Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileAcademic lineage
Possible advisorsa guess from early papers, not confirmed
- Ali BorjiSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works128 from public data
- Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions5,324
The Pyramid Vision Transformer (PVT) is introduced, which overcomes the difficulties of porting Transformer to various dense prediction tasks and is validated through extensive experiments, showing that it boosts the performance of many downstream tasks, including object detection, instance and semantic segmentation.
- PVT v2: Improved baselines with pyramid vision transformer2,673
This work improves the original Pyramid Vision Transformer (PVT v1) by adding three designs: a linear complexity attention layer, an overlapping patch embedding, and a convolutional feed-forward network to reduce the computational complexity of PVT v1 to linearity and provide significant improvements on fundamental vision tasks.
- Structure-Measure: A New Way to Evaluate Foreground Maps1,970
A novel, efficient, and easy to calculate measure known as S-measure (structural measure) to evaluate foreground maps, which simultaneously evaluates region-aware and object-aware structural similarity between a foreground map and a ground-truth map.
- PraNet: Parallel Reverse Attention Network for Polyp Segmentation1,966
Quantitative and qualitative evaluations on five challenging datasets across six metrics show that the PraNet improves the segmentation accuracy significantly, and presents a number of advantages in terms of generalizability, and real-time segmentation efficiency.
- 1,938
- Enhanced-alignment Measure for Binary Foreground Map Evaluation1,716
This paper takes a detailed look at current binary FM evaluation measures and proposes a novel and effective E-measure (Enhanced-alignment measure), jointly capturing image-level statistics and local pixel matching information, which demonstrates the superiority of this measure over the available measures on 4 popular datasets via 5 meta-measures.
- 1,279
- EGNet: Edge Guidance Network for Salient Object Detection1,212
This paper presents an edge guidance network (EGNet) for salient object detection with three steps to simultaneously model these two kinds of complementary information in a single network to solve the complementarity between salient edge information and salient object information.
- 915
- Concealed Object Detection786
The first systematic study on concealed object detection (COD), which aims to identify objects that are visually embedded in their background, is presented, and rich annotations including object categories, object boundaries, challenging attributes, object-level labels, and instance-level annotations are provided.
- Rethinking RGB-D Salient Object Detection: Models, Data Sets, and Large-Scale Benchmarks729
It is demonstrated that D3Net can be used to efficiently extract salient object masks from real scenes, enabling effective background-changing application with a speed of 65 frames/s on a single GPU.
- Polyp-PVT: Polyp Segmentation with Pyramid Vision Transformers626
The proposed model, named Polyp-PVT, effectively suppresses noises in the features and significantly improves their expressive capabilities, and is more robust to various challenging situations than existing representative methods.
- Simultaneously Localize, Segment and Rank the Camouflaged Objects599
It is argued that explicitly modeling the conspicuousness of camouflaged objects against their particular backgrounds can not only lead to a better understanding about camouflage and evolution of animals, but also provide guidance to design more sophisticated camouflage techniques.
- Camouflaged Object Segmentation with Distraction Mining564
This paper develops a bio-inspired framework, termed Positioning and Focus Network (PFNet), which mimics the process of predation in nature and significantly outperforms 18 cutting-edge models on three challenging datasets under four standard metrics.
- 537
- Segment anything model for medical images?518
This comprehensive report comprehensively analyzed different models and strategies on the so-called COSMOS 1050K dataset to fully validate SAM's performance on medical data and help researchers explore the potential of SAM applications in MIS, and guide how to appropriately use and develop SAM.
- Salient Object Detection via Integrity Learning480
This work designs a novel integrity learning for SOD, which outperforms the baseline methods in terms of a wide range of metrics and introduces an integrity channel enhancement (ICE) component with the goal of enhancing feature channels that highlight the integral salient objects, while suppressing the other distracting ones.
- 442
- UC-Net: Uncertainty Inspired RGB-D Saliency Detection via Conditional Variational Autoencoders408
Inspired by the saliency data labeling process, a probabilistic RGB-D saliency detection network via conditional variational autoencoders to model human annotation uncertainty and generate multiple saliency maps for each input image by sampling in the latent space is proposed.
- BBS-Net: RGB-D Salient Object Detection with a Bifurcated Backbone Strategy Network402
This paper proposes a bifurcated backbone strategy (BBS) to split the multi-level features of RGB-D salient object detection into teacher and student features, and utilizes a depth-enhanced module (DEM) to excavate informative parts of depth cues from the channel and spatial views.
