{"list":"other","total":79,"rows":[{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"id":"1806.07572","title":"Neural Tangent Kernel: Convergence and Generalization in Neural Networks","created":"2018-06-20","cited_by_count":2621},{"id":"1512.04150","title":"Learning Deep Features for Discriminative Localization","created":"2015-12-14","cited_by_count":2436},{"id":"2103.17239","title":"Going deeper with Image Transformers","created":"2021-03-31","cited_by_count":764},{"id":"2205.08534","title":"Vision Transformer Adapter for Dense Predictions","created":"2022-05-17","cited_by_count":565},{"id":"1701.04128","title":"Understanding the Effective Receptive Field in Deep Convolutional Neural Networks","created":"2017-01-15","cited_by_count":553},{"id":"2209.08575","title":"SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentation","created":"2022-09-18","cited_by_count":252},{"id":"2206.06522","title":"LST: Ladder Side-Tuning for Parameter and Memory Efficient Transfer Learning","created":"2022-06-13","cited_by_count":230},{"id":"1406.2807","title":"The Secrets of Salient Object Segmentation","created":"2014-06-11","cited_by_count":200},{"id":"2103.04011","title":"Simultaneously Localize, Segment and Rank the Camouflaged Objects","created":"2021-03-06","cited_by_count":198},{"id":"1503.08663","title":"Visual Saliency Based on Multiscale Deep Features","created":"2015-03-30","cited_by_count":185},{"id":"2104.12099","title":"Visual Saliency Transformer","created":"2021-04-25","cited_by_count":175},{"id":"1904.09146","title":"Salient Object Detection in the Deep Learning Era: An In-Depth Survey","created":"2019-04-19","cited_by_count":164},{"id":"1712.02478","title":"Stacked Conditional Generative Adversarial Networks for Jointly Learning Shadow Detection and Shadow Removal","created":"2017-12-07","cited_by_count":161},{"id":"2203.02688","title":"Zoom In and Out: A Mixed-scale Triplet Network for Camouflaged Object Detection","created":"2022-03-05","cited_by_count":145},{"id":"2207.03620","title":"More ConvNets in the 2020s: Scaling up Kernels Beyond 51x51 using Sparsity","created":"2022-07-07","cited_by_count":142},{"id":"2001.06810","title":"See More, Know More: Unsupervised Video Object Segmentation with Co-Attention Siamese Networks","created":"2020-01-19","cited_by_count":138},{"id":"2009.14530","title":"Asymmetric Contextual Modulation for Infrared Small Target Detection","created":"2020-09-30","cited_by_count":138},{"id":"2106.00487","title":"Dense Nested Attention Network for Infrared Small Target Detection","created":"2021-06-01","cited_by_count":135},{"id":"2101.07663","title":"Salient Object Detection via Integrity Learning","created":"2021-01-19","cited_by_count":133},{"id":"2212.00968","title":"UIU-Net: U-Net in U-Net for Infrared Small Object Detection","created":"2022-12-02","cited_by_count":127},{"id":"2303.10883","title":"Explicit Visual Prompting for Low-Level Structure Segmentations","created":"2023-03-20","cited_by_count":114},{"id":"2203.03041","title":"Highly Accurate Dichotomous Image Segmentation","created":"2022-03-06","cited_by_count":110},{"id":"2012.08573","title":"Attentional Local Contrast Networks for Infrared Small Target Detection","created":"2020-12-15","cited_by_count":109},{"id":"2303.14816","title":"Feature Shrinkage Pyramid for Camouflaged Object Detection with Transformers","created":"2023-03-26","cited_by_count":87},{"id":"2203.11624","title":"High-resolution Iterative Feedback Network for Camouflaged Object Detection","created":"2022-03-22","cited_by_count":78},{"id":"2407.05848","title":"Wavelet Convolutions for Large Receptive Fields","created":"2024-07-08","cited_by_count":74},{"id":"1703.09157","title":"Reweighted Infrared Patch-Tensor Model With Both Non-Local and Local Priors for Single-Frame