Related papers: SELC: Self-Supervised Efficient Local Corresponden…
Semantic correspondence methods have advanced to obtaining high-quality correspondences employing complicated networks, aiming to maximize the model capacity. However, despite the performance improvements, they may remain constrained by the…
Vision-language contrastive learning frameworks such as CLIP enable learning representations from natural language supervision and provide strong zero-shot classification capabilities. However, due to the nature of the supervisory signal in…
The objective of this paper is self-supervised learning of feature embeddings that are suitable for matching correspondences along the videos, which we term correspondence flow. By leveraging the natural spatial-temporal coherence in…
Finding correspondences between semantically similar points across images and object instances is one of the everlasting challenges in computer vision. While large pre-trained vision models have recently been demonstrated as effective…
We propose a novel feature re-identification method for real-time visual-inertial SLAM. The front-end module of the state-of-the-art visual-inertial SLAM methods (e.g. visual feature extraction and matching schemes) relies on feature tracks…
Simultaneous mapping and localization (SLAM) in an real indoor environment is still a challenging task. Traditional SLAM approaches rely heavily on low-level geometric constraints like corners or lines, which may lead to tracking failure in…
Traditional simultaneous localization and mapping (SLAM) methods focus on improvement in the robot's localization under environment and sensor uncertainty. This paper, however, focuses on mitigating the need for exact localization of a…
We address the task of active learning in the context of semantic segmentation and show that self-consistency can be a powerful source of self-supervision to greatly improve the performance of a data-driven model with access to only a small…
Matching objects across partially overlapping camera views is crucial in multi-camera systems and requires a view-invariant feature extraction network. Training such a network with cycle-consistency circumvents the need for labor-intensive…
We present a novel method for efficiently producing semi-dense matches across images. Previous detector-free matcher LoFTR has shown remarkable matching capability in handling large-viewpoint change and texture-poor scenarios but suffers…
We study self-supervised video representation learning, which is a challenging task due to 1) lack of labels for explicit supervision; 2) unstructured and noisy visual information. Existing methods mainly use contrastive loss with video…
As advanced image manipulation techniques emerge, detecting the manipulation becomes increasingly important. Despite the success of recent learning-based approaches for image manipulation detection, they typically require expensive…
Dense correspondence across semantically related images has been extensively studied, but still faces two challenges: 1) large variations in appearance, scale and pose exist even for objects from the same category, and 2) labeling…
Few-shot learning (FSL) aims to learn novel visual categories from very few samples, which is a challenging problem in real-world applications. Many methods of few-shot classification work well on general images to learn global…
Zero-shot classification of image scenes which can recognize the image scenes that are not seen in the training stage holds great promise of lowering the dependence on large numbers of labeled samples. To address the zero-shot image scene…
Image-level weakly supervised semantic segmentation is a challenging problem that has been deeply studied in recent years. Most of advanced solutions exploit class activation map (CAM). However, CAMs can hardly serve as the object mask due…
Establishing dense correspondences across semantically similar images remains a challenging task due to the significant intra-class variations and background clutters. Traditionally, a supervised learning was used for training the models,…
Self-supervision has emerged as a propitious method for visual representation learning after the recent paradigm shift from handcrafted pretext tasks to instance-similarity based approaches. Most state-of-the-art methods enforce similarity…
Vision-language pre-training like CLIP has shown promising performance on various downstream tasks such as zero-shot image classification and image-text retrieval. Most of the existing CLIP-alike works usually adopt relatively large image…
We are interested in long-term deployments of autonomous robots to aid astronauts with maintenance and monitoring operations in settings such as the International Space Station. Unfortunately, such environments tend to be highly dynamic and…