Related papers: Scene-Aware Feature Matching
Segment Anything Model (SAM) has revolutionized the way of segmentation. However, SAM's performance may decline when applied to tasks involving domains that differ from natural images. Nonetheless, by employing fine-tuning techniques, SAM…
High-resolution aerial images have a wide range of applications, such as military exploration, and urban planning. Semantic segmentation is a fundamental method extensively used in the analysis of high-resolution aerial images. However, the…
Sharpness-aware minimization (SAM) is a recently proposed method that minimizes the sharpness of the training loss of a neural network. While its generalization improvement is well-known and is the primary motivation, we uncover an…
Automatic emotion recognition is a hot topic with a wide range of applications. Much work has been done in the area of automatic emotion recognition in recent years. The focus has been mainly on using the characteristics of a person such as…
Image harmonization is a crucial technique in image composition that aims to seamlessly match the background by adjusting the foreground of composite images. Current methods adopt either global-level or pixel-level feature matching.…
Object detection is essential to safe autonomous or assisted driving. Previous works usually utilize RGB images or LiDAR point clouds to identify and localize multiple objects in self-driving. However, cameras tend to fail in bad driving…
Feature fusion, the combination of features from different layers or branches, is an omnipresent part of modern network architectures. It is often implemented via simple operations, such as summation or concatenation, but this might not be…
Image assessment aims to evaluate the quality and aesthetics of images and has been applied across various scenarios, such as natural and AIGC scenes. Existing methods mostly address these sub-tasks or scenes individually. While some works…
Most automatic matting methods try to separate the salient foreground from the background. However, the insufficient quantity and subjective bias of the current existing matting datasets make it difficult to fully explore the semantic…
Recently, scene text detection has been a challenging task. Texts with arbitrary shape or large aspect ratio are usually hard to detect. Previous segmentation-based methods can describe curve text more accurately but suffer from over…
Detecting and recognizing human action in videos with crowded scenes is a challenging problem due to the complex environment and diversity events. Prior works always fail to deal with this problem in two aspects: (1) lacking utilizing…
Segmenting anything is a ground-breaking step toward artificial general intelligence, and the Segment Anything Model (SAM) greatly fosters the foundation models for computer vision. We could not be more excited to probe the performance…
Attention--or attribution--maps methods are methods designed to highlight regions of the model's input that were discriminative for its predictions. However, different attention maps methods can highlight different regions of the input,…
Scene text recognition is a challenging task due to the complex backgrounds and diverse variations of text instances. In this paper, we propose a novel Semantic GAN and Balanced Attention Network (SGBANet) to recognize the texts in scene…
A large body of recent work targets semantically conditioned image generation. Most such methods focus on the narrower task of pose transfer and ignore the more challenging task of subject transfer that consists in not only transferring the…
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…
Convolutional neural networks (CNN) have enabled significant improvements in pedestrian detection owing to the strong representation ability of the CNN features. Recently, aggregating features from multiple layers of a CNN has been…
End-to-end scene text spotting, which unifies text detection and recognition within a single framework, has witnessed remarkable progress driven by deep learning advances. However, most existing approaches still suffer from incomplete mask…
In this paper, we focus on designing effective method for fast and accurate scene parsing. A common practice to improve the performance is to attain high resolution feature maps with strong semantic representation. Two strategies are widely…
In urban cities, visual information on and along roadways is likely to distract drivers and lead to missing traffic signs and other accident-prone (AP) features. To avoid accidents due to missing these visual cues, this paper proposes a…