{"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":"/method/dino/papers/2","list_of":"/method/dino","method":"DINO","archive":{"snapshot":"2025-07-28"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"date (newest first), then slug","page":2,"pages_in_order":3,"rows_per_page":100,"rows":[101,200],"of":208,"counts":{"archive_papers_tagged":208,"with_a_code_link":105,"where_syntology_ran_a_sample":30,"not_listed_spam_title":0,"listed":208,"listed_where_code_ran":30,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":28,"every_run_a_failure_of_syntologys_instrument":2,"listed_with_a_run_with_no_instrument_failure":28,"listed_every_run_a_failure_of_syntologys_instrument":2,"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":"/method/dino","prev":"/method/dino","next":"/method/dino/papers/3","papers":[{"paper":"/paper/swiss-dino-efficient-and-versatile-vision","slug":"swiss-dino-efficient-and-versatile-vision","title":"Swiss DINO: Efficient and Versatile Vision Framework for On-device Personal Object Search","date":"2024-07-10","arxiv_id":"2407.07541","n_code_links":1,"syntology":null},{"paper":null,"slug":"segment-anything-model-for-automated-image","title":"Segment Anything Model for automated image data annotation: empirical studies using text prompts from Grounding DINO","date":"2024-06-27","arxiv_id":"2406.19057","n_code_links":0,"syntology":null},{"paper":"/paper/enhanced-bank-check-security-introducing-a","slug":"enhanced-bank-check-security-introducing-a","title":"Enhanced Bank Check Security: Introducing a Novel Dataset and Transformer-Based Approach for Detection and Verification","date":"2024-06-20","arxiv_id":"2406.14370","n_code_links":1,"syntology":null},{"paper":null,"slug":"liveness-detection-in-computer-vision","title":"Liveness Detection in Computer Vision: Transformer-based Self-Supervised Learning for Face Anti-Spoofing","date":"2024-06-19","arxiv_id":"2406.13860","n_code_links":0,"syntology":null},{"paper":"/paper/mixing-natural-and-synthetic-images-for","slug":"mixing-natural-and-synthetic-images-for","title":"MixDiff: Mixing Natural and Synthetic Images for Robust Self-Supervised Representations","date":"2024-06-18","arxiv_id":"2406.12368","n_code_links":1,"syntology":null},{"paper":null,"slug":"ice-g-image-conditional-editing-of-3d","title":"ICE-G: Image Conditional Editing of 3D Gaussian Splats","date":"2024-06-12","arxiv_id":"2406.08488","n_code_links":0,"syntology":null},{"paper":null,"slug":"uvis-unsupervised-video-instance-segmentation","title":"UVIS: Unsupervised Video Instance Segmentation","date":"2024-06-11","arxiv_id":"2406.06908","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-comparative-survey-of-vision-transformers","title":"A Comparative Survey of Vision Transformers for Feature Extraction in Texture Analysis","date":"2024-06-10","arxiv_id":"2406.06136","n_code_links":0,"syntology":null},{"paper":"/paper/decomposing-and-interpreting-image","slug":"decomposing-and-interpreting-image","title":"Decomposing and Interpreting Image Representations via Text in ViTs Beyond CLIP","date":"2024-06-03","arxiv_id":"2406.01583","n_code_links":1,"syntology":{"ran":10,"of":13,"n_ran_checked":10,"n_instrument":0,"unverified":3,"pointer_only":13,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["sriramb-98/vit-decompose"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"elsa-evaluating-localization-of-social","title":"ELSA: Evaluating Localization of Social Activities in Urban Streets using Open-Vocabulary Detection","date":"2024-06-03","arxiv_id":"2406.01551","n_code_links":0,"syntology":null},{"paper":null,"slug":"eating-smart-advancing-health-informatics","title":"Eating Smart: Advancing