{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/semantic-segmentation/papers/75","list_of":"/task/semantic-segmentation","task":"Semantic Segmentation","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":75,"pages_in_order":148,"rows_per_page":100,"rows":[7401,7500],"of":14763,"counts":{"archive_papers_tagged":14763,"with_a_code_link":6644,"where_syntology_ran_a_sample":1583,"not_listed_spam_title":0,"listed":14763,"listed_where_code_ran":1583,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1384,"every_run_a_failure_of_syntologys_instrument":199,"listed_with_a_run_with_no_instrument_failure":1384,"listed_every_run_a_failure_of_syntologys_instrument":199,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/semantic-segmentation","prev":"/task/semantic-segmentation/papers/74","next":"/task/semantic-segmentation/papers/76","papers":[{"url":null,"slug":"gags-granularity-aware-feature-distillation","title":"GAGS: Granularity-Aware Feature Distillation for Language Gaussian Splatting","date":"2024-12-18","arxiv_id":"2412.13654","repositories_listed":0,"syntology":null},{"url":null,"slug":"incorporating-feature-pyramid-tokenization","title":"Incorporating Feature Pyramid Tokenization and Open Vocabulary Semantic Segmentation","date":"2024-12-18","arxiv_id":"2412.14145","repositories_listed":0,"syntology":null},{"url":null,"slug":"language-guided-medical-image-segmentation","title":"Language-guided Medical Image Segmentation with Target-informed Multi-level Contrastive Alignments","date":"2024-12-18","arxiv_id":"2412.13533","repositories_listed":0,"syntology":null},{"url":null,"slug":"optical-aberrations-in-autonomous-driving","title":"Optical aberrations in autonomous driving: Physics-informed parameterized temperature scaling for neural network uncertainty calibration","date":"2024-12-18","arxiv_id":"2412.13695","repositories_listed":0,"syntology":null},{"url":null,"slug":"prompt-categories-cluster-for-weakly","title":"Prompt Categories Cluster for Weakly Supervised Semantic Segmentation","date":"2024-12-18","arxiv_id":"2412.13823","repositories_listed":0,"syntology":null},{"url":null,"slug":"split-learning-in-computer-vision-for","title":"Split Learning in Computer Vision for Semantic Segmentation Delay Minimization","date":"2024-12-18","arxiv_id":"2412.14272","repositories_listed":0,"syntology":null},{"url":null,"slug":"vitmix-vision-transformer-explainability","title":"ViTmiX: Vision Transformer Explainability Augmented by Mixed Visualization Methods","date":"2024-12-18","arxiv_id":"2412.14231","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-event-based-semantic-segmentation","title":"Efficient Event-based Semantic Segmentation with Spike-driven Lightweight Transformer-based Networks","date":"2024-12-17","arxiv_id":"2412.12843","repositories_listed":0,"syntology":null},{"url":null,"slug":"in-context-learning-for-medical-image","title":"In-context learning for medical image segmentation","date":"2024-12-17","arxiv_id":"2412.13299","repositories_listed":0,"syntology":null},{"url":null,"slug":"open-world-panoptic-segmentation","title":"Open-World Panoptic Segmentation","date":"2024-12-17","arxiv_id":"2412.12740","repositories_listed":0,"syntology":null},{"url":null,"slug":"seg-sam-semantic-guided-sam-for-unified","title":"SEG-SAM: Semantic-Guided SAM for Unified Medical Image Segmentation","date":"2024-12-17","arxiv_id":"2412.12660","repositories_listed":0,"syntology":null},{"url":null,"slug":"semstereo-semantic-constrained-stereo","title":"SemStereo: Semantic-Constrained Stereo Matching Network for Remote