Related papers: Pseudo-Label Guided Real-World Image De-weathering…

This paper proposes a novel framework to reinforce classification models using language-guided generated counterfactual images. Deep learning classification models are often trained using datasets that mirror real-world scenarios. In this…

In most studies on learning-based image super-resolution (SR), the paired training dataset is created by downscaling high-resolution (HR) images with a predetermined operation (e.g., bicubic). However, these methods fail to super-resolve…

3D object detection aims to recover the 3D information of concerning objects and serves as the fundamental task of autonomous driving perception. Its performance greatly depends on the scale of labeled training data, yet it is costly to…

Recent advances in generative models have empowered impressive layered image generation, yet their success is largely confined to graphic design domains. The layering of in-the-wild images remains an underexplored problem, limiting…

Multi-view learning has become a popular research topic in recent years, but research on the cross-application of classic multi-label classification and multi-view learning is still in its early stages. In this paper, we focus on the…

Contrastive self-supervised learning has shown impressive results in learning visual representations from unlabeled images by enforcing invariance against different data augmentations. However, the learned representations are often…

This paper briefly reviews the connections between meta-learning and self-supervised learning. Meta-learning can be applied to improve model generalization capability and to construct general AI algorithms. Self-supervised learning utilizes…

Image restoration under adverse weather conditions (e.g., rain, snow and haze) is a fundamental computer vision problem and has important indications for various downstream applications. Different from early methods that are specially…

Pseudo-supervised learning methods have been shown to be effective for weakly supervised object localization tasks. However, the effectiveness depends on the powerful regularization ability of deep neural networks. Based on the assumption…

Recently, there has been substantial progress in image synthesis from semantic labelmaps. However, methods used for this task assume the availability of complete and unambiguous labelmaps, with instance boundaries of objects, and class…

Disentangling visual layers in real-world images is a persistent challenge in vision and graphics, as such layers often involve non-linear and globally coupled interactions, including shading, reflection, and perspective distortion. In this…

Existing weakly or semi-supervised semantic segmentation methods utilize image or box-level supervision to generate pseudo-labels for weakly labeled images. However, due to the lack of strong supervision, the generated pseudo-labels are…

Partially-supervised learning can be challenging for segmentation due to the lack of supervision for unlabeled structures, and the methods directly applying fully-supervised learning could lead to incompatibility, meaning ground truth is…

Real-world low-light images often suffer from complex degradations such as local overexposure, low brightness, noise, and uneven illumination. Supervised methods tend to overfit to specific scenarios, while unsupervised methods, though…

This work addresses the unsupervised adaptation of an existing object detector to a new target domain. We assume that a large number of unlabeled videos from this domain are readily available. We automatically obtain labels on the target…

Previous face inverse rendering methods often require synthetic data with ground truth and/or professional equipment like a lighting stage. However, a model trained on synthetic data or using pre-defined lighting priors is typically unable…

Semi-supervised learning frameworks usually adopt mutual learning approaches with multiple submodels to learn from different perspectives. To avoid transferring erroneous pseudo labels between these submodels, a high threshold is usually…

Many self-supervised learning (SSL) methods have been successful in learning semantically meaningful visual representations by solving pretext tasks. However, prior work in SSL focuses on tasks like object recognition or detection, which…

This paper investigates the effective utilization of unlabeled data for large-area cross-view geo-localization (CVGL), encompassing both unsupervised and semi-supervised settings. Common approaches to CVGL rely on ground-satellite image…

Assessing the blurriness of an object image is fundamentally important to improve the performance for object recognition and retrieval. The main challenge lies in the lack of abundant images with reliable labels and effective learning…