相关论文: Self-Supervised Learning of Video-Induced Visual I…

This paper proposes a novel method of learning by predicting view assignments with support samples (PAWS). The method trains a model to minimize a consistency loss, which ensures that different views of the same unlabeled instance are…

Self-supervised approaches for video have shown impressive results in video understanding tasks. However, unlike early works that leverage temporal self-supervision, current state-of-the-art methods primarily rely on tasks from the image…

Self-supervised learning (SSL) methods have achieved remarkable success in learning image representations allowing invariances in them - but therefore discarding transformation information that some computer vision tasks actually require.…

The keep-growing content of Web images may be the next important data source to scale up deep neural networks, which recently obtained a great success in the ImageNet classification challenge and related tasks. This prospect, however, has…

In the past decade, image foundation models (IFMs) have achieved unprecedented progress. However, the potential of directly using IFMs for video self-supervised representation learning has largely been overlooked. In this study, we propose…

Current visual representation learning remains bifurcated: vision-language models (e.g., CLIP) excel at global semantic alignment but lack spatial precision, while self-supervised methods (e.g., MAE, DINO) capture intricate local structures…

Recent works in self-supervised learning have shown impressive results on single-object images, but they struggle to perform well on complex multi-object images as evidenced by their poor visual grounding. To demonstrate this concretely, we…

Many statistical learning models hold an assumption that the training data and the future unlabeled data are drawn from the same distribution. However, this assumption is difficult to fulfill in real-world scenarios and creates barriers in…

Recent advances in video-large language models (Video-LLMs) have led to significant progress in video understanding. Current preference optimization methods often rely on proprietary APIs or human-annotated captions to generate preference…

Multiview recognition has been well studied in the literature and achieves decent performance in object recognition and retrieval task. However, most previous works rely on supervised learning and some impractical underlying assumptions,…

Visual localization is the task of estimating camera pose in a known scene, which is an essential problem in robotics and computer vision. However, long-term visual localization is still a challenge due to the environmental appearance…

Recent single-image super-resolution (SISR) networks, which can adapt their network parameters to specific input images, have shown promising results by exploiting the information available within the input data as well as large external…

How can unlabeled video augment visual learning? Existing methods perform "slow" feature analysis, encouraging the representations of temporally close frames to exhibit only small differences. While this standard approach captures the fact…

Learning is an inherently continuous phenomenon. When humans learn a new task there is no explicit distinction between training and inference. As we learn a task, we keep learning about it while performing the task. What we learn and how we…

The recently advanced unsupervised learning approaches use the siamese-like framework to compare two "views" from the same image for learning representations. Making the two views distinctive is a core to guarantee that unsupervised methods…

Weakly supervised learning has emerged as an appealing alternative to alleviate the need for large labeled datasets in semantic segmentation. Most current approaches exploit class activation maps (CAMs), which can be generated from…

Vision Transformers (ViTs) have emerged as popular models in computer vision, demonstrating state-of-the-art performance across various tasks. This success typically follows a two-stage strategy involving pre-training on large-scale…

Self-supervised learning techniques have shown their abilities to learn meaningful feature representation. This is made possible by training a model on pretext tasks that only requires to find correlations between inputs or parts of inputs.…

Vision-language models such as CLIP are pretrained on large volumes of internet sourced image and text pairs, and have been shown to sometimes exhibit impressive zero- and low-shot image classification performance. However, due to their…

Recent single image unsupervised representation learning techniques show remarkable success on a variety of tasks. The basic principle in these works is instance discrimination: learning to differentiate between two augmented versions of…