Sensing","date":"2024-12-17","arxiv_id":"2412.12685","repositories_listed":0,"syntology":null},{"url":null,"slug":"hresformer-hybrid-residual-transformer-for","title":"HResFormer: Hybrid Residual Transformer for Volumetric Medical Image Segmentation","date":"2024-12-16","arxiv_id":"2412.11458","repositories_listed":0,"syntology":null},{"url":null,"slug":"pypotterylens-an-open-source-deep-learning","title":"PyPotteryLens: An Open-Source Deep Learning Framework for Automated Digitisation of Archaeological Pottery Documentation","date":"2024-12-16","arxiv_id":"2412.11574","repositories_listed":0,"syntology":null},{"url":null,"slug":"samic-segment-anything-with-in-context","title":"SAMIC: Segment Anything with In-Context Spatial Prompt Engineering","date":"2024-12-16","arxiv_id":"2412.11998","repositories_listed":0,"syntology":null},{"url":null,"slug":"classification-drives-geographic-bias-in","title":"Classification Drives Geographic Bias in Street Scene Segmentation","date":"2024-12-15","arxiv_id":"2412.11061","repositories_listed":0,"syntology":null},{"url":null,"slug":"sam-if-leveraging-sam-for-incremental-few","title":"SAM-IF: Leveraging SAM for Incremental Few-Shot Instance Segmentation","date":"2024-12-15","arxiv_id":"2412.11034","repositories_listed":0,"syntology":null},{"url":null,"slug":"mal-cluster-masked-and-multi-task-pretraining","title":"MAL: Cluster-Masked and Multi-Task Pretraining for Enhanced xLSTM Vision Performance","date":"2024-12-14","arxiv_id":"2412.10730","repositories_listed":0,"syntology":null},{"url":null,"slug":"omnihd-scenes-a-next-generation-multimodal","title":"OmniHD-Scenes: A Next-Generation Multimodal Dataset for Autonomous Driving","date":"2024-12-14","arxiv_id":"2412.10734","repositories_listed":0,"syntology":null},{"url":"/paper/a-universal-degradation-based-bridging","slug":"a-universal-degradation-based-bridging","title":"A Universal Degradation-based Bridging Technique for Domain Adaptive Semantic Segmentation","date":"2024-12-13","arxiv_id":"2412.10339","repositories_listed":0,"syntology":{"n":10,"n_ran":9,"n_constructed":0,"n_ran_checked":6,"n_instrument":3,"n_unverified":1,"n_honours":2,"n_violates":3,"n_no_contract":1,"n_pointer_only":10,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 3 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/a-universal-degradation-based-bridging#ran","syntology_url":"https://syntology.ai/paper/2412.10339","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.10339"}},"official":null}},{"url":null,"slug":"object-focused-data-selection-for-dense","title":"Object-Focused Data Selection for Dense Prediction Tasks","date":"2024-12-13","arxiv_id":"2412.10032","repositories_listed":0,"syntology":null},{"url":null,"slug":"spt-sequence-prompt-transformer-for","title":"SPT: Sequence Prompt Transformer for Interactive Image Segmentation","date":"2024-12-13","arxiv_id":"2412.10224","repositories_listed":0,"syntology":null},{"url":null,"slug":"supergseg-open-vocabulary-3d-segmentation","title":"SuperGSeg: Open-Vocabulary 3D Segmentation with Structured Super-Gaussians","date":"2024-12-13","arxiv_id":"2412.10231","repositories_listed":0,"syntology":null},{"url":null,"slug":"ultra-high-resolution-segmentation-via","title":"Ultra-High Resolution Segmentation via Boundary-Enhanced Patch-Merging Transformer","date":"2024-12-13","arxiv_id":"2412.10181","repositories_listed":0,"syntology":null},{"url":null,"slug":"dqa-an-efficient-method-for-deep-quantization","title":"DQA: An Efficient Method for Deep Quantization of Deep Neural Network Activations","date":"2024-12-12","arxiv_id":"2412.09687","repositories_listed":0,"syntology":null},{"url":null,"slug":"embeddings-are-all-you-need-achieving-high","title":"Embeddings