Health Informatics with the Grounding DINO based Dietary Assistant App","date":"2024-06-02","arxiv_id":"2406.00848","n_code_links":0,"syntology":null},{"paper":"/paper/fdqn-a-flexible-deep-q-network-framework-for","slug":"fdqn-a-flexible-deep-q-network-framework-for","title":"FDQN: A Flexible Deep Q-Network Framework for Game Automation","date":"2024-05-29","arxiv_id":"2405.18761","n_code_links":1,"syntology":null},{"paper":"/paper/adapting-pre-trained-vision-models-for-novel","slug":"adapting-pre-trained-vision-models-for-novel","title":"Adapting Pre-Trained Vision Models for Novel Instance Detection and Segmentation","date":"2024-05-28","arxiv_id":"2405.17859","n_code_links":1,"syntology":{"ran":7,"of":7,"n_ran_checked":7,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["youngsean/nids-net"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"sa-gs-semantic-aware-gaussian-splatting-for","title":"SA-GS: Semantic-Aware Gaussian Splatting for Large Scene Reconstruction with Geometry Constrain","date":"2024-05-27","arxiv_id":"2405.16923","n_code_links":0,"syntology":null},{"paper":"/paper/designing-a-sustainable-marine-debris-clean","slug":"designing-a-sustainable-marine-debris-clean","title":"Designing A Sustainable Marine Debris Clean-up Framework without Human Labels","date":"2024-05-23","arxiv_id":"2405.14815","n_code_links":1,"syntology":null},{"paper":null,"slug":"text-prompting-for-multi-concept-video","title":"Text Prompting for Multi-Concept Video Customization by Autoregressive Generation","date":"2024-05-22","arxiv_id":"2405.13951","n_code_links":0,"syntology":null},{"paper":"/paper/track-anything-rapter-tar","slug":"track-anything-rapter-tar","title":"Track Anything Rapter(TAR)","date":"2024-05-19","arxiv_id":"2405.11655","n_code_links":1,"syntology":null},{"paper":"/paper/dino-as-a-von-mises-fisher-mixture-model-1","slug":"dino-as-a-von-mises-fisher-mixture-model-1","title":"DINO as a von Mises-Fisher mixture model","date":"2024-05-17","arxiv_id":"2405.10939","n_code_links":0,"syntology":null},{"paper":"/paper/grounding-dino-1-5-advance-the-edge-of-open","slug":"grounding-dino-1-5-advance-the-edge-of-open","title":"Grounding DINO 1.5: Advance the \"Edge\" of Open-Set Object Detection","date":"2024-05-16","arxiv_id":"2405.10300","n_code_links":3,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["idea-research/grounding-dino-1.5-api"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"multi-method-integration-with-confidence","title":"Multi-method Integration with Confidence-based Weighting for Zero-shot Image Classification","date":"2024-05-03","arxiv_id":"2405.02155","n_code_links":0,"syntology":null},{"paper":"/paper/exploring-self-supervised-vision-transformers","slug":"exploring-self-supervised-vision-transformers","title":"Exploring Self-Supervised Vision Transformers for Deepfake Detection: A Comparative Analysis","date":"2024-05-01","arxiv_id":"2405.00355","n_code_links":1,"syntology":null},{"paper":"/paper/masked-multi-query-slot-attention-for","slug":"masked-multi-query-slot-attention-for","title":"Masked Multi-Query Slot Attention for Unsupervised Object Discovery","date":"2024-04-30","arxiv_id":"2404.19654","n_code_links":1,"syntology":null},{"paper":"/paper/parameter-efficient-fine-tuning-of-self","slug":"parameter-efficient-fine-tuning-of-self","title":"Parameter Efficient Fine-tuning of Self-supervised ViTs without Catastrophic Forgetting","date":"2024-04-26","arxiv_id":"2404.17245","n_code_links":1,"syntology":null},{"paper":"/paper/boosting-unsupervised-semantic-segmentation","slug":"boosting-unsupervised-semantic-segmentation","title":"Boosting Unsupervised Semantic Segmentation with Principal Mask Proposals","date":"2024-04-25","arxiv_id":"2404.16818","n_code_links":1,"syntology":null},{"paper":"/paper/sparo-selective-attention-for-robust-and","slug":"sparo-selective-attention-for-robust-and","title":"SPARO: Selective Attention for Robust and Compositional Transformer Encodings for Vision","date":"2024-04-24","arxiv_id":"2404.15721","n_code_links":1,"syntology":null},{"paper":null,"slug":"1st-place-solution-to-the-1st-skatingverse","title":"1st Place Solution to the 1st SkatingVerse Challenge","date":"2024-04-22","arxiv_id":"2404.14032","n_code_links":0,"syntology":null},{"paper":"/paper/filo-zero-shot-anomaly-detection-by-fine","slug":"filo-zero-shot-anomaly-detection-by-fine","title":"FiLo: Zero-Shot Anomaly Detection by Fine-Grained Description and High-Quality Localization","date":"2024-04-21","arxiv_id":"2404.13671","n_code_links":1,"syntology":{"ran":7,"of":12,"n_ran_checked":5,"n_instrument":2,"unverified":5,"pointer_only":7,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified","official":{"repos":["casia-iva-lab/filo"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":"/paper/vim4path-self-supervised-vision-mamba-for","slug":"vim4path-self-supervised-vision-mamba-for","title":"Vim4Path: Self-Supervised Vision Mamba for Histopathology Images","date":"2024-04-20","arxiv_id":"2404.13222","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":1,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["atlasanalyticslab/vim4path"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"paper":"/paper/the-devil-is-in-the-object-boundary-towards","slug":"the-devil-is-in-the-object-boundary-towards","title":"The devil is in the object boundary: towards annotation-free instance segmentation using Foundation Models","date":"2024-04-18","arxiv_id":"2404.11957","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["chengshiest/zip-your-clip"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"hyperbolic-learning-with-synthetic-captions","title":"Hyperbolic Learning with Synthetic Captions for Open-World Detection","date":"2024-04-07","arxiv_id":"2404.05016","n_code_links":0,"syntology":null},{"paper":"/paper/cluster-based-video-summarization-with","slug":"cluster-based-video-summarization-with","title":"Cluster-based Video Summarization with Temporal Context Awareness","date":"2024-04-06","arxiv_id":"2404.04511","n_code_links":1,"syntology":null},{"paper":null,"slug":"opennerf-open-set-3d-neural-scene","title":"OpenNeRF: Open Set 3D Neural Scene Segmentation with Pixel-Wise Features and Rendered Novel Views","date":"2024-04-04","arxiv_id":"2404.03650","n_code_links":0,"syntology":null},{"paper":null,"slug":"investigating-robustness-of-open-vocabulary","title":"Open-Vocabulary Object Detectors: Robustness Challenges under Distribution Shifts","date":"2024-04-01","arxiv_id":"2405.14874","n_code_links":0,"syntology":null},{"paper":null,"slug":"illicit-object-detection-in-x-ray-images","title":"Illicit object detection in X-ray images using Vision Transformers","date":"2024-03-27","arxiv_id":"2403.19043","n_code_links":0,"syntology":null},{"paper":null,"slug":"lift3d-zero-shot-lifting-of-any-2d-vision","title":"Lift3D: Zero-Shot Lifting of Any 2D Vision Model to 3D","date":"2024-03-27","arxiv_id":"2403.18922","n_code_links":0,"syntology":null},{"paper":"/paper/towards-large-scale-training-of-pathology","slug":"towards-large-scale-training-of-pathology","title":"Towards Large-Scale Training of Pathology Foundation Models","date":"2024-03-24","arxiv_id":"2404.15217","n_code_links":2,"syntology":{"ran":0,"of":3,"n_ran_checked":0,"n_instrument":0,"unverified":3,"pointer_only":3,"phrase":"0 ran · 3 