Related papers: A Unified Mixture-View Framework for Unsupervised …

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…

Most multi-view clustering methods are limited by shallow models without sound nonlinear information perception capability, or fail to effectively exploit complementary information hidden in different views. To tackle these issues, we…

This work presents improvements in monocular hand shape estimation by building on top of recent advances in unsupervised learning. We extend momentum contrastive learning and contribute a structured collection of hand images, well suited…

We present a comparative study on how and why contrastive learning (CL) and masked image modeling (MIM) differ in their representations and in their performance of downstream tasks. In particular, we demonstrate that self-supervised Vision…

Self-supervised learning enables networks to learn discriminative features from massive data itself. Most state-of-the-art methods maximize the similarity between two augmentations of one image based on contrastive learning. By utilizing…

Recent work has compared neural network representations via similarity-based analyses to improve model interpretation. The quality of a similarity measure is typically evaluated by its success in assigning a high score to representations…

As the real propagation environment becomes in creasingly complex and dynamic, millimeter wave beam prediction faces huge challenges. However, the powerful cross modal representation capability of vision-language model (VLM) provides a…

Recently, contrastive learning has been shown to be effective in improving pre-trained language models (PLM) to derive high-quality sentence representations. It aims to pull close positive examples to enhance the alignment while push apart…

Learning with complete or partial supervision is powerful but relies on ever-growing human annotation efforts. As a way to mitigate this serious problem, as well as to serve specific applications, unsupervised learning has emerged as an…

Multi-view representation learning is essential for many multi-view tasks, such as clustering and classification. However, there are two challenging problems plaguing the community: i)how to learn robust multi-view representation from mass…

Detecting objects accurately from a large or open vocabulary necessitates the vision-language alignment on region representations. However, learning such a region-text alignment by obtaining high-quality box annotations with text labels or…

Representation learning has been evolving from traditional supervised training to Contrastive Learning (CL) and Masked Image Modeling (MIM). Previous works have demonstrated their pros and cons in specific scenarios, i.e., CL and supervised…

Unsupervised representation learning with contrastive learning achieved great success. This line of methods duplicate each training batch to construct contrastive pairs, making each training batch and its augmented version forwarded…

The success of data mixing augmentations in image classification tasks has been well-received. However, these techniques cannot be readily applied to object detection due to challenges such as spatial misalignment, foreground/background…

We propose a self-supervised method to learn feature representations from videos. A standard approach in traditional self-supervised methods uses positive-negative data pairs to train with contrastive learning strategy. In such a case,…

In typical multimodal contrastive learning, such as CLIP, encoders produce one point in the latent representation space for each input. However, one-point representation has difficulty in capturing the relationship and the similarity…

Self-supervised learning algorithms based on instance discrimination train encoders to be invariant to pre-defined transformations of the same instance. While most methods treat different views of the same image as positives for a…

This paper studies the unsupervised embedding learning problem, which requires an effective similarity measurement between samples in low-dimensional embedding space. Motivated by the positive concentrated and negative separated properties…

Unsupervised person re-identification (ReID) aims at learning discriminative identity features without annotations. Recently, self-supervised contrastive learning has gained increasing attention for its effectiveness in unsupervised…

Contrastive learning methods train visual encoders by comparing views from one instance to others. Typically, the views created from one instance are set as positive, while views from other instances are negative. This binary instance…