- JL-DCF: Joint Learning and Densely-Cooperative Fusion Framework for RGB-D Salient Object Detection365
The JL module provides robust saliency feature learning, while the latter is introduced for complementary feature discovery, and the designed framework yields a robust RGB-D saliency detector with good generalization.
- Mutual Graph Learning for Camouflaged Object Detection350
A novel Mutual Graph Learning (MGL) model is designed, which generalizes the idea of conventional mutual learning from regular grids to the graph domain and fully exploits the mutual benefits by recurrently reasoning their high-order relations through graphs.
- Salient Objects in Clutter: Bringing Salient Object Detection to the Foreground349
This work identifies a serious design bias of existing SOD datasets which assumes that each image contains at least one clearly outstanding salient object in low clutter, and proposes a new high quality dataset and updates the previous saliency benchmark.
- 335
- RGB-D salient object detection: A survey329
This paper provides a comprehensive survey of RGB-D based salient object detection models from various perspectives, and review related benchmark datasets in detail, and investigates the ability of existing models to detect salient objects.
- Deep Gradient Learning for Efficient Camouflaged Object Detection288
The proposed DGNet performs well in the polyp segmentation, defect detection, and transparent object segmentation tasks, and achieves comparable results to the cutting-edge model JCSOD-CVPR21 with only 6.82% parameters.
- Practical Blind Image Denoising via Swin-Conv-UNet and Data Synthesis270
Extensive experiments on AGWN removal and real image denoising demonstrate that the new network architecture design achieves state-of-the-art performance and the new degradation model can help to significantly improve the practicability.
- Specificity-preserving RGB-D Saliency Detection261
A novel framework, the specificity-preserving network (SPNet), which improves SOD performance by exploring both the shared information and modality-specific properties, and which outperforms cutting-edge approaches on six popular RGB-D SOD and three camouflaged object detection benchmarks.
- Siamese Network for RGB-D Salient Object Detection and Beyond250
The proposed JL-DCF module provides robust saliency feature learning by exploiting cross-modal commonality via a Siamese network, while the DCF module is introduced for complementary feature discovery.
- Fast and Low-GPU-memory abdomen CT organ segmentation: The FLARE challenge202
The winning method surpassed the existing state-of-the-art method, achieving a 19× faster inference speed and reducing the GPU memory consumption by 60% with comparable accuracy.
- CamoFormer: Masked Separable Attention for Camouflaged Object Detection195
Inspired by the multi-head self-attention in Transformers, a simple masked separable attention (MSA) for camouflaged object detection is presented and proposed to capture high-resolution semantic representations progressively based on a simple top-down decoder with the proposed MSA to attain precise segmentation results.
- Video Polyp Segmentation: A Deep Learning Perspective193
This work introduces a high-quality frame-by-frame annotated VPS dataset, named SUN-SEG, which contains 158 690 colonoscopy video frames from the well-known SUN-database and designs a simple but efficient baseline, named PNS+, which achieves the best performance and real-time inference speed.
- Progressively Normalized Self-Attention Network for Video Polyp Segmentation186
The novel PNS-Net (Progressively Normalized Self-attention Network), which can efficiently learn representations from polyp videos with real-time speed on a single RTX 2080 GPU and no post-processing, is proposed.
- Full-duplex strategy for video object segmentation180
This work introduces a relational cross-attention module (RCAM) to achieve bidirectional message propagation across embedding sub-spaces and adopts a biddirectional purification module after the RCAM to improve the model’s robustness and update inconsistent features from the spatiotemporal embeddings.
- Bilateral Reference for High-Resolution Dichotomous Image Segmentation175
This work introduces a novel bilateral reference framework (BiRefNet) for high-resolution dichotomous image segmentation (DIS) that exhibits remarkable performance, outperforming task-specific cutting-edge methods across all benchmarks.
- Bifurcated Backbone Strategy for RGB-D Salient Object Detection173
This paper uses the inherent multi-modal and multi-level nature of RGB-D salient object detection to devise a novel Bifurcated Backbone Strategy Network (BBS-Net), which significantly outperforms 18 state-of-the-art (SOTA) models on eight challenging datasets under five evaluation measures.
