Search Results for author:
Found 23 papers, 16 papers with code
Efficient Test-Time Adaptation of Vision-Language Models
TDA works with a lightweight key-value cache that maintains a dynamic queue with few-shot pseudo labels as values and the corresponding test-sample features as keys.
BenchLMM: Benchmarking Cross-style Visual Capability of Large Multimodal Models
Large Multimodal Models (LMMs) such as GPT-4V and LLaVA have shown remarkable capabilities in visual reasoning with common image styles.
Ranked #1000000000 on
Visual Question Answering
on MS COCO
Noise-Tolerant Unsupervised Adapter for Vision-Language Models
NtUA works as a key-value cache that formulates visual features and predicted pseudo-labels of the few-shot unlabelled target samples as key-value pairs.
3D Semantic Segmentation in the Wild: Learning Generalized Models for Adverse-Condition Point Clouds
In addition, we design a domain randomization technique that alternatively randomizes the geometry styles of point clouds and aggregates their embeddings, ultimately leading to a generalizable model that can improve 3DSS under various adverse weather effectively.
PolarMix: A General Data Augmentation Technique for LiDAR Point Clouds
The first is scene-level swapping which exchanges point cloud sectors of two LiDAR scans that are cut along the azimuth axis.
Domain Adaptive Video Segmentation via Temporal Pseudo Supervision
Specifically, we design cross-frame pseudo labelling to provide pseudo supervision from previous video frames while learning from the augmented current video frames.
Unbiased Subclass Regularization for Semi-Supervised Semantic Segmentation
We build the balanced subclass distributions by clustering pixels of each original class into multiple subclasses of similar sizes, which provide class-balanced pseudo supervision to regularize the class-biased segmentation.
Unsupervised Point Cloud Representation Learning with Deep Neural Networks: A Survey
The convergence of point cloud and DNNs has led to many deep point cloud models, largely trained under the supervision of large-scale and densely-labelled point cloud data.
Model Adaptation: Historical Contrastive Learning for Unsupervised Domain Adaptation without Source Data
To this end, we design an innovative historical contrastive learning (HCL) technique that exploits historical source hypothesis to make up for the absence of source data in UMA.
Domain Adaptive Video Segmentation via Temporal Consistency Regularization
This paper presents DA-VSN, a domain adaptive video segmentation network that addresses domain gaps in videos by temporal consistency regularization (TCR) for consecutive frames of target-domain videos.
Transfer Learning from Synthetic to Real LiDAR Point Cloud for Semantic Segmentation
Extensive experiments show that SynLiDAR provides a high-quality data source for studying 3D transfer and the proposed PCT achieves superior point cloud translation consistently across the three setups.
RDA: Robust Domain Adaptation via Fourier Adversarial Attacking
With FAA-generated samples, the training can continue the 'random walk' and drift into an area with a flat loss landscape, leading to more robust domain adaptation.
Category Contrast for Unsupervised Domain Adaptation in Visual Tasks
In this work, we explore the idea of instance contrastive learning in unsupervised domain adaptation (UDA) and propose a novel Category Contrast technique (CaCo) that introduces semantic priors on top of instance discrimination for visual UDA tasks.
Semi-Supervised Domain Adaptation via Adaptive and Progressive Feature Alignment
We position the few labeled target samples as references that gauge the similarity between source and target features and guide adaptive inter-domain alignment for learning more similar source features.
MLAN: Multi-Level Adversarial Network for Domain Adaptive Semantic Segmentation
Recent progresses in domain adaptive semantic segmentation demonstrate the effectiveness of adversarial learning (AL) in unsupervised domain adaptation.
Cross-View Regularization for Domain Adaptive Panoptic Segmentation
The inter-task regularization exploits the complementary nature of instance segmentation and semantic segmentation and uses it as a constraint for better feature alignment across domains.
Ranked #2 on
Domain Adaptation
on Panoptic SYNTHIA-to-Mapillary
FSDR: Frequency Space Domain Randomization for Domain Generalization
It has been studied widely by domain randomization that transfers source images to different styles in spatial space for learning domain-agnostic features.
FPS-Net: A Convolutional Fusion Network for Large-Scale LiDAR Point Cloud Segmentation
Specifically, we design a residual dense block with multiple receptive fields as a building block in the encoder which preserves detailed information in each modality and learns hierarchical modality-specific and fused features effectively.
Ranked #23 on
3D Semantic Segmentation
on SemanticKITTI
Uncertainty-Aware Unsupervised Domain Adaptation in Object Detection
Specifically, we design an uncertainty metric that assesses the alignment of each sample and adjusts the strength of adversarial learning for well-aligned and poorly-aligned samples adaptively.
Contextual-Relation Consistent Domain Adaptation for Semantic Segmentation
Recent advances in unsupervised domain adaptation for semantic segmentation have shown great potentials to relieve the demand of expensive per-pixel annotations.
Unsupervised Domain Adaptation for Multispectral Pedestrian Detection
In this paper, we propose a novel unsupervised domain adaptation framework for multispectral pedestrian detection, by iteratively generating pseudo annotations and updating the parameters of our designed multispectral pedestrian detector on target domain.
Box-level Segmentation Supervised Deep Neural Networks for Accurate and Real-time Multispectral Pedestrian Detection
Effective fusion of complementary information captured by multi-modal sensors (visible and infrared cameras) enables robust pedestrian detection under various surveillance situations (e. g. daytime and nighttime).
Fusion of Multispectral Data Through Illumination-aware Deep Neural Networks for Pedestrian Detection
Moreover, we utilized illumination information together with multispectral data to generate more accurate semantic segmentation which are used to boost pedestrian detection accuracy.