Small Target Detection","created":"2017-03-27","cited_by_count":73},{"id":"2403.19366","title":"Infrared Small Target Detection with Scale and Location Sensitivity","created":"2024-03-28","cited_by_count":73},{"id":"2403.07392","title":"ViT-CoMer: Vision Transformer with Convolutional Multi-scale Feature Interaction for Dense Predictions","created":"2024-03-12","cited_by_count":66},{"id":"2311.15599","title":"UniRepLKNet: A Universal Perception Large-Kernel ConvNet for Audio, Video, Point Cloud, Time-Series and Image Recognition","created":"2023-11-27","cited_by_count":64},{"id":"2408.08870","title":"SAM2-UNet: Segment Anything 2 Makes Strong Encoder for Natural and Medical Image Segmentation","created":"2024-08-16","cited_by_count":64},{"id":"2401.15583","title":"SCTransNet: Spatial-channel Cross Transformer Network for Infrared Small Target Detection","created":"2024-01-28","cited_by_count":62},{"id":"2212.06570","title":"CamoFormer: Masked Separable Attention for Camouflaged Object Detection","created":"2022-12-10","cited_by_count":58},{"id":"2008.04254","title":"Informative Dropout for Robust Representation Learning: A Shape-bias Perspective","created":"2020-08-10","cited_by_count":57},{"id":"2403.19967","title":"Rewrite the Stars","created":"2024-03-29","cited_by_count":55},{"id":"2208.08738","title":"RFLA: Gaussian Receptive Field based Label Assignment for Tiny Object Detection","created":"2022-08-18","cited_by_count":51},{"id":"2209.13756","title":"MTU-Net: Multi-level TransUNet for Space-based Infrared Tiny Ship Detection","created":"2022-09-28","cited_by_count":48},{"id":"2407.07520","title":"IRSAM: Advancing Segment Anything Model for Infrared Small Target Detection","created":"2024-07-10","cited_by_count":46},{"id":"2311.00917","title":"RPCANet: Deep Unfolding RPCA Based Infrared Small Target Detection","created":"2023-11-02","cited_by_count":44},{"id":"2403.11735","title":"LSKNet: A Foundation Lightweight Backbone for Remote Sensing","created":"2024-03-18","cited_by_count":44},{"id":"1809.01826","title":"Connecting Image Denoising and High-Level Vision Tasks via Deep Learning","created":"2018-09-06","cited_by_count":39},{"id":"2406.09627","title":"RobustSAM: Segment Anything Robustly on Degraded Images","created":"2024-06-13","cited_by_count":36},{"id":"2408.08345","title":"5%>100%: Breaking Performance Shackles of Full Fine-Tuning on Visual Recognition Tasks","created":"2024-08-15","cited_by_count":34},{"id":"2412.16986","title":"Pinwheel-shaped Convolution and Scale-based Dynamic Loss for Infrared Small Target Detection","created":"2024-12-22","cited_by_count":34},{"id":"2409.17874","title":"DarkSAM: Fooling Segment Anything Model to Segment Nothing","created":"2024-09-26","cited_by_count":32},{"id":"2408.04326","title":"Multi-Scale and Detail-Enhanced Segment Anything Model for Salient Object Detection","created":"2024-08-08","cited_by_count":30},{"id":"2212.11005","title":"Revisiting Residual Networks for Adversarial Robustness: An Architectural Perspective","created":"2022-12-21","cited_by_count":28},{"id":"2310.11725","title":"VST++: Efficient and Stronger Visual Saliency Transformer","created":"2023-10-18","cited_by_count":28},{"id":"2406.14482","title":"Visible-Thermal Tiny Object Detection: A Benchmark Dataset and Baselines","created":"2024-06-20","cited_by_count":27},{"id":"2308.14316","title":"UniPT: Universal Parallel Tuning for Transfer Learning with Efficient Parameter and Memory","created":"2023-08-28","cited_by_count":26},{"id":"2309.01439","title":"Large Separable Kernel Attention: Rethinking the Large Kernel Attention Design in CNN","created":"2023-09-04","cited_by_count":25},{"id":"2306.09729","title":"Parameter-efficient is not sufficient: Exploring Parameter, Memory, and Time Efficient Adapter Tuning