Papers with Code 아카이브
Object Localization
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 5
- 평가표
- 18
- 보존된 평가 기록
- 51
Object Localization is the task of locating an instance of a particular object category in an image, typically by specifying a tightly cropped bounding box centered on the instance. An object proposal specifies a candidate bounding box, and an object proposal is said to be a correct localization if it sufficiently overlaps a human-labeled “ground-truth” bounding box for the given object. In the literature, the “Object Localization” task is to locate one instance of an object category, whereas “object detection” focuses on locating all instances of a category in a given image.
Source: Fast On-Line Kernel Density Estimation for Active Object Localization
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/hyliang96/CSGCNN
공식 코드Training Interpretable Convolutional Neural Networks by Differentiating Class-specific Filters
https://github.com/hzzone/pseco
공식 코드Point, Segment and Count: A Generalized Framework for Object Counting
https://github.com/ieee8023/countception
공식 코드Count-ception: Counting by Fully Convolutional Redundant Counting
https://github.com/jacobswan1/MTG-pytorch
공식 코드https://github.com/javiribera/locating-objects-without-bboxes
공식 코드https://github.com/jazzcharles/cream
공식 코드CREAM: Weakly Supervised Object Localization via Class RE-Activation Mapping
https://github.com/jbhuang0604/WSL
공식 코드Progressive Representation Adaptation for Weakly Supervised Object Localization
https://github.com/jeff-zilence/transgeo2022
공식 코드TransGeo: Transformer Is All You Need for Cross-view Image Geo-localization
https://github.com/jeromerony/survey_wsl_histology
공식 코드https://github.com/jerpelhan/GeCo
공식 코드A Novel Unified Architecture for Low-Shot Counting by Detection and Segmentation
https://github.com/jonathanventura/p1ac
공식 코드P1AC: Revisiting Absolute Pose From a Single Affine Correspondence
https://github.com/kai3316/yolic-labeling
공식 코드YOLIC: An Efficient Method for Object Localization and Classification on Edge Devices
https://github.com/karanwxliaa/underwater-trash-detection
공식 코드Deep Learning Innovations for Underwater Waste Detection: An In-Depth Analysis
https://github.com/kkanshul/Hide-and-Seek
공식 코드Hide-and-Seek: A Data Augmentation Technique for Weakly-Supervised Localization and Beyond
https://github.com/krishnap25/casimir
공식 코드https://github.com/lachlants/denet
공식 코드DeNet: Scalable Real-time Object Detection with Directed Sparse Sampling
https://github.com/layumi/University1652-Baseline
공식 코드University-1652: A Multi-view Multi-source Benchmark for Drone-based Geo-localization
https://github.com/linjiatai/broadcam
공식 코드BroadCAM: Outcome-agnostic Class Activation Mapping for Small-scale Weakly Supervised Applications
https://github.com/litingