Self-supervised representation learning based on Contrastive Learning (CL) has been the subject of much attention in recent years. This is due to the excellent results obtained on a variety of subsequent tasks (in particular…
Contrastive learning, a dominant self-supervised technique, emphasizes similarity in representations between augmentations of the same input and dissimilarity for different ones. Although low contrastive loss often correlates with high…
Video object detection is a challenging task because videos often suffer from image deterioration such as motion blur, occlusion, and deformable shapes, making it significantly more difficult than detecting objects in still images. Prior…
Diabetic retinopathy (DR) is a leading global cause of blindness. Early detection of hard exudates plays a crucial role in identifying DR, which aids in treating diabetes and preventing vision loss. However, the unique characteristics of…
This paper tackles the problem of motion deblurring of dynamic scenes. Although end-to-end fully convolutional designs have recently advanced the state-of-the-art in non-uniform motion deblurring, their performance-complexity trade-off is…
Current foundation models for 3D shapes excel at global tasks (retrieval, classification) but transfer poorly to local part-level reasoning. Recent approaches leverage vision and language foundation models to directly solve dense tasks…
Contrastive self-supervised learning (CSL) is an approach to learn useful representations by solving a pretext task that selects and compares anchor, negative and positive (APN) features from an unlabeled dataset. We present a conceptual…
This paper studies learning fair encoders in a self-supervised learning (SSL) setting, in which all data are unlabeled and only a small portion of them are annotated with sensitive attribute. Adversarial fair representation learning is well…
Contrastive Language-Image Pre-training (CLIP) has achieved success on multiple downstream tasks by aligning image and text modalities. However, the nature of global contrastive learning limits CLIP's ability to comprehend compositional…
Single-cell RNA sequencing (scRNA-seq) data is a potent tool for comprehending the "language of life" and can provide insights into various downstream biomedical tasks. Large-scale language models (LLMs) are starting to be used for cell…
Contrastive learning has emerged as an essential approach for self-supervised learning in visual representation learning. The central objective of contrastive learning is to maximize the similarities between two augmented versions of an…
We focus on a relatively unexplored learning paradigm known as {\em Online Unsupervised Continual Learning} (O-UCL), where an agent receives a non-stationary, unlabeled data stream and progressively learns to identify an increasing number…