are all you need! Achieving High Performance Medical Image Classification through Training-Free Embedding Analysis","date":"2024-12-12","arxiv_id":"2412.09445","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-effectiveness-of-rotation-equivariance","title":"On the effectiveness of Rotation-Equivariance in U-Net: A Benchmark for Image Segmentation","date":"2024-12-12","arxiv_id":"2412.09182","repositories_listed":0,"syntology":null},{"url":null,"slug":"steam-squeeze-and-transform-enhanced","title":"STEAM: Squeeze and Transform Enhanced Attention Module","date":"2024-12-12","arxiv_id":"2412.09023","repositories_listed":0,"syntology":null},{"url":null,"slug":"vicas-a-dataset-for-combining-holistic-and","title":"ViCaS: A Dataset for Combining Holistic and Pixel-level Video Understanding using Captions with Grounded Segmentation","date":"2024-12-12","arxiv_id":"2412.09754","repositories_listed":0,"syntology":null},{"url":null,"slug":"vlms-meet-uda-boosting-transferability-of","title":"VLMs meet UDA: Boosting Transferability of Open Vocabulary Segmentation with Unsupervised Domain Adaptation","date":"2024-12-12","arxiv_id":"2412.09240","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-deep-semantic-segmentation-network-with","title":"A Deep Semantic Segmentation Network with Semantic and Contextual Refinements","date":"2024-12-11","arxiv_id":"2412.08671","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-feature-refinement-module-for-light-weight","title":"A feature refinement module for light-weight semantic segmentation network","date":"2024-12-11","arxiv_id":"2412.08670","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-image-annotation-for-mapped","title":"Automatic Image Annotation for Mapped Features Detection","date":"2024-12-11","arxiv_id":"2412.10438","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-context-alignment-with","title":"Hierarchical Context Alignment with Disentangled Geometric and Temporal Modeling for Semantic Occupancy Prediction","date":"2024-12-11","arxiv_id":"2412.08243","repositories_listed":0,"syntology":null},{"url":null,"slug":"intelligent-control-of-robotic-x-ray-devices","title":"Intelligent Control of Robotic X-ray Devices using a Language-promptable Digital Twin","date":"2024-12-11","arxiv_id":"2412.08020","repositories_listed":0,"syntology":null},{"url":null,"slug":"lightweight-method-for-interactive-3d-medical","title":"Lightweight Method for Interactive 3D Medical Image Segmentation with Multi-Round Result Fusion","date":"2024-12-11","arxiv_id":"2412.08315","repositories_listed":0,"syntology":null},{"url":null,"slug":"post-hoc-mots-exploring-the-capabilities-of","title":"Post-Hoc MOTS: Exploring the Capabilities of Time-Symmetric Multi-Object Tracking","date":"2024-12-11","arxiv_id":"2412.08313","repositories_listed":0,"syntology":null},{"url":null,"slug":"static-dynamic-class-level-perception","title":"Static-Dynamic Class-level Perception Consistency in Video Semantic Segmentation","date":"2024-12-11","arxiv_id":"2412.08034","repositories_listed":0,"syntology":null},{"url":null,"slug":"structured-ib-improving-information","title":"Structured IB: Improving Information Bottleneck with Structured Feature Learning","date":"2024-12-11","arxiv_id":"2412.08222","repositories_listed":0,"syntology":null},{"url":null,"slug":"unified-ht-cnns-architecture-transfer","title":"Unified HT-CNNs Architecture: Transfer Learning for Segmenting Diverse Brain Tumors in MRI from Gliomas to Pediatric Tumors","date":"2024-12-11","arxiv_id":"2412.08240","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-generative-victim-model-for-segmentation","title":"A