Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks247 from public data
- Contrastive Learning for Compact Single Image Dehazing926
This paper proposes a novel contrastive regularization (CR) built upon contrastive learning to exploit both the information of hazy images and clear images as negative and positive samples, respectively and develops a compact dehazing network based on autoencoder-like framework.
- 762
- 739
- On Unifying Multi-view Self-Representations for Clustering by Tensor Multi-rank Minimization505
The proposed method has achieved highly competent objective performance compared to several state-of-the-art multi-view clustering methods and its minimization problem can be efficiently solved with theoretical convergence guarantee and relatively low computational complexity.
- LatticeNet: Towards Lightweight Image Super-Resolution with Lattice Block367
A lightweight SR model, LatticeNet, is proposed, which uses series connection of LBs and the backward feature fusion, which can achieve superior accuracy on four available benchmark datasets against other state-of-the-art methods, while maintaining relatively low computation and memory requirements.
- 320
- Instance-Level Salient Object Segmentation297
This paper presents a salient instance segmentation method that produces a saliency mask with distinct object instance labels for an input image, and proposes a multiscale saliency refinement network, which generates high-quality salient region masks and salient object contours.
- 214
- PromptAD: Learning Prompts with only Normal Samples for Few-Shot Anomaly Detection212
A one-class prompt learning method for few-shot anomaly detection, termed PromptAD, which proposes semantic concatenation which can transpose normal prompts into anomaly prompts by concatenating normal prompts with anomaly suffixes, and introduces the concept of explicit anomaly margin.
- 212
- 206
- 184
- Farewell to Mutual Information: Variational Distillation for Cross-Modal Person Re-Identification172
A new strategy, Variational Self-Distillation (VSD), is presented, which provides a scalable, flexible and analytic solution to essentially fitting the mutual information but without explicitly estimating it, and highlights the need to rethink the way to estimate mutual information.
- Hyperspectral Image Restoration via Iteratively Regularized Weighted Schatten $p$ -Norm Minimization162
- 139
- Semi-Supervised Video Salient Object Detection Using Pseudo-Labels136
This paper presents an effective video saliency detector that consists of a spatial refinement network and a spatiotemporal module and proposes a novel method for generating pixel-level pseudo-labels from sparsely annotated frames.
- Weakly Supervised Salient Object Detection Using Image Labels135
This paper proposes to use the combination of a coarse salient object activation map from the classification network and saliency maps generated from unsupervised methods as pixel-level annotation, and develops a simple yet very effective algorithm to train fully convolutional networks for salient object detection supervised by these noisy annotations.
- Weakly Supervised Semantic Segmentation for Large-Scale Point Cloud125
An effective weakly supervised method containing two components to solve the problem of ineffective learning of network for large-scale point cloud semantic segmentation, and a sparse label propagation mechanism is proposed with the help of generated class prototypes which is used to measure the classification confidence of unlabeled point.
- NTIRE 2020 Challenge on NonHomogeneous Dehazing125
This paper reviews the NTIRE 2020 Challenge on Non-Homogeneous Dehazing of images (restoration of rich details in hazy image) and proposed solutions gauge the state-of-the-art in image dehazing.
- 121
- 116
- Dual Reweighting Domain Generalization for Face Presentation Attack Detection106
A novel Dual Reweighting Domain Generalization (DRDG) framework which iteratively reweights the relative importance between samples to further improve the generalization.
- 101
- Not All Pixels Are Matched99
A dense contrastive learning framework (DCLNet) is proposed, which performs pixel-to-pixel dense alignment acting on the intermediate representations, rather than the final deep feature, reducing the modality gap from a new perspective.
- 99
- NTIRE 2022 Challenge on Efficient Super-Resolution: Methods and Results94
The NTIRE 2022 challenge was to super-resolve an input image with a magnification factor of ×4 based on pairs of low and corresponding high resolution images and the aim was to design a network for single image super-resolution that achieved improvement of efficiency measured according to several metrics.