unverified","official":{"repos":["kaiko-ai/eva","kaiko-ai/towards_large_pathology_fms"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":[]}}},{"paper":null,"slug":"unsupervised-audio-visual-segmentation-with","title":"Unsupervised Audio-Visual Segmentation with Modality Alignment","date":"2024-03-21","arxiv_id":"2403.14203","n_code_links":0,"syntology":null},{"paper":"/paper/tag-guidance-free-open-vocabulary-semantic","slug":"tag-guidance-free-open-vocabulary-semantic","title":"TAG: Guidance-free Open-Vocabulary Semantic Segmentation","date":"2024-03-17","arxiv_id":"2403.11197","n_code_links":1,"syntology":null},{"paper":"/paper/efficient-geometric-markov-chain-monte-carlo","slug":"efficient-geometric-markov-chain-monte-carlo","title":"Derivative-informed neural operator acceleration of geometric MCMC for infinite-dimensional Bayesian inverse problems","date":"2024-03-13","arxiv_id":"2403.08220","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["hippylib/hippyflow"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"self-supervised-multiple-instance-learning","title":"Self-Supervised Multiple Instance Learning for Acute Myeloid Leukemia Classification","date":"2024-03-08","arxiv_id":"2403.05379","n_code_links":0,"syntology":null},{"paper":"/paper/ao-detr-anti-overlapping-detr-for-x-ray","slug":"ao-detr-anti-overlapping-detr-for-x-ray","title":"AO-DETR: Anti-Overlapping DETR for X-Ray Prohibited Items Detection","date":"2024-03-07","arxiv_id":"2403.04309","n_code_links":1,"syntology":null},{"paper":"/paper/deformable-one-shot-face-stylization-via-dino","slug":"deformable-one-shot-face-stylization-via-dino","title":"Deformable One-shot Face Stylization via DINO Semantic Guidance","date":"2024-03-01","arxiv_id":"2403.00459","n_code_links":1,"syntology":null},{"paper":"/paper/self-supervised-visualisation-of-medical","slug":"self-supervised-visualisation-of-medical","title":"Self-supervised Visualisation of Medical Image Datasets","date":"2024-02-22","arxiv_id":"2402.14566","n_code_links":1,"syntology":null},{"paper":null,"slug":"dinobot-robot-manipulation-via-retrieval-and","title":"DINOBot: Robot Manipulation via Retrieval and Alignment with Vision Foundation Models","date":"2024-02-20","arxiv_id":"2402.13181","n_code_links":0,"syntology":null},{"paper":"/paper/biofusionnet-deep-learning-based-survival","slug":"biofusionnet-deep-learning-based-survival","title":"BioFusionNet: Deep Learning-Based Survival Risk Stratification in ER+ Breast Cancer Through Multifeature and Multimodal Data Fusion","date":"2024-02-16","arxiv_id":"2402.10717","n_code_links":1,"syntology":null},{"paper":"/paper/just-cluster-it-an-approach-for-exploration","slug":"just-cluster-it-an-approach-for-exploration","title":"Just Cluster It: An Approach for Exploration in High-Dimensions using Clustering and Pre-Trained Representations","date":"2024-02-05","arxiv_id":"2402.03138","n_code_links":1,"syntology":{"ran":7,"of":8,"n_ran_checked":6,"n_instrument":1,"unverified":1,"pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["stefanwm13/just-cluster-it-public"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/a-probabilistic-model-to-explain-self","slug":"a-probabilistic-model-to-explain-self","title":"A Probabilistic Model Behind Self-Supervised Learning","date":"2024-02-02","arxiv_id":"2402.01399","n_code_links":1,"syntology":{"ran":9,"of":10,"n_ran_checked":7,"n_instrument":2,"unverified":1,"pointer_only":10,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["alicebizeul/simvae"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/enhancing-multimodal-large-language-models","slug":"enhancing-multimodal-large-language-models","title":"From Training-Free to Adaptive: Empirical Insights into