Generative Victim Model for Segmentation","date":"2024-12-10","arxiv_id":"2412.07274","repositories_listed":0,"syntology":null},{"url":null,"slug":"active-learning-with-context-sampling-and-one","title":"Active Learning with Context Sampling and One-vs-Rest Entropy for Semantic Segmentation","date":"2024-12-09","arxiv_id":"2412.06470","repositories_listed":0,"syntology":null},{"url":null,"slug":"batseg-boundary-aware-multiclass-spinal-cord","title":"BATseg: Boundary-aware Multiclass Spinal Cord Tumor Segmentation on 3D MRI Scans","date":"2024-12-09","arxiv_id":"2412.06507","repositories_listed":0,"syntology":null},{"url":null,"slug":"contrail-a-framework-for-realistic-railway","title":"ContRail: A Framework for Realistic Railway Image Synthesis using ControlNet","date":"2024-12-09","arxiv_id":"2412.06742","repositories_listed":0,"syntology":null},{"url":null,"slug":"densevlm-a-retrieval-and-decoupled-alignment","title":"DenseVLM: A Retrieval and Decoupled Alignment Framework for Open-Vocabulary Dense Prediction","date":"2024-12-09","arxiv_id":"2412.06244","repositories_listed":0,"syntology":null},{"url":null,"slug":"gcunet-a-gnn-based-contextual-learning","title":"GCUNet: A GNN-Based Contextual Learning Network for Tertiary Lymphoid Structure Semantic Segmentation in Whole Slide Image","date":"2024-12-09","arxiv_id":"2412.06129","repositories_listed":0,"syntology":null},{"url":null,"slug":"how-certain-are-uncertainty-estimates-three","title":"How Certain are Uncertainty Estimates? Three Novel Earth Observation Datasets for Benchmarking Uncertainty Quantification in Machine Learning","date":"2024-12-09","arxiv_id":"2412.06451","repositories_listed":0,"syntology":null},{"url":null,"slug":"mscrackmamba-leveraging-vision-mamba-for","title":"MSCrackMamba: Leveraging Vision Mamba for Crack Detection in Fused Multispectral Imagery","date":"2024-12-09","arxiv_id":"2412.06211","repositories_listed":0,"syntology":null},{"url":null,"slug":"open-vocabulary-high-resolution-3d-ovhr3d","title":"Open-Vocabulary High-Resolution 3D (OVHR3D) Data Segmentation and Annotation Framework","date":"2024-12-09","arxiv_id":"2412.06268","repositories_listed":0,"syntology":null},{"url":null,"slug":"sphereuformer-a-u-shaped-transformer-for","title":"SphereUFormer: A U-Shaped Transformer for Spherical 360 Perception","date":"2024-12-09","arxiv_id":"2412.06968","repositories_listed":0,"syntology":null},{"url":null,"slug":"csg-a-context-semantic-guided-diffusion","title":"CSG: A Context-Semantic Guided Diffusion Approach in De Novo Musculoskeletal Ultrasound Image Generation","date":"2024-12-08","arxiv_id":"2412.05833","repositories_listed":0,"syntology":null},{"url":null,"slug":"dilated-balanced-cross-entropy-loss-for","title":"Dilated Balanced Cross Entropy Loss for Medical Image Segmentation","date":"2024-12-08","arxiv_id":"2412.06045","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-semantic-splatting-for-remote","title":"Efficient Semantic Splatting for Remote Sensing Multi-view Segmentation","date":"2024-12-08","arxiv_id":"2412.05969","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-deterministic-to-probabilistic-a-novel","title":"From Deterministic to Probabilistic: A Novel Perspective on Domain Generalization for Medical Image Segmentation","date":"2024-12-07","arxiv_id":"2412.05572","repositories_listed":0,"syntology":null},{"url":null,"slug":"integrating-yolo11-and-convolution-block","title":"Integrating YOLO11 and Convolution Block Attention Module for Multi-Season Segmentation of Tree Trunks and Branches in Commercial Apple