{"list":"other","total":58,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"2405.21060","title":"Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality","created":"2024-05-31","cited_by_count":1336},{"id":"1805.04687","title":"BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning","created":"2018-05-12","cited_by_count":1288},{"id":"1608.02192","title":"Playing for Data: Ground Truth from Computer Games","created":"2016-08-07","cited_by_count":818},{"id":"2201.03546","title":"Language-driven Semantic Segmentation","created":"2022-01-10","cited_by_count":717},{"id":"2112.01071","title":"Extract Free Dense Labels from CLIP","created":"2021-12-02","cited_by_count":583},{"id":"2210.04150","title":"Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP","created":"2022-10-09","cited_by_count":565},{"id":"2303.11331","title":"EVA-02: A Visual Representation for Neon Genesis","created":"2023-03-20","cited_by_count":381},{"id":"2302.12242","title":"Side Adapter Network for Open-Vocabulary Semantic Segmentation","created":"2023-02-23","cited_by_count":300},{"id":"2112.14757","title":"A Simple Baseline for Open-Vocabulary Semantic Segmentation with Pre-trained Vision-language Model","created":"2021-12-29","cited_by_count":223},{"id":"2303.11797","title":"CAT-Seg: Cost Aggregation for Open-Vocabulary Semantic Segmentation","created":"2023-03-21","cited_by_count":219},{"id":"2312.01597","title":"SCLIP: Rethinking Self-Attention for Dense Vision-Language Inference","created":"2023-12-04","cited_by_count":170},{"id":"2211.14813","title":"SegCLIP: Patch Aggregation with Learnable Centers for Open-Vocabulary Semantic Segmentation","created":"2022-11-27","cited_by_count":164},{"id":"2104.14812","title":"SegmentMeIfYouCan: A Benchmark for Anomaly Segmentation","created":"2021-04-30","cited_by_count":150},{"id":"1904.07595","title":"Detecting the Unexpected via Image Resynthesis","created":"2019-04-16","cited_by_count":137},{"id":"2310.01403","title":"CLIPSelf: Vision Transformer Distills Itself for Open-Vocabulary Dense Prediction","created":"2023-10-02","cited_by_count":118},{"id":"1609.04653","title":"Lost and Found: Detecting Small Road Hazards for Self-Driving Vehicles","created":"2016-09-15","cited_by_count":117},{"id":"2407.12442","title":"ClearCLIP: Decomposing CLIP Representations for Dense Vision-Language Inference","created":"2024-07-17","cited_by_count":113},{"id":"2408.04883","title":"ProxyCLIP: Proxy Attention Improves CLIP for Open-Vocabulary Segmentation","created":"2024-08-09","cited_by_count":111},{"id":"2103.05445","title":"Pixel-wise Anomaly Detection in Complex Driving Scenes","created":"2021-03-09","cited_by_count":109},{"id":"2312.12359","title":"CLIP-DINOiser: Teaching CLIP a few DINO tricks for open-vocabulary semantic segmentation","created":"2023-12-19","cited_by_count":96},{"id":"2312.00878","title":"Grounding Everything: Emerging Localization Properties in Vision-Language Transformers","created":"2023-12-01","cited_by_count":91},{"id":"2111.12264","title":"Pixel-wise Energy-biased Abstention Learning for Anomaly Segmentation on Complex Urban Driving Scenes","created":"2021-11-24","cited_by_count":83},{"id":"2312.04265","title":"Stronger, Fewer, & Superior: Harnessing Vision Foundation Models for Domain Generalized Semantic Segmentation","created":"2023-12-07","cited_by_count":83},{"id":"2210.09996","title":"Perceptual Grouping in Contrastive Vision-Language Models","created":"2022-10-18","cited_by_count":82},{"id":"2412.16334","title":"DINOv2 Meets Text: A Unified Framework for Image- and Pixel-Level Vision-Language Alignment","created":"2024-12-20","cited_by_count":79},{"id":"2207.04892","title":"Adversarial Style Augmentation for Domain Generalized Urban-Scene Segmentation","created":"2022-07-11","cited_by_count":70},{"id":"2312.07661","title":"CLIP as RNN: Segment Countless Visual Concepts without Training Endeavor","created":"2023-12-12","cited_by_count":69},{"id":"2407.08268","title":"Explore