MLLMs' Understanding of Detection Information","date":"2024-01-31","arxiv_id":"2401.17981","n_code_links":0,"syntology":null},{"paper":"/paper/cross-domain-few-shot-learning-via-adaptive","slug":"cross-domain-few-shot-learning-via-adaptive","title":"Cross-Domain Few-Shot Learning via Adaptive Transformer Networks","date":"2024-01-25","arxiv_id":"2401.13987","n_code_links":1,"syntology":null},{"paper":"/paper/grounded-sam-assembling-open-world-models-for","slug":"grounded-sam-assembling-open-world-models-for","title":"Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks","date":"2024-01-25","arxiv_id":"2401.14159","n_code_links":5,"syntology":{"ran":15,"of":15,"n_ran_checked":10,"n_instrument":5,"unverified":0,"pointer_only":5,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 0 violated, 9 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified","official":{"repos":["IDEA-Research/Grounded-Segment-Anything"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/datus-2-data-driven-unsupervised-semantic","slug":"datus-2-data-driven-unsupervised-semantic","title":"DatUS^2: Data-driven Unsupervised Semantic Segmentation with Pre-trained Self-supervised Vision Transformer","date":"2024-01-23","arxiv_id":"2401.12820","n_code_links":1,"syntology":null},{"paper":"/paper/a-novel-benchmark-for-few-shot-semantic","slug":"a-novel-benchmark-for-few-shot-semantic","title":"A Novel Benchmark for Few-Shot Semantic Segmentation in the Era of Foundation Models","date":"2024-01-20","arxiv_id":"2401.11311","n_code_links":1,"syntology":null},{"paper":"/paper/image-similarity-using-an-ensemble-of-context","slug":"image-similarity-using-an-ensemble-of-context","title":"Image Similarity using An Ensemble of Context-Sensitive Models","date":"2024-01-15","arxiv_id":"2401.07951","n_code_links":1,"syntology":null},{"paper":null,"slug":"cosseggaussians-compact-and-swift-scene","title":"Learning Segmented 3D Gaussians via Efficient Feature Unprojection for Zero-shot Neural Scene Segmentation","date":"2024-01-11","arxiv_id":"2401.05925","n_code_links":0,"syntology":null},{"paper":"/paper/surgical-dino-adapter-learning-of-foundation","slug":"surgical-dino-adapter-learning-of-foundation","title":"Surgical-DINO: Adapter Learning of Foundation Models for Depth Estimation in Endoscopic Surgery","date":"2024-01-11","arxiv_id":"2401.06013","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"0 ran · 1 unverified","official":{"repos":["beileicui/surgicaldino"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":null,"slug":"attention-guided-erasing-a-novel-augmentation","title":"Attention-Guided Erasing: A Novel Augmentation Method for Enhancing Downstream Breast Density Classification","date":"2024-01-08","arxiv_id":"2401.03912","n_code_links":0,"syntology":null},{"paper":null,"slug":"boosting-transformer-s-robustness-and","title":"A Novel Transformer-Based Self-Supervised Learning Method to Enhance Photoplethysmogram Signal Artifact Detection","date":"2024-01-02","arxiv_id":"2401.01013","n_code_links":0,"syntology":null},{"paper":null,"slug":"kd-detr-knowledge-distillation-for-detection","title":"KD-DETR: Knowledge Distillation for Detection Transformer with Consistent Distillation Points Sampling","date":"2024-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"analyzing-local-representations-of-self","title":"Analyzing Local Representations of Self-supervised Vision Transformers","date":"2023-12-31","arxiv_id":"2401.00463","n_code_links":0,"syntology":null},{"paper":"/paper/learning-vision-from-models-rivals-learning","slug":"learning-vision-from-models-rivals-learning","title":"Learning Vision from Models Rivals Learning Vision from