Orchards","date":"2024-12-07","arxiv_id":"2412.05728","repositories_listed":0,"syntology":null},{"url":null,"slug":"refsam3d-adapting-sam-with-cross-modal","title":"RefSAM3D: Adapting SAM with Cross-modal Reference for 3D Medical Image Segmentation","date":"2024-12-07","arxiv_id":"2412.05605","repositories_listed":0,"syntology":null},{"url":null,"slug":"unet-and-lstm-combined-approach-for-breast","title":"UNet++ and LSTM combined approach for Breast Ultrasound Image Segmentation","date":"2024-12-07","arxiv_id":"2412.05585","repositories_listed":0,"syntology":null},{"url":null,"slug":"fogros2-ft-fault-tolerant-cloud-robotics","title":"FogROS2-FT: Fault Tolerant Cloud Robotics","date":"2024-12-06","arxiv_id":"2412.05408","repositories_listed":0,"syntology":null},{"url":null,"slug":"generative-model-based-fusion-for-improved","title":"Generative Model-Based Fusion for Improved Few-Shot Semantic Segmentation of Infrared Images","date":"2024-12-06","arxiv_id":"2412.05341","repositories_listed":0,"syntology":null},{"url":null,"slug":"osteoporosis-prediction-from-hand-x-ray","title":"Osteoporosis Prediction from Hand X-ray Images Using Segmentation-for-Classification and Self-Supervised Learning","date":"2024-12-06","arxiv_id":"2412.05345","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-segmentation-by-diffusing","title":"Unsupervised Segmentation by Diffusing, Walking and Cutting","date":"2024-12-06","arxiv_id":"2412.04678","repositories_listed":0,"syntology":null},{"url":null,"slug":"video-decomposition-prior-a-methodology-to","title":"Video Decomposition Prior: A Methodology to Decompose Videos into Layers","date":"2024-12-06","arxiv_id":"2412.04930","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-hitchhiker-s-guide-to-understanding","title":"A Hitchhiker's Guide to Understanding Performances of Two-Class Classifiers","date":"2024-12-05","arxiv_id":"2412.04377","repositories_listed":0,"syntology":null},{"url":null,"slug":"assessing-and-learning-alignment-of-unimodal","title":"Assessing and Learning Alignment of Unimodal Vision and Language Models","date":"2024-12-05","arxiv_id":"2412.04616","repositories_listed":0,"syntology":null},{"url":null,"slug":"customize-segment-anything-model-for-multi","title":"Customize Segment Anything Model for Multi-Modal Semantic Segmentation with Mixture of LoRA Experts","date":"2024-12-05","arxiv_id":"2412.04220","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-fully-convolutional-networks-for","title":"Exploring Fully Convolutional Networks for the Segmentation of Hyperspectral Imaging Applied to Advanced Driver Assistance Systems","date":"2024-12-05","arxiv_id":"2412.03982","repositories_listed":0,"syntology":null},{"url":null,"slug":"ll-icm-image-compression-for-low-level","title":"LL-ICM: Image Compression for Low-level Machine Vision via Large Vision-Language Model","date":"2024-12-05","arxiv_id":"2412.03841","repositories_listed":0,"syntology":null},{"url":null,"slug":"text-change-detection-in-multilingual","title":"Text Change Detection in Multilingual Documents Using Image Comparison","date":"2024-12-05","arxiv_id":"2412.04137","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-real-time-open-vocabulary-video","title":"Towards Real-Time Open-Vocabulary Video Instance Segmentation","date":"2024-12-05","arxiv_id":"2412.04434","repositories_listed":0,"syntology":null},{"url":null,"slug":"using-diffusion-priors-for-video-amodal","title":"Using Diffusion Priors for Video Amodal Segmentation","date":"2024-12-05","arxiv_id":"2412.04623","repositories_listed":0,"syntology":null},{"url":null,"slug":"appearance-matching-adapter-for-exemplar","title":"Appearance Matching Adapter for Exemplar-based Semantic Image Synthesis","date":"2024-12-04","arxiv_id":"2412.03150","repositories_listed":0,"syntology":null},{"url":null,"slug":"assessing-the-performance-of-ct-image","title":"Assessing the performance of CT image denoisers using Laguerre-Gauss Channelized Hotelling Observer for lesion detection","date":"2024-12-04","arxiv_id":"2412.02920","repositories_listed":0,"syntology":null},{"url":null,"slug":"benchmarking-pretrained-attention-based","title":"Benchmarking Pretrained Attention-based Models for Real-Time Recognition in Robot-Assisted Esophagectomy","date":"2024-12-04","arxiv_id":"2412.03401","repositories_listed":0,"syntology":null},{"url":null,"slug":"biologically-inspired-semi-supervised","title":"Biologically-inspired Semi-supervised Semantic Segmentation for Biomedical Imaging","date":"2024-12-04","arxiv_id":"2412.03192","repositories_listed":0,"syntology":null},{"url":null,"slug":"designing-dnns-for-a-trade-off-between","title":"Designing DNNs for a trade-off between robustness and processing performance in embedded devices","date":"2024-12-04","arxiv_id":"2412.03682","repositories_listed":0,"syntology":null},{"url":null,"slug":"is-foreground-prototype-sufficient-few-shot","title":"Is Foreground Prototype Sufficient? Few-Shot Medical Image Segmentation with Background-Fused Prototype","date":"2024-12-04","arxiv_id":"2412.02983","repositories_listed":0,"syntology":null},{"url":null,"slug":"progressive-vision-language-prompt-for-multi","title":"Progressive Vision-Language Prompt for Multi-Organ Multi-Class Cell Semantic Segmentation with Single Branch","date":"2024-12-04","arxiv_id":"2412.02978","repositories_listed":0,"syntology":null},{"url":null,"slug":"semantic-segmentation-prior-for-diffusion","title":"Semantic Segmentation Prior for Diffusion-Based Real-World Super-Resolution","date":"2024-12-04","arxiv_id":"2412.02960","repositories_listed":0,"syntology":null},{"url":null,"slug":"task-driven-image-fusion-with-learnable","title":"Task-driven Image Fusion with Learnable Fusion Loss","date":"2024-12-04","arxiv_id":"2412.03240","repositories_listed":0,"syntology":null},{"url":null,"slug":"ah-ocda-amplitude-based-curriculum-learning","title":"AH-OCDA: Amplitude-based Curriculum Learning and Hopfield Segmentation Model for Open Compound Domain Adaptation","date":"2024-12-03","arxiv_id":"2412.02280","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-robot-autonomous-3d-reconstruction","title":"Multi-robot autonomous 3D reconstruction using Gaussian splatting with Semantic guidance","date":"2024-12-03","arxiv_id":"2412.02249","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-scale-and-multi-path-cascaded","title":"Multi-scale and Multi-path Cascaded Convolutional Network for Semantic Segmentation of Colorectal Polyps","date":"2024-12-03","arxiv_id":"2412.02443","repositories_listed":0,"syntology":null},{"url":null,"slug":"topology-preserving-image-segmentation-with","title":"Topology-Preserving Image Segmentation with Spatial-Aware Persistent Feature Matching","date":"2024-12-03","arxiv_id":"2412.02076","repositories_listed":0,"syntology":null},{"url":null,"slug":"u-net-in-medical-image-segmentation-a-review","title":"U-Net in Medical Image Segmentation: A Review of Its Applications Across Modalities","date":"2024-12-03","arxiv_id":"2412.02242","repositories_listed":0,"syntology":null},{"url":null,"slug":"3dsceneeditor-controllable-3d-scene-editing","title":"3DSceneEditor: Controllable 3D Scene Editing with Gaussian Splatting","date":"2024-12-02","arxiv_id":"2412.01583","repositories_listed":0,"syntology":null},{"url":null,"slug":"a2vis-amodal-aware-approach-to-video-instance","title":"A2VIS: Amodal-Aware