- Re-thinking Co-Salient Object Detection170
A novel CoEG-Net is proposed that augments the authors' prior model EGNet with a co-attention projection strategy to enable fast common information learning and fully leverages previous large-scale SOD datasets and significantly improves the model scalability and stability.
- Uncertainty Inspired RGB-D Saliency Detection168
Qualitative and quantitative results on six challengingRGB-D benchmark datasets show the first stochastic framework to employ uncertainty for RGB-D saliency detection by learning from the data labeling process superior performance in learning the distribution of saliency maps.
- VSCode: General Visual Salient and Camouflaged Object Detection with 2D Prompt Learning162
VS-Code is introduced, a generalist model with novel 2D prompt learning, to jointly address four SOD tasks and three COD tasks and exhibits zero-shot generalization to unseen tasks by combining 2D prompts, such as RGB-D COD.
- Advances in deep concealed scene understanding148
A comprehensive survey of deep learning techniques aimed at CSU, including a taxonomy, task-specific challenges, and ongoing developments is presented, and the largest and latest benchmark for concealed object segmentation (COS) is offered.
- Kaleido-BERT: Vision-Language Pre-training on Fashion Domain145
A new vision-language (VL) pre-training model dubbed Kaleido-BERT is presented, which introduces a novel kaleido strategy for fashion cross-modality representations from transformers, and design alignment guided masking to jointly focus more on image-text semantic relations.
- Source-free Depth for Object Pop-out142
This work adapts depth inference models for object segmentation using the objects’ "pop-out" prior in 3D to adapt the inferred depth maps such that objects can be localized using only 3D information.
- SAM struggles in concealed scenes — empirical study on “Segment Anything”134
This report chooses three concealed scenes, i.e., camouflaged animals, industrial defects, and medical lesions, to evaluate SAM under unprompted settings, and observation is that SAM looks unskilled in concealed scenes.
- RGB-D Saliency Detection via Cascaded Mutual Information Minimization131
This paper introduces a novel multistage cascaded learning framework via mutual information minimization to explicitly model the multi-modal information between RGB image and depth data.
- 131
- Mindstorms in Natural Language-Based Societies of Mind124
This work assemble and experiment with several of NLSOMs, leveraging mindstorms in them to solve some practical AI tasks: visual question answering, image captioning, text-to-image synthesis, 3D generation, egocentric retrieval, embodied AI, and general language-based task solving.
- 121
- Toward Deeper Understanding of Camouflaged Object Detection115
This paper argues that the binary segmentation setting fails to fully understand the concept of camouflage, and presents the first triple-task learning framework to simultaneously localize, segment, and rank camouflaged objects, indicating the conspicuousness level of camouflage.
- Semantic Edge Detection with Diverse Deep Supervision113
A novel fully convolutional neural network using diverse deep supervision within a multi-task framework where bottom layers aim at generating category-agnostic edges, while top layers are responsible for the detection of category-aware semantic edges is proposed.
- Implicit Motion Handling for Video Camouflaged Object Detection111
A new video camouflaged object detection framework that can exploit both short-term dynamics and long-term temporal consistency to detect camouflaged objects from video frames is proposed and unifies motion estimation and object segmentation within a single optimization framework.
- 109
- Group Collaborative Learning for Co-Salient Object Detection106
This paper’s new technical contributions on a number of important downstream computer vision applications including content aware co-segmentation, co-localization based automatic thumbnails, etc are demonstrated.
- 96
- Light field salient object detection: A review and benchmark91
This paper provides the first comprehensive review and a benchmark for light field SOD, which has long been lacking in the saliency community and benchmarking results are publicly available at https://github.com/kerenfu/LFSOD-Survey.
- COVID-19 lung infection segmentation with a novel two-stage cross-domain transfer learning framework84
- 78
- 77
- 67
- Salient Objects in Clutter65
It is argued that improving the dataset can yield higher performance gains than focusing only on the decoder design, and several dataset-enhancement strategies are investigated, including label smoothing to implicitly emphasize salient boundaries, random image augmentation to adapt saliency models to various scenarios, and self-supervised learning as a regularization strategy to learn from small datasets.
- RUN: Reversible Unfolding Network for Concealed Object Segmentation64
The Reversible Unfolding Network (RUN), which applies reversible strategies across both mask and RGB domains through a theoretically grounded framework, enabling accurate segmentation and highlighting the potential of unfolding-based frameworks for COS and other high-level vision tasks.