- 93
- 92
- 92
- 91
- 90
- 86
- Recent Advances of Foundation Language Models-based Continual Learning: A Survey85
This article delves into a comprehensive review, summarization, and classification of the existing literature on CL-based approaches applied to foundation language models, such as pre-trained language models, large language models, and vision-language models.
- Unveiling the Power of CLIP in Unsupervised Visible-Infrared Person Re-Identification85
A new prompt learning paradigm for unsupervised visible-infrared person re-identification (USL-VI-ReID) by taking full advantage of the visual-text representation ability from CLIP is proposed and a new memory-swapping contrastive learning is proposed.
- LAKe-Net: Topology-Aware Point Cloud Completion by Localizing Aligned Keypoints84
LAKe-Net is proposed, a novel topology-aware point cloud completion model by localizing aligned keypoints, with a novel Keypoints-Skeleton-Shape prediction manner, and experimental results show that the method achieves the state-of-the-art performance on point cloudpletion.
- 79
- 77
- Moving Object Detection Using Tensor-Based Low-Rank and Saliently Fused-Sparse Decomposition73
A new low-rank and sparse representation model for moving object detection that significantly outperforms the state-of-the-art approaches and works effectively on a wide range of complex scenarios.
- 72
- Boundary-Aware Geometric Encoding for Semantic Segmentation of Point Clouds69
A Boundary Prediction Module (BPM) to predict boundary points and a boundary-aware Geometric Encoding Module (GEM) is designed to encode geometric information and aggregate features with discrimination in a neighborhood, so that the local features belonging to different categories will not be polluted by each other.
- Adversarial Graph Representation Adaptation for Cross-Domain Facial Expression Recognition64
This work proposes a novel Adversarial Graph Representation Adaptation (AGRA) framework that unifies graph representation propagation with adversarial learning for cross-domain holistic-local feature co-adaptation and shows that the proposed AGRA framework achieves superior performance over previous state-of-the-art methods.
- Towards Compact Single Image Super-Resolution via Contrastive Self-distillation61
A novel contrastive self-distillation (CSD) framework to simultaneously compress and accelerate various off-the-shelf SR models to improve the quality of SR images and PSNR/SSIM via explicit knowledge transfer is proposed.
- Improved YOLOv5-based for small traffic sign detection under complex weather60
A small object detection algorithm based on improved YOLOv5s in complex weather, using the coordinate attention(CA) mechanism in the backbone, a light-weight yet effective module, embedding the location information of traffic signs into the channel attention to improve the feature extraction ability of the network.
- Omni-supervised Point Cloud Segmentation via Gradual Receptive Field Component Reasoning60
This paper brings the first omni-scale supervision method to point cloud segmentation via the proposed gradual Receptive Field Component Reasoning (RFCR) and brings new state-of-the-art performances for S3DIS as well as Semantic3D and ranks the 1st in the ScanNet benchmark among all the point-based methods.
- 60
- 59
- CLIP-Guided Federated Learning on Heterogeneity and Long-Tailed Data58
This paper uses CLIP to optimize the federated learning between server and client models under its vision-language supervision, and proposes the CLIP-guided FL (CLIP2FL) method, which achieves impressive performance and effectively deals with data heterogeneity and long-tail distribution.
- 55
- 55
- Image captioning via hierarchical attention mechanism and policy gradient optimization54
A hierarchical attention model is proposed by utilizing both of the global CNN features and the local object features for more effective feature representation and reasoning in image captioning and achieves state-of-the-art results on several important metrics in the MSCOCO dataset.
- 53
- EGEMM-TC52
This paper builds Emulated GEMM on Tensor Cores (EGEMM-TC), a lightweight emulation algorithm that exploits a set of Tensor Core kernel optimizations to achieve high performance and incorporates a hardware-aware analytic model to offer large flexibility for automatic performance tuning across various scientific computing workloads and input datasets.
- 51
- 48
- NTIRE 2020 Challenge on Image Demoireing: Methods and Results45
This paper reviews the Challenge on Image Demoireing that was part of the New Trends in Image Restoration and Enhancement (NTIRE) workshop, held in conjunction with CVPR 2020, and examines the current state-of-the-art in image and burst image demoireing problems.