Data","date":"2023-12-28","arxiv_id":"2312.17742","n_code_links":2,"syntology":{"ran":4,"of":4,"n_ran_checked":2,"n_instrument":2,"unverified":0,"pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["google-research/syn-rep-learn"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/langsplat-3d-language-gaussian-splatting","slug":"langsplat-3d-language-gaussian-splatting","title":"LangSplat: 3D Language Gaussian Splatting","date":"2023-12-26","arxiv_id":"2312.16084","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":1,"n_instrument":2,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["minghanqin/LangSplat"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"unsupervised-segmentation-of-colonoscopy","title":"Unsupervised Segmentation of Colonoscopy Images","date":"2023-12-19","arxiv_id":"2312.12599","n_code_links":0,"syntology":null},{"paper":null,"slug":"guided-diffusion-from-self-supervised","title":"Guided Diffusion from Self-Supervised Diffusion Features","date":"2023-12-14","arxiv_id":"2312.08825","n_code_links":0,"syntology":null},{"paper":"/paper/mixed-pseudo-labels-for-semi-supervised","slug":"mixed-pseudo-labels-for-semi-supervised","title":"Mixed Pseudo Labels for Semi-Supervised Object Detection","date":"2023-12-12","arxiv_id":"2312.07006","n_code_links":1,"syntology":null},{"paper":"/paper/learning-efficient-unsupervised-satellite","slug":"learning-efficient-unsupervised-satellite","title":"Learning Efficient Unsupervised Satellite Image-based Building Damage Detection","date":"2023-12-04","arxiv_id":"2312.01576","n_code_links":1,"syntology":null},{"paper":null,"slug":"multi-task-image-restoration-guided-by-robust","title":"Multi-task Image Restoration Guided By Robust DINO Features","date":"2023-12-04","arxiv_id":"2312.01677","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-lightweight-clustering-framework-for","title":"A Lightweight Clustering Framework for Unsupervised Semantic Segmentation","date":"2023-11-30","arxiv_id":"2311.18628","n_code_links":0,"syntology":null},{"paper":null,"slug":"hifi-tuner-high-fidelity-subject-driven-fine","title":"HiFi Tuner: High-Fidelity Subject-Driven Fine-Tuning for Diffusion Models","date":"2023-11-30","arxiv_id":"2312.00079","n_code_links":0,"syntology":null},{"paper":"/paper/label-efficient-training-of-small-task","slug":"label-efficient-training-of-small-task","title":"Knowledge Transfer from Vision Foundation Models for Efficient Training of Small Task-specific Models","date":"2023-11-30","arxiv_id":"2311.18237","n_code_links":1,"syntology":null},{"paper":"/paper/betrayed-by-attention-a-simple-yet-effective","slug":"betrayed-by-attention-a-simple-yet-effective","title":"Betrayed by Attention: A Simple yet Effective Approach for Self-supervised Video Object Segmentation","date":"2023-11-29","arxiv_id":"2311.17893","n_code_links":1,"syntology":{"ran":10,"of":12,"n_ran_checked":8,"n_instrument":2,"unverified":2,"pointer_only":12,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["shvdiwnkozbw/ssl-uvos"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/dyra-dynamic-resolution-adjustment-for-scale","slug":"dyra-dynamic-resolution-adjustment-for-scale","title":"DyRA: Portable Dynamic Resolution Adjustment Network for Existing Detectors","date":"2023-11-28","arxiv_id":"2311.17098","n_code_links":2,"syntology":null},{"paper":"/paper/understanding-self-supervised-features-for","slug":"understanding-self-supervised-features-for","title":"Understanding Self-Supervised Features for Learning Unsupervised Instance Segmentation","date":"2023-11-24","arxiv_id":"2311.14665","n_code_links":0,"syntology":null},{"paper":"/paper/importance-of-feature-extraction-in-the","slug":"importance-of-feature-extraction-in-the","title":"Feature