- 56
- Scoot: A Perceptual Metric for Facial Sketches52
The results suggest that “spatial structure” and “co-occurrence texture” are two generally applicable perceptual features in face sketch synthesis, and the first largest scale human-perception-based sketch database that can evaluate how well a metric consistent with human perception is evaluated.
- Facial-sketch Synthesis: A New Challenge51
This paper introduces a high-quality dataset for FSS, named FS2K, which consists of 2 104 image-sketch pairs spanning three types of sketch styles, image backgrounds, lighting conditions, skin colors, and facial attributes, and presents the largest-scale FSS investigation by reviewing 89 classic methods.
- GCoNet+: A Stronger Group Collaborative Co-Salient Object Detector46
A novel end-to-end group collaborative learning network, termed GCoNet+, which can effectively and efficiently identify co-salient objects in natural scenes and outperforms the existing 12 cutting-edge models.
- 46
- 45
- 44
- 39
- Edge-aware Feature Aggregation Network for Polyp Segmentation37
A novel edge-aware feature aggregation network (EFA-Net) for polyp segmentation, which can fully make use of cross-level and multi-scale features to enhance the performance of polyp segmentation.
- Referring Camouflaged Object Detection37
This work develops a simple but strong dual-branch framework, dubbed R2CNet, with a reference branch embedding the common representations of target objects from referring images and a segmentation branch identifying and segmenting camouflaged objects under the guidance of the common representations.
- 37
- CalibNet: Dual-Branch Cross-Modal Calibration for RGB-D Salient Instance Segmentation33
This study proposes a novel approach for RGB-D salient instance segmentation using a dual-branch cross-modal feature calibration architecture called CalibNet, which simultaneously calibrates depth and RGB features in the kernel and mask branches to generate instance-aware kernels and mask features.
- 32
- Masked Vision-language Transformer in Fashion28
MVLT is an extensible and convenient architecture that admits raw multi-modal inputs without extra pre-processing models (e.g., ResNet), implicitly modeling the vision-language alignments and can easily generalize to various matching and generative tasks.
- CamDiff: Camouflage Image Augmentation via Diffusion Model28
CamDiff is introduced, a novel approach inspired by AI-Generated Content that overcomes the scarcity of multi-pattern training images and significantly enhances COD baselines' training and testing phases, emphasizing robustness across diverse domains.
- BA-SAM: Scalable Bias-Mode Attention Mask for Segment Anything Model25
A Scalable Bias-Mode Attention Mask (BA-SAM) is proposed to enhance SAM's adaptability to varying image resolutions while eliminating the need for structure modifications, and a new scaling factor is introduced to ensure consistent magnitude in the attention layer's dot product values when the token sequence length changes.
- LAKE-RED: Camouflaged Images Generation by Latent Background Knowledge Retrieval-Augmented Diffusion25
This paper proposes a Latent Background Knowledge Retrieval-Augmented Diffusion (LAKE-RED) for camouflaged image generation, the first knowledge retrieval-augmented method with interpretability for camouflaged generation, and is the first knowledge retrieval-augmented method with interpretability for camouflaged generation.
- 25
- Learnable differencing center for nighttime depth perception24
The key idea is to use recurrent inter-convolution differencing (RICD) and illumination affinitive intra-convolution differencing (IAICD) to enhance the nighttime color images and reduce the negative effects of the varying illumination, respectively.
- 24
- How Good is Google Bard’s Visual Understanding? An Empirical Study on Open Challenges22
This study focuses on 15 diverse task scenarios encompassing regular, camouflaged, medical, under-water and remote sensing data to comprehensively evaluate Google Bard’s performance, and indicates that Bard still struggles in these vision scenarios.
- RGB-D Indiscernible Object Counting in Underwater Scenes21
IOCFormer is proposed, a new strong baseline that combines density and regression branches in a unified framework and can effectively tackle object counting under concealed scenes and IOCFormer-D is proposed to enable the effective usage of depth modality to help count objects hidden in their environments.
- COMPrompter: reconceptualized segment anything model with multiprompt network for camouflaged object detection21
The segment anything model is rethink and a novel multiprompt network called COMPrompter is proposed, which aims to enhance the single prompt strategy in SAM to a multiprompt strategy and guides the network to achieve enhanced segmentation results, thereby advancing the development of SAM in terms of COD.
- 19
- Sub-JEPA: Subspace Gaussian Regularization for Stable End-to-End World Models18
AME is proposed, which seeks a favorable operatingpoint on the bias-variance frontier by applying Gaussian constraints in multiple random subspaces rather than in the originalembedding space, leading to a better balance between training stability and representation flexibility.
- Vanishing-Point-Guided Video Semantic Segmentation of Driving Scenes18
This work is the first to harness vanishing point (VP) priors for more effective segmentation in video semantic segmentation (VSS), and demonstrates that VPSeg outperforms previous SOTA methods, with only modest computational overhead.
- Mask Factory: Towards High-quality Synthetic Data Generation for Dichotomous Image Segmentation18
A general mask editing method that combines rigid and non-rigid editing techniques to generate high-quality synthetic masks is introduced, which provides a scalable solution for generating diverse and precise datasets, markedly reducing preparation time and costs.
- Large Model Based Referring Camouflaged Object Detection17
A large-model-based Multi-Level Knowledge-Guided multimodal method for Ref-COD termed MLKG, where multi-level knowledge descriptions from MLLM are organized to guide the large vision model of segmentation to perceive the camouflage-targets and camouflage-scene progressively and meanwhile deeply align the textual references with camouflaged photos.
- 16
- 16
- LSANet: Feature Learning on Point Sets by Local Spatial Attention15
This work designs a novel Local Spatial Attention (LSA) module to adaptively generate attention maps according to the spatial distribution of local regions and proposes the Spatial Feature Extractor (SFE), which constructs a branch architecture, to aggregate the spatial information with associated features in each layer of the network better.
- Latent Semantic Consensus for Deterministic Geometric Model Fitting14
This paper attempts to sample high-quality subsets and select model instances to estimate parameters in the multi-structural data and proposes an effective method called Latent Semantic Consensus (LSC), able to provide consistent and reliable solutions for general multi-structural model fitting.
- Reversible Unfolding Network for Concealed Visual Perception with Generative Refinement13
A reversible unfolding network with generative refinement that first formulates the CVP task as a mathematical optimization problem and unfolds the iterative solution into a multi-stage deep network, providing a principled way to apply reversible modeling across both mask and RGB domains while leveraging a diffusion model to resolve the resulting uncertainty.
- 13
- Sequential interactive image segmentation13
This paper forms a sequential interactive image segmentation task for minimizing user interaction when segmenting sequences of related images, and provides a practical approach to this task using two pertinent designs, including a novel interaction mode and an online optimization strategy.
- Validating polyp and instrument segmentation methods in colonoscopy through Medico 2020 and MedAI 2021 Challenges12
A comprehensive summary and analysis of the "Medico automatic polyp segmentation (Medico 2020)" and "MedAI: Transparency in Medical Image Segmentation (MedAI 2021)" competitions is presented, which highlight the advancements in polyp and surgical instrument segmentation but also encourage subjective evaluation for building more transparent and understandable AI-based colonoscopy systems.
- 12
- Acquiring Weak Annotations for Tumor Localization in Temporal and Volumetric Data11
This research proposes an efficient annotation strategy for tumor detection and localization that is less accurate than per-pixel annotations but useful for creating large-scale datasets for screening tumors in various medical modalities.
- 11
- Open-Vocabulary Camouflaged Object Segmentation with Cascaded Vision Language Models10
This paper introduces a novel VLM-guided cascaded framework, which treats the segmentation output as a soft spatial prior via the alpha channel, which retains the full image context while providing precise spatial guidance, leading to more accurate and context-aware classification of camouflaged objects.
- 10
- 10
- 10
- 8
- LawDIS: Language-Window-Based Controllable Dichotomous Image Segmentation8
This work presents LawDIS, a language-window-based controllable dichotomous image segmentation (DIS) framework that produces high-quality object masks and significantly outperforms 11 cutting-edge methods across all metrics.
- 8
- Deep Learning in Concealed Dense Prediction6
This article introduces and review a family of complex tasks, termed Concealed Dense Prediction (CDP), which has great value in agriculture, industry, etc and develops a taxonomy based on concealment counteracting to summarize deep learning efforts in CDP.
