Related papers: SEAL: Semantic-aware Single-image Sticker Personal…
Recently supervised learning rapidly develops in scene text segmentation. However, the lack of high-quality datasets and the high cost of pixel annotation greatly limit the development of them. Considering the well-performed few-shot…
In an augmented reality (AR) application, placing labels in a manner that is clear and readable without occluding the critical information from the real-world can be a challenging problem. This paper introduces a label placement technique…
Fine-tuning on task-specific data to boost downstream performance is a crucial step for leveraging Large Language Models (LLMs). However, previous studies have demonstrated that fine-tuning the models on several adversarial samples or even…
Person re-identification aims to match a person's identity across multiple camera streams. Deep neural networks have been successfully applied to the challenging person re-identification task. One remarkable bottleneck is that the existing…
Training deep networks for semantic segmentation requires large amounts of labeled training data, which presents a major challenge in practice, as labeling segmentation masks is a highly labor-intensive process. To address this issue, we…
The ability to efficiently search for images is essential for improving the user experiences across various products. Incorporating user feedback, via multi-modal inputs, to navigate visual search can help tailor retrieved results to…
Semantic segmentation has been continuously investigated in the last ten years, and majority of the established technologies are based on supervised models. In recent years, image-level weakly supervised semantic segmentation (WSSS),…
In text-to-image personalization, a timely and crucial challenge is the tendency of generated images overfitting to the biases present in the reference images. We initiate our study with a comprehensive categorization of the biases into…
Multi-label image recognition is a fundamental yet practical task because real-world images inherently possess multiple semantic labels. However, it is difficult to collect large-scale multi-label annotations due to the complexity of both…
This paper presents Scalable Semantic Transfer (SST), a novel training paradigm, to explore how to leverage the mutual benefits of the data from different label domains (i.e. various levels of label granularity) to train a powerful human…
Semi-supervised learning (SSL) for medical image segmentation is a challenging yet highly practical task, which reduces reliance on large-scale labeled dataset by leveraging unlabeled samples. Among SSL techniques, the weak-to-strong…
Multi-modal 3D semantic segmentation is vital for applications such as autonomous driving and virtual reality (VR). To effectively deploy these models in real-world scenarios, it is essential to employ cross-domain adaptation techniques…
Semantic segmentation has made tremendous progress in recent years. However, satisfying performance highly depends on a large number of pixel-level annotations. Therefore, in this paper, we focus on the semi-supervised segmentation problem…
The recent success of learning-based algorithms can be greatly attributed to the immense amount of annotated data used for training. Yet, many datasets lack annotations due to the high costs associated with labeling, resulting in degraded…
A common class of problems in remote sensing is scene classification, a fundamentally important task for natural hazards identification, geographic image retrieval, and environment monitoring. Recent developments in this field rely…
Fine-grained multi-label classification models have broad applications in e-commerce, such as visual based label predictions ranging from fashion attribute detection to brand recognition. One challenge to achieve satisfactory performance…
Stickers have become a popular form of visual communication, yet understanding their semantic relationships remains challenging due to their highly diverse and symbolic content. In this work, we formally {define the Sticker Semantic…
Sequential self-attention models usually rely on additive positional embeddings, which inject positional information into item representations at the input. In the absence of positional signals, the attention block is…
Training deep networks with limited labeled data while achieving a strong generalization ability is key in the quest to reduce human annotation efforts. This is the goal of semi-supervised learning, which exploits more widely available…
Since annotating pixel-level labels for semantic segmentation is laborious, leveraging synthetic data is an attractive solution. However, due to the domain gap between synthetic domain and real domain, it is challenging for a model trained…