Related papers: FeatureFox: Sample-Efficient Panoptic Graph Segmen…

Learning pyramidal feature representations is crucial for recognizing object instances at different scales. Feature Pyramid Network (FPN) is the classic architecture to build a feature pyramid with high-level semantics throughout. However,…

Manually annotating complex scene point cloud datasets is both costly and error-prone. To reduce the reliance on labeled data, a new model called SnapshotNet is proposed as a self-supervised feature learning approach, which directly works…

Camouflaged object detection and segmentation is a new and challenging research topic in computer vision. There is a serious issue of lacking data on concealed objects such as camouflaged animals in natural scenes. In this paper, we address…

Graph anomaly detection (GAD) has garnered increasing attention in recent years, yet remains challenging due to two key factors: (1) label scarcity stemming from the high cost of annotations and (2) homophily disparity at node and class…

We propose a simple, fast, and flexible framework to generate simultaneously semantic and instance masks for panoptic segmentation. Our method, called PanoNet, incorporates a clean and natural structure design that tackles the problem…

We propose Panoptic Lifting, a novel approach for learning panoptic 3D volumetric representations from images of in-the-wild scenes. Once trained, our model can render color images together with 3D-consistent panoptic segmentation from…

Automated feature engineering (AFE) enables AI systems to autonomously construct high-utility representations from raw tabular data. However, existing AFE methods rely on statistical heuristics, yielding brittle features that fail under…

Recently, methods have been proposed for 3D open-vocabulary semantic segmentation. Such methods are able to segment scenes into arbitrary classes based on text descriptions provided during runtime. In this paper, we propose to the best of…

3D semantic segmentation is a fundamental building block for several scene understanding applications such as autonomous driving, robotics and AR/VR. Several state-of-the-art semantic segmentation models suffer from the part…

Semantic segmentation is fundamental to vision systems requiring pixel-level scene understanding, yet deploying it on resource-constrained devices demands efficient architectures. Although existing methods achieve real-time inference…

Effective deep feature extraction via feature-level fusion is crucial for multimodal object detection. However, previous studies often involve complex training processes that integrate modality-specific features by stacking multiple…

Recognizing 3D part instances from a 3D point cloud is crucial for 3D structure and scene understanding. Several learning-based approaches use semantic segmentation and instance center prediction as training tasks and fail to further…

Currently available face datasets mainly consist of a large number of high-quality and a small number of low-quality samples. As a result, a Face Recognition (FR) network fails to learn the distribution of low-quality samples since they are…

Current supervised methods for facial landmark detection require a large amount of training data and may suffer from overfitting to specific datasets due to the massive number of parameters. We introduce a semi-supervised method in which…

Feature selection (FS) is a fundamental challenge in machine learning, particularly for high-dimensional tabular data, where interpretability and computational efficiency are critical. Existing FS methods often cannot automatically detect…

Discriminative representation is essential to keep a unique identifier for each target in Multiple object tracking (MOT). Some recent MOT methods extract features of the bounding box region or the center point as identity embeddings.…

As forgery types continue to emerge consistently, Incremental Face Forgery Detection (IFFD) has become a crucial paradigm. However, existing methods typically rely on data replay or coarse binary supervision, which fails to explicitly…

Feature selection aims to identify the optimal feature subset for enhancing downstream models. Effective feature selection can remove redundant features, save computational resources, accelerate the model learning process, and improve the…

Few-shot learning (FSL) based on manifold regularization aims to improve the recognition capacity of novel objects with limited training samples by mixing two samples from different categories with a blending factor. However, this mixing…

Semantic mapping based on the supervised object detectors is sensitive to image distribution. In real-world environments, the object detection and segmentation performance can lead to a major drop, preventing the use of semantic mapping in…