- WinDB: HMD-Free and Distortion-Free Panoptic Video Fixation Learning4
The auxiliary WinDB approach is introduced, which doesn't need HMD and is able to well reflect the regional-wise importance degree and a new dataset, containing 300 panoptic clips covering over 225 categories is released, containing 300 panoptic clips covering over 225 categories.
- 4
- Weakly supervised visual-auditory fixation prediction with multigranularity perception2
A novel weakly supervised approach that alleviates the demand for large-scale training sets for visual-audio model training by using only the video category tags and distill knowledge from these regions to obtain completely new spatial-temporal-audio (STA) fixation prediction (FP) networks, enabling broad applications when video tags are unavailable.
- Connecting dreams with visual brainstorming instruction2
This paper presents DreamConnect, employing a dual-stream diffusion framework to manipulate visually stimulated brain signals, and demonstrates the efficacy of the method to accurately direct human brain signals in desired directions, ultimately enabling concept manipulation through direct manipulation of the functional magnetic resonance imaging signals.
- OnUVS: Online Feature Decoupling Framework for High-Fidelity Ultrasound Video Synthesis2
A novel online feature-decoupling framework called OnUVS for high-fidelity US video synthesis is presented, which introduced anatomic information into keypoint learning through a weakly-supervised training strategy, resulting in improved preservation of anatomical integrity and motion while minimizing the labeling burden.
- 2
- 2
- QR-CLIP: Introducing Explicit Open-World Knowledge for Location and Time Reasoning1
This study lays a technical foundation for location and time reasoning and suggests that effectively introducing open-world knowledge is one of the panaceas for the tasks.
- T2ID: Towards trustworthy incomplete modality diagnosis via dual-axis adaptive completion and confidence-aware integration–
The T2ID is proposed, a multimodal diagnostic framework, which adaptively completes missing modalities and explicitly models cross-modal interactions while maintaining trustworthiness and robustness against missing modality scenarios.
- 1%>100%: High-Efficiency Visual Adapter with Complex Linear Projection Optimization–
It is demonstrated that CoLin outperforms both full fine-tuning and classical delta-tuning approaches with merely 1% parameters for the first time, providing a novel and efficient solution for deployment of vision foundation models.
- General Collaborative Intelligence: Architecting Cognition for Resilient Multi-Agent Ecosystems–
This review offers a unified synthesis of collaboration architectures and topologies, neural-communication co-design that treats the channel as a differentiable pipeline component, embodied action-perception loops via multi-agent reinforcement learning, and resilience mechanisms for synchronization, uncertainty quantification, and label-efficient learning.
- Q-Bone system: an intelligent quantitative system for alveolar bone loss to assist the diagnosis of periodontitis – model development and validation–
The Q-Bone system enables automated tooth segmentation, anatomical keypoint localization, tooth-level quantification of alveolar bone loss, and patient-level assessment across Stage, Grade, and Extent, and showed high agreement with specialist reference standards across multicenter and cross-device settings, supporting its applicability as a standardized imaging-based assistance tool for periodontal evaluation.
- AngleRoCL: Angle-Robust Concept Learning for Physically View-Invariant T2I Adversarial Patches–
The angle robustness of T2I adversarial patches is studied comprehensively, revealing their angle-robust issues, and AngleRoCL is introduced, a simple and flexible approach that significantly enhances the angle robustness of T2I adversarial patches compared to baseline methods.
- RefOnce: Distilling References into a Prototype Memory for Referring Camouflaged Object Detection–
A Ref-COD framework that distills references into a class-prototype memory during training and synthesizes a reference vector at inference via a query-conditioned mixture of prototypes, and a bidirectional attention alignment module that adapts both the query features and the class representation.
- –
- RefCut: Interactive Segmentation with Reference Guidance–
RefCut is introduced, a reference-based interactive segmentation framework designed to address part ambiguity and object ambiguity in segmenting specific targets and a new Target Disassembly Dataset which contains two subsets of part disassembly and object disassembly for evaluation.
- –
- –
- PR-MIM: Delving Deeper into Partial Reconstruction in Masked Image Modeling–
This work proposes a progressive reconstruction strategy and a furthest sampling strategy to reconstruct those thrown tokens in an extremely lightweight way instead of completely abandoning them and validates the effectiveness of the proposed method across various existing frameworks.
- –
- –
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 2026-10-12. 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.