- Patch Proposal Network for Fast Semantic Segmentation of High-Resolution Images44
A patch proposal network (PPN) is introduced, which adaptively distinguishes the critical patches from the trivial ones to fuse with the whole image for refining segmentation and achieves almost the best segmentation performance compared with the state-of-the-art segmentation methods.
- 43
- One-for-More: Continual Diffusion Model for Anomaly Detection41
An iterative singular value decomposition method based on the transitive property of linear representation, which consumes tiny memory and incurs almost no performance loss, and an anomaly-masked network to enhance the condition mechanism of the diffusion model are proposed.
- GEOcc: Geometrically Enhanced 3D Occupancy Network With Implicit-Explicit Depth Fusion and Contextual Self-Supervision41
GEOcc, a Geometric-Enhanced Occupancy network tailored for vision-only surround-view perception achieves State-of-the-Art performance on the Occ3D-nuScenes dataset with the least image resolution needed and the most weightless image backbone compared with current models, marking an improvement of 3.3% due to the proposed contributions.
- Cross-Domain and Cross-Modal Knowledge Distillation in Domain Adaptation for 3D Semantic Segmentation41
This paper designs the multi-modal style transfer to convert source image and point cloud to target style and proposes a novel model (Dual-Cross) that integrates Cross-Domain knowledge distillation (CDKD) and Cross-Modal Knowledge Distillation (CMKD), which significantly outperforms both uni- modal and cross-modAL state-of-the-art methods.
- Boosting Night-Time Scene Parsing With Learnable Frequency39
This paper proposes to exploit the image frequency distributions for night-time scene parsing with a Learnable Frequency Encoder (LFE) to model the relationship between different frequency coefficients to measure all frequency components dynamically and proposes a Spatial Frequency Fusion module (SFF) that fuses both spatial and frequency information to guide the extraction of spatial context features.
- 38
- 38
- Discriminative subspace learning with sparse representation view-based model for robust visual tracking38
A robust tracking algorithm to handle drifting problem and address the problem of learning maximum margin projection under the Spectral Regression (SR) which results in significant savings in computational time.
- Discrete-continuous Action Space Policy Gradient-based Attention for Image-Text Matching36
A novel attention scheme which projects the image and text embedding into a common space and optimises the attention weights directly towards the evaluation metrics, outperforming the previous approaches by a large margin.
- Facial Landmark Machines: A Backbone-Branches Architecture With Progressive Representation Learning35
This paper proposes a novel cascaded backbone-branches fully convolutional neural network (BB-FCN) for rapidly and accurately localizing facial landmarks in unconstrained and cluttered settings and confirms that high-quality facial landmarks localized with the proposed network can also improve the precision and recall of face detection.
- Image Understands Point Cloud: Weakly Supervised 3D Semantic Segmentation via Association Learning32
This paper designs a dual-branch network equipped with an active labeling strategy to maximize the power of tiny parts of labels and to directly realize 2D-to-3D knowledge transfer and establishes a cross-modal self-training framework, which iterates between parameter updating and pseudolabel estimation.
- 31
- 31
- 29
- 29
- 28
- 28
- 27
- 27
- 26
- 25
- 25
- 24
- 23
- 23
- 22
- 22
- 22
- 21
- 21
- SceneEncoder: Scene-Aware Semantic Segmentation of Point Clouds with A Learnable Scene Descriptor21
A SceneEncoder module to impose a scene-aware guidance to enhance the effect of global information, which predicts a scene descriptor, which learns to represent the categories of objects existing in the scene and directly guides the point-level semantic segmentation through filtering out categories not belonging to this scene.
- 21
- 21
- 20
- Optimization over Disentangled Encoding: Unsupervised Cross-Domain Point Cloud Completion via Occlusion Factor Manipulation20
This paper disentangle partial scans into three (domain, shape, and occlusion) factors to handle the output gap in cross-domain completion and introduces an optimization stage to maximize the consistency between completed shapes and input scans.