Approach to Video Instance Segmentation","date":"2024-12-02","arxiv_id":"2412.01147","repositories_listed":0,"syntology":null},{"url":null,"slug":"epipolar-attention-field-transformers-for","title":"Epipolar Attention Field Transformers for Bird's Eye View Semantic Segmentation","date":"2024-12-02","arxiv_id":"2412.01595","repositories_listed":0,"syntology":null},{"url":null,"slug":"global-average-feature-augmentation-for","title":"Global Average Feature Augmentation for Robust Semantic Segmentation with Transformers","date":"2024-12-02","arxiv_id":"2412.01941","repositories_listed":0,"syntology":null},{"url":null,"slug":"holistic-understanding-of-3d-scenes-as","title":"Holistic Understanding of 3D Scenes as Universal Scene Description","date":"2024-12-02","arxiv_id":"2412.01398","repositories_listed":0,"syntology":null},{"url":null,"slug":"insight-explainable-weakly-supervised-medical","title":"INSIGHT: Explainable Weakly-Supervised Medical Image Analysis","date":"2024-12-02","arxiv_id":"2412.02012","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-and-transferable-backdoor-attacks","title":"Robust and Transferable Backdoor Attacks Against Deep Image Compression With Selective Frequency Prior","date":"2024-12-02","arxiv_id":"2412.01646","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-semi-supervised-approach-with-error","title":"A Semi-Supervised Approach with Error Reflection for Echocardiography Segmentation","date":"2024-12-01","arxiv_id":"2412.00715","repositories_listed":0,"syntology":null},{"url":null,"slug":"dpe-net-dual-parallel-encoder-based-network","title":"DPE-Net: Dual-Parallel Encoder Based Network for Semantic Segmentation of Polyps","date":"2024-12-01","arxiv_id":"2412.00888","repositories_listed":0,"syntology":null},{"url":null,"slug":"spf-net-solar-panel-fault-detection-using-u","title":"SPF-Net: Solar panel fault detection using U-Net based deep learning image classification","date":"2024-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"tsubf-net-trans-spatial-unet-like-network","title":"TSUBF-Net: Trans-Spatial UNet-like Network with Bi-direction Fusion for Segmentation of Adenoid Hypertrophy in CT","date":"2024-12-01","arxiv_id":"2412.00787","repositories_listed":0,"syntology":null},{"url":null,"slug":"lmseg-unleashing-the-power-of-large-scale","title":"LMSeg: Unleashing the Power of Large-Scale Models for Open-Vocabulary Semantic Segmentation","date":"2024-11-30","arxiv_id":"2412.00364","repositories_listed":0,"syntology":null},{"url":null,"slug":"retrieval-guided-cross-view-image-synthesis","title":"Retrieval-guided Cross-view Image Synthesis","date":"2024-11-29","arxiv_id":"2411.19510","repositories_listed":0,"syntology":null},{"url":null,"slug":"beyond-logit-lens-contextual-embeddings-for","title":"Beyond Logit Lens: Contextual Embeddings for Robust Hallucination Detection & Grounding in VLMs","date":"2024-11-28","arxiv_id":"2411.19187","repositories_listed":0,"syntology":null},{"url":null,"slug":"fan-unet-enhancing-unet-with-vision-fourier","title":"FAN-Unet: Enhancing Unet with vision Fourier Analysis Block for Biomedical Image Segmentation","date":"2024-11-28","arxiv_id":"2411.18975","repositories_listed":0,"syntology":null},{"url":null,"slug":"gms-vins-multi-category-dynamic-objects","title":"GMS-VINS:Multi-category Dynamic Objects Semantic Segmentation for Enhanced Visual-Inertial Odometry Using a Promptable Foundation Model","date":"2024-11-28","arxiv_id":"2411.19289","repositories_listed":0,"syntology":null}],"record_sha256":"c9d8a030eb2a910291580b0cdc67b3a89202d4ce22f8b3863e45ec66aed53d49","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}