Search Results for author:
Found 19 papers, 15 papers with code
Calib3D: Calibrating Model Preferences for Reliable 3D Scene Understanding
Safety-critical 3D scene understanding tasks necessitate not only accurate but also confident predictions from 3D perception models.
Self-Supervised Class-Agnostic Motion Prediction with Spatial and Temporal Consistency Regularizations
To this end, we explore the feasibility of self-supervised motion prediction with only unlabeled LiDAR point clouds.
Consistent Prompting for Rehearsal-Free Continual Learning
Specifically, all existing classifiers are exposed to prompt training, resulting in classifier consistency learning.
Using Left and Right Brains Together: Towards Vision and Language Planning
Large Language Models (LLMs) and Large Multi-modality Models (LMMs) have demonstrated remarkable decision masking capabilities on a variety of tasks.
Towards Few-shot Out-of-Distribution Detection
Out-of-distribution (OOD) detection is critical for ensuring the reliability of open-world intelligent systems.
CMDFusion: Bidirectional Fusion Network with Cross-modality Knowledge Distillation for LIDAR Semantic Segmentation
In this way, RGB images are not required during inference anymore since the 2D knowledge branch provides 2D information according to the 3D LIDAR input.
Segment Any Point Cloud Sequences by Distilling Vision Foundation Models
Recent advancements in vision foundation models (VFMs) have opened up new possibilities for versatile and efficient visual perception.
SAD: Segment Any RGBD
The Segment Anything Model (SAM) has demonstrated its effectiveness in segmenting any part of 2D RGB images.
Open Vocabulary Semantic Segmentation
Panoptic Segmentation
+1
Enlarging Instance-specific and Class-specific Information for Open-set Action Recognition
In this paper, we begin with analyzing the feature representation behavior in the open-set action recognition (OSAR) problem based on the information bottleneck (IB) theory, and propose to enlarge the instance-specific (IS) and class-specific (CS) information contained in the feature for better performance.
CLIP-guided Prototype Modulating for Few-shot Action Recognition
Learning from large-scale contrastive language-image pre-training like CLIP has shown remarkable success in a wide range of downstream tasks recently, but it is still under-explored on the challenging few-shot action recognition (FSAR) task.
The Devil is in the Wrongly-classified Samples: Towards Unified Open-set Recognition
Recently, Unified Open-set Recognition (UOSR) has been proposed to reject not only unknown samples but also known but wrongly classified samples, which tends to be more practical in real-world applications.
Learning a Condensed Frame for Memory-Efficient Video Class-Incremental Learning
The former is to reduce the memory cost by preserving only one condensed frame instead of the whole video, while the latter aims to compensate the lost spatio-temporal details in the Frame Condensing stage.
Attention Guided Network for Salient Object Detection in Optical Remote Sensing Images
Specifically, the position enhancement stage consists of a semantic attention module and a contextual attention module to accurately describe the approximate location of salient objects.
Open-world Semantic Segmentation for LIDAR Point Clouds
Current methods for LIDAR semantic segmentation are not robust enough for real-world applications, e. g., autonomous driving, since it is closed-set and static.
A lightweight multi-scale context network for salient object detection in optical remote sensing images
Meanwhile, in order to accurately detect complete salient objects in complex backgrounds, we design an attention-based pyramid feature aggregation mechanism for gradually aggregating and refining the salient regions from the multi-scale context extraction module.
Open-set 3D Object Detection
The first step is solved by the finding that unknown objects are often classified as known objects with low confidence, and we show that the Euclidean distance sum based on metric learning is a better confidence score than the naive softmax probability to differentiate unknown objects from known objects.
Deep Metric Learning for Open World Semantic Segmentation
Incrementally learning these OOD objects with few annotations is an ideal way to enlarge the knowledge base of the deep learning models.
MPI: Multi-receptive and Parallel Integration for Salient Object Detection
The semantic representation of deep features is essential for image context understanding, and effective fusion of features with different semantic representations can significantly improve the model's performance on salient object detection.
BORM: Bayesian Object Relation Model for Indoor Scene Recognition
First, we utilize an improved object model (IOM) as a baseline that enriches the object knowledge by introducing a scene parsing algorithm pretrained on the ADE20K dataset with rich object categories related to the indoor scene.