Extraction for Generative Medical Imaging Evaluation: New Evidence Against an Evolving Trend","date":"2023-11-22","arxiv_id":"2311.13717","n_code_links":2,"syntology":null},{"paper":"/paper/white-box-transformers-via-sparse-rate-1","slug":"white-box-transformers-via-sparse-rate-1","title":"White-Box Transformers via Sparse Rate Reduction: Compression Is All There Is?","date":"2023-11-22","arxiv_id":"2311.13110","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":1,"n_instrument":2,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":null,"slug":"a-large-scale-car-parts-lscp-dataset-for","title":"A Large-Scale Car Parts (LSCP) Dataset for Lightweight Fine-Grained Detection","date":"2023-11-20","arxiv_id":"2311.11754","n_code_links":0,"syntology":null},{"paper":"/paper/freekd-knowledge-distillation-via-semantic","slug":"freekd-knowledge-distillation-via-semantic","title":"FreeKD: Knowledge Distillation via Semantic Frequency Prompt","date":"2023-11-20","arxiv_id":"2311.12079","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["Gumpest/FreeKD"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/unifiedvisiongpt-streamlining-vision-oriented","slug":"unifiedvisiongpt-streamlining-vision-oriented","title":"UnifiedVisionGPT: Streamlining Vision-Oriented AI through Generalized Multimodal Framework","date":"2023-11-16","arxiv_id":"2311.10125","n_code_links":1,"syntology":null},{"paper":null,"slug":"generalizable-imitation-learning-through-pre","title":"Generalizable Imitation Learning Through Pre-Trained Representations","date":"2023-11-15","arxiv_id":"2311.09350","n_code_links":0,"syntology":null},{"paper":"/paper/cal-detr-calibrated-detection-transformer-1","slug":"cal-detr-calibrated-detection-transformer-1","title":"Cal-DETR: Calibrated Detection Transformer","date":"2023-11-06","arxiv_id":"2311.03570","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","official":{"repos":["akhtarvision/cal-detr"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":"/paper/masking-hyperspectral-imaging-data-with","slug":"masking-hyperspectral-imaging-data-with","title":"Masking Hyperspectral Imaging Data with Pretrained Models","date":"2023-11-06","arxiv_id":"2311.03053","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-self-supervised-approach-to-land-cover","title":"A Self-Supervised Approach to Land Cover Segmentation","date":"2023-10-27","arxiv_id":"2310.18251","n_code_links":0,"syntology":null},{"paper":null,"slug":"samclr-contrastive-pre-training-on-complex","title":"SAMCLR: Contrastive pre-training on complex scenes using SAM for view sampling","date":"2023-10-23","arxiv_id":"2310.14736","n_code_links":0,"syntology":null},{"paper":"/paper/from-clip-to-dino-visual-encoders-shout-in","slug":"from-clip-to-dino-visual-encoders-shout-in","title":"From CLIP to DINO: Visual Encoders Shout in Multi-modal Large Language Models","date":"2023-10-13","arxiv_id":"2310.08825","n_code_links":1,"syntology":null},{"paper":null,"slug":"computational-pathology-at-health-system","title":"Computational Pathology at Health System Scale -- Self-Supervised Foundation Models from Three Billion Images","date":"2023-10-10","arxiv_id":"2310.07033","n_code_links":0,"syntology":null},{"paper":"/paper/what-does-stable-diffusion-know-about-the-3d","slug":"what-does-stable-diffusion-know-about-the-3d","title":"A General Protocol to Probe Large Vision Models for 3D Physical Understanding","date":"2023-10-10","arxiv_id":"2310.06836","n_code_links":1,"syntology":null},{"paper":null,"slug":"exploring-dino-emergent-properties-and","title":"Exploring DINO: Emergent Properties and Limitations for Synthetic Aperture Radar Imagery","date":"2023-10-05","arxiv_id":"2310.03513","n_code_links":0,"syntology":null},{"paper":"/paper/hard-view-selection-for-contrastive-learning","slug":"hard-view-selection-for-contrastive-learning","title":"Beyond Random Augmentations: Pretraining with Hard Views","date":"2023-10-05","arxiv_id":"2310.03940","n_code_links":2,"syntology":null},{"paper":null,"slug":"adapting-vision-foundation-models-for-plant","title":"Adapting Vision Foundation Models for Plant Phenotyping","date":"2023-10-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"d-3-fields-dynamic-3d-descriptor-fields-for","title":"D$^3$Fields: Dynamic 3D Descriptor Fields for Zero-Shot Generalizable Rearrangement","date":"2023-09-28","arxiv_id":"2309.16118","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-sam-based-solution-for-hierarchical","title":"A SAM-based Solution for Hierarchical Panoptic Segmentation of Crops and Weeds Competition","date":"2023-09-24","arxiv_id":"2309.13578","n_code_links":0,"syntology":null},{"paper":"/paper/dac-detr-divide-the-attention-layers-and","slug":"dac-detr-divide-the-attention-layers-and","title":"DAC-DETR: Divide the Attention Layers and Conquer","date":"2023-09-21","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/flsl-feature-level-self-supervised-learning","slug":"flsl-feature-level-self-supervised-learning","title":"FLSL: Feature-level Self-supervised Learning","date":"2023-09-21","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"lepard-learning-explicit-part-discovery-for","title":"LEPARD: Learning Explicit Part Discovery for 3D Articulated Shape Reconstruction","date":"2023-09-21","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/leveraging-in-the-wild-data-for-effective","slug":"leveraging-in-the-wild-data-for-effective","title":"Leveraging In-the-Wild Data for Effective Self-Supervised Pretraining in Speaker Recognition","date":"2023-09-21","arxiv_id":"2309.11730","n_code_links":1,"syntology":null},{"paper":"/paper/re-masked-autoencoders-are-small-scale-vision","slug":"re-masked-autoencoders-are-small-scale-vision","title":"[Re] Masked Autoencoders Are Small Scale Vision Learners: A Reproduction Under Resource Constraints","date":"2023-09-21","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"language-embedded-radiance-fields-for-zero","title":"Language Embedded Radiance Fields for Zero-Shot Task-Oriented Grasping","date":"2023-09-14","arxiv_id":"2309.07970","n_code_links":0,"syntology":null},{"paper":null,"slug":"leveraging-pretrained-image-text-models-for","title":"Leveraging Pretrained Image-text Models for Improving Audio-Visual Learning","date":"2023-09-08","arxiv_id":"2309.04628","n_code_links":0,"syntology":null},{"paper":null,"slug":"adapting-self-supervised-representations-to","title":"Adapting Self-Supervised Representations to Multi-Domain Setups","date":"2023-09-07","arxiv_id":"2309.03999","n_code_links":0,"syntology":null},{"paper":"/paper/masking-strategies-for-background-bias","slug":"masking-strategies-for-background-bias","title":"Masking Strategies for Background Bias Removal in Computer Vision Models","date":"2023-08-23","arxiv_id":"2308.12127","n_code_links":1,"syntology":null},{"paper":"/paper/emergent-correspondence-from-image-diffusion","slug":"emergent-correspondence-from-image-diffusion","title":"Emergent Correspondence from Image Diffusion","date":"2023-06-06","arxiv_id":"2306.03881","n_code_links":2,"syntology":{"ran":4,"of":6,"n_ran_checked":4,"n_instrument":0,"unverified":2,"pointer_only":2,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":null}}],"record_sha256":"8fcaf01f7ed93277c4b730f6749f41f5d7198bfe8bc3417cc2bdc7af00e13dfa","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}