- Novelty Detection via Contrastive Learning with Negative Data Augmentation20
This work introduces a novel decoder-encoder framework that has significant superiority over cutting-edge novelty detectors and achieves new state-of-the-art results on various novelty detection benchmarks, e.g. CIFAR10 and DCASE.
- 19
- 18
- 18
- 18
- 18
- 17
- 17
- 16
- 15
- 15
- 14
- 14
- 14
- 13
- 13
- 13
- 13
- 13
- 12
- 12
- 12
- 12
- 12
- 12
- 12
- 12
- 12
- 12
- 11
- 11
- 11
- 10
- 10
- 10
- 10
- Global Meets Local: Effective Multi-Label Image Classification via Category-Aware Weak Supervision10
This paper builds a unified framework to perform effective noisy-proposal suppression and to interact between global and local features for robust feature learning, and proposes category-aware weak supervision to concentrate on non-existent categories so as to provide deterministic information for local feature learning.
- PIG: Prompt Images Guidance for Night-Time Scene Parsing9
This paper proposes a Night-Focused Network (NFNet) to learn night-specific features from both target domain images and prompt images and proposes two data augmentation strategies: the Prompt Mixture Strategy (PMS) and the Alternate Mask Strategy (AMS), aimed at mitigating the overfitting of the NFNet to a few prompt images.
- Rethinking the Metric in Few-shot Learning9
This paper investigates the contributions of different distance metrics, proposes an adaptive fusion scheme, and designs a few-shot classification framework AMTNet, including the AMM and the Global Adaptive Loss, to jointly optimize the few- shot task and auxiliary self-supervised task, making the embedding features more robust.
- 9
- 9
- 8
- 8
- 8
- 8
- 7
- 7
- 7
- 7
- 7
- 6
- 6
- Adjustable Memory-efficient Image Super-resolution via Individual Kernel Sparsity6
This work essentially provides a dynamic parameter reassignment scheme with a given resource budget for an off-the-shelf SR model and demonstrates that IKS imparts considerable sparsity with negligible effect on SR quality.
- Hierarchical Walking Transformer for Object Re-Identification6
A new hierarchical walking attention is presented, which provides a scalable, flexible, and interpretable sparsification strategy to reduce the complexity from quadratic to linear, and meanwhile evidently boost the performance.
- 6
- 6
- 6
- 6
- 6
- 6
- 5
- 5
- 5
- 5
- 5
- 5
- 5
- 5
- 5
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- 3
- PFDepth: Heterogeneous Pinhole-Fisheye Joint Depth Estimation via Distortion-aware Gaussian-Splatted Volumetric Fusion3
This is the first systematic study of heterogeneous pinhole-fisheye depth estimation, offering both technical novelty and valuable empirical insights, and sets a state-of-the-art performance on KITTI-360 and RealHet datasets over current mainstream depth networks.
- 3
- 3
- Learnable scene prior for point cloud semantic segmentation3
A SceneEncoder module to give scene-aware guidance to final segmentation results, which learns to predict a scene descriptor that represents the categories existing in the scene and uses it to filter out categories not belonging to this scene directly.
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- Glass Surface Detection Method Based on Visual Distortion1
The proposed method achieves improvements in IoU ranging from 0.83% to 4.73%, improvements in F -measure ranging from 1.40% to 6.60%, reductions in MAE ranging from 0.72% to 2.60%, and decreases in BER ranging from 0.58% to 2.66% across four benchmark datasets.
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- –
- –
- –
- –
- Control Study of a Fuzzy Super-Helical Sliding Mode Observer for Permanent Magnet Synchronous Motors–
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- Isolation and Integration: A Strong Pre-trained Model-Based Paradigm for Class-Incremental Learning–
This work proposes a brand-new stage-isolation based class incremental learning framework, which leverages parameter-efficient tuning technique to finetune the pre-trained model for each task, thus mitigating information interference and conflicts among tasks.
- –
- –
- –
- –
- –
- –
- –
- –
- –
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-13. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.