for Dense Predictions","created":"2023-06-16","cited_by_count":24},{"id":"2404.04996","title":"Fantastic Animals and Where to Find Them: Segment Any Marine Animal with Dual SAM","created":"2024-04-07","cited_by_count":23},{"id":"2306.17075","title":"Detect Any Deepfakes: Segment Anything Meets Face Forgery Detection and Localization","created":"2023-06-29","cited_by_count":20},{"id":"2408.15020","title":"Hierarchical Graph Interaction Transformer with Dynamic Token Clustering for Camouflaged Object Detection","created":"2024-08-27","cited_by_count":18},{"id":"2305.18476","title":"Explicit Visual Prompting for Universal Foreground Segmentations","created":"2023-05-29","cited_by_count":17},{"id":"2307.14052","title":"Unite-Divide-Unite: Joint Boosting Trunk and Structure for High-accuracy Dichotomous Image Segmentation","created":"2023-07-26","cited_by_count":17},{"id":"2309.13646","title":"ILNet: Low-level Matters for Salient Infrared Small Target Detection","created":"2023-09-24","cited_by_count":17},{"id":"2404.15700","title":"MAS-SAM: Segment Any Marine Animal with Aggregated Features","created":"2024-04-24","cited_by_count":15},{"id":"2409.12421","title":"Frequency-Guided Spatial Adaptation for Camouflaged Object Detection","created":"2024-09-19","cited_by_count":15},{"id":"2407.13133","title":"FocusDiffuser: Perceiving Local Disparities for Camouflaged Object Detection","created":"2024-07-18","cited_by_count":14},{"id":"2211.15644","title":"Efficient Mirror Detection via Multi-level Heterogeneous Learning","created":"2022-11-28","cited_by_count":13},{"id":"2402.02046","title":"TCI-Former: Thermal Conduction-Inspired Transformer for Infrared Small Target Detection","created":"2024-02-03","cited_by_count":12},{"id":"2207.06332","title":"Symmetry-Aware Transformer-based Mirror Detection","created":"2022-07-13","cited_by_count":11},{"id":"2404.16385","title":"Efficiency in Focus: LayerNorm as a Catalyst for Fine-tuning Medical Visual Language Pre-trained Models","created":"2024-04-25","cited_by_count":11},{"id":"2311.11465","title":"Understanding Segment Anything Model: SAM is Biased Towards Texture Rather than Shape","created":"2023-06-03","cited_by_count":10},{"id":"2401.09109","title":"Trapped in texture bias? A large scale comparison of deep instance segmentation","created":"2024-01-17","cited_by_count":10},{"id":"2311.16835","title":"Unified-modal Salient Object Detection via Adaptive Prompt Learning","created":"2023-11-28","cited_by_count":9},{"id":"2401.01752","title":"FullLoRA: Efficiently Boosting the Robustness of Pretrained Vision Transformers","created":"2024-01-03","cited_by_count":9},{"id":"2503.08043","title":"Structural and Statistical Texture Knowledge Distillation and Learning for Segmentation","created":"2025-03-11","cited_by_count":9},{"id":"2310.18788","title":"PrObeD: Proactive Object Detection Wrapper","created":"2023-10-28","cited_by_count":7},{"id":"2405.16555","title":"Building Vision Models upon Heat Conduction","created":"2024-05-26","cited_by_count":7},{"id":"2408.01835","title":"TS-SAM: Fine-Tuning Segment-Anything Model for Downstream Tasks","created":"2024-08-03","cited_by_count":5},{"id":"2312.01741","title":"SRSNetwork: Siamese Reconstruction-Segmentation Networks based on Dynamic-Parameter Convolution","created":"2023-12-04","cited_by_count":4},{"id":"2403.11792","title":"SETA: Semantic-Aware Token Augmentation for Domain Generalization","created":"2024-03-18","cited_by_count":3},{"id":"2406.13445","title":"Lost in UNet: Improving Infrared Small Target Detection by Underappreciated Local Features","created":"2024-06-19","cited_by_count":3},{"id":"2412.19676","title":"Optimizing Local-Global Dependencies for Accurate 3D Human Pose Estimation","created":"2024-12-27","cited_by_count":3}],"next_cursor":null}