Related papers: Regional Semantic Contrast and Aggregation for Wea…

Retrieval-augmented Generation (RAG) extends large language models (LLMs) with external knowledge but faces key challenges: restricted effective context length and redundancy in retrieved documents. Pure compression-based approaches reduce…

State-of-the-art methods for semantic segmentation are based on deep neural networks trained on large-scale labeled datasets. Acquiring such datasets would incur large annotation costs, especially for dense pixel-level prediction tasks like…

Weakly supervised semantic segmentation (WSSS), which aims to mine the object regions by merely using class-level labels, is a challenging task in computer vision. The current state-of-the-art CNN-based methods usually adopt…

A large gap exists between fully-supervised object detection and weakly-supervised object detection. To narrow this gap, some methods consider knowledge transfer from additional fully-supervised dataset. But these methods do not fully…

Contrastive learning has proven to be highly efficient and adaptable in shaping representation spaces across diverse modalities by pulling similar samples together and pushing dissimilar ones apart. However, two key limitations persist: (1)…

This paper describes a fast and accurate semantic image segmentation approach that encodes not only the discriminative features from deep neural networks, but also the high-order context compatibility among adjacent objects as well as low…

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…

Multi-label image classification, which can be categorized into label-dependency and region-based methods, is a challenging problem due to the complex underlying object layouts. Although region-based methods are less likely to encounter…

This work addresses weakly-supervised image semantic segmentation based on image-level class labels. One common approach to this task is to propagate the activation scores of Class Activation Maps (CAMs) using a random-walk mechanism in…

Weakly-supervised object localization methods tend to fail for object classes that consistently co-occur with the same background elements, e.g. trains on tracks. We propose a method to overcome these failures by adding a very small amount…

Weakly supervised semantic segmentation (WSSS) with image-level labels aims to achieve segmentation tasks without dense annotations. However, attributed to the frequent coupling of co-occurring objects and the limited supervision from…

Recently, significant improvement has been made on semantic object segmentation due to the development of deep convolutional neural networks (DCNNs). Training such a DCNN usually relies on a large number of images with pixel-level…

Context is essential for semantic segmentation. Due to the diverse shapes of objects and their complex layout in various scene images, the spatial scales and shapes of contexts for different objects have very large variation. It is thus…

Recently, learning open-vocabulary semantic segmentation from text supervision has achieved promising downstream performance. Nevertheless, current approaches encounter an alignment granularity gap owing to the absence of dense annotations,…

Keypoint detection and description is fundamental yet important in many vision applications. Most existing methods use detect-then-describe or detect-and-describe strategy to learn local features without considering their context…

Weakly supervised visual grounding (VG) aims to locate objects in images based on text descriptions. Despite significant progress, existing methods lack strong cross-modal reasoning to distinguish subtle semantic differences in text…

Autonomous off-road navigation faces challenges due to diverse, unstructured environments, requiring robust perception with both geometric and semantic understanding. However, scarce densely labeled semantic data limits generalization…

Discovering fine-grained categories from coarsely labeled data is a practical and challenging task, which can bridge the gap between the demand for fine-grained analysis and the high annotation cost. Previous works mainly focus on…

Thanks to the advantages of the friendly annotations and the satisfactory performance, Weakly-Supervised Semantic Segmentation (WSSS) approaches have been extensively studied. Recently, the single-stage WSSS was awakened to alleviate…

Deep neural networks suffer from the major limitation of catastrophic forgetting old tasks when learning new ones. In this paper we focus on class incremental continual learning in semantic segmentation, where new categories are made…