the Potential of CLIP for Training-Free Open Vocabulary Semantic Segmentation","created":"2024-07-11","cited_by_count":61},{"id":"2211.14512","title":"Residual Pattern Learning for Pixel-wise Out-of-Distribution Detection in Semantic Segmentation","created":"2022-11-26","cited_by_count":55},{"id":"2312.04089","title":"Open-Vocabulary Segmentation with Semantic-Assisted Calibration","created":"2023-12-07","cited_by_count":49},{"id":"2312.03048","title":"DGInStyle: Domain-Generalizable Semantic Segmentation with Image Diffusion Models and Stylized Semantic Control","created":"2023-12-05","cited_by_count":45},{"id":"2404.06542","title":"Training-Free Open-Vocabulary Segmentation with Offline Diffusion-Augmented Prototype Generation","created":"2024-04-09","cited_by_count":44},{"id":"2408.00744","title":"Collaborative Vision-Text Representation Optimizing for Open-Vocabulary Segmentation","created":"2024-08-01","cited_by_count":41},{"id":"2212.00979","title":"PASTA: Proportional Amplitude Spectrum Training Augmentation for Syn-to-Real Domain Generalization","created":"2022-12-02","cited_by_count":39},{"id":"2408.04961","title":"In Defense of Lazy Visual Grounding for Open-Vocabulary Semantic Segmentation","created":"2024-08-09","cited_by_count":38},{"id":"2411.10086","title":"CorrCLIP: Reconstructing Patch Correlations in CLIP for Open-Vocabulary Semantic Segmentation","created":"2024-11-15","cited_by_count":34},{"id":"2505.04410","title":"DeCLIP: Decoupled Learning for Open-Vocabulary Dense Perception","created":"2025-05-07","cited_by_count":33},{"id":"2403.07369","title":"Textual Knowledge Matters: Cross-Modality Co-Teaching for Generalized Visual Class Discovery","created":"2024-03-12","cited_by_count":31},{"id":"2307.00371","title":"Learning Content-enhanced Mask Transformer for Domain Generalized Urban-Scene Segmentation","created":"2023-07-01","cited_by_count":30},{"id":"2412.04077","title":"SoMA: Singular Value Decomposed Minor Components Adaptation for Domain Generalizable Representation Learning","created":"2024-12-05","cited_by_count":24},{"id":"2406.07661","title":"ROADWork: A Dataset and Benchmark for Learning to Recognize, Observe, Analyze and Drive Through Work Zones","created":"2024-06-11","cited_by_count":22},{"id":"2407.18568","title":"Learning Spectral-Decomposed Tokens for Domain Generalized Semantic Segmentation","created":"2024-07-26","cited_by_count":22},{"id":"2311.16516","title":"Segment Every Out-of-Distribution Object","created":"2023-11-27","cited_by_count":21},{"id":"2407.09033","title":"Textual Query-Driven Mask Transformer for Domain Generalized Segmentation","created":"2024-07-12","cited_by_count":21},{"id":"2410.19213","title":"Prototypical Hash Encoding for On-the-Fly Fine-Grained Category Discovery","created":"2024-10-24","cited_by_count":21},{"id":"2412.04533","title":"Mask-Adapter: The Devil is in the Masks for Open-Vocabulary Segmentation","created":"2024-12-05","cited_by_count":20},{"id":"2411.14723","title":"Effective SAM Combination for Open-Vocabulary Semantic Segmentation","created":"2024-11-22","cited_by_count":17},{"id":"2503.17940","title":"FisherTune: Fisher-Guided Robust Tuning of Vision Foundation Models for Domain Generalized Segmentation","created":"2025-03-23","cited_by_count":16},{"id":"2504.02328","title":"Refining CLIP's Spatial Awareness: A Visual-Centric Perspective","created":"2025-04-03","cited_by_count":13},{"id":"2412.15541","title":"ChangeDiff: A Multi-Temporal Change Detection Data Generator with Flexible Text Prompts via Diffusion Model","created":"2024-12-20","cited_by_count":10},{"id":"2412.06244","title":"Unbiased Region-Language Alignment for Open-Vocabulary Dense Prediction","created":"2024-12-09","cited_by_count":9},{"id":"2312.06331","title":"Semantic Connectivity-Driven Pseudo-labeling for Cross-domain Segmentation","created":"2023-12-11","cited_by_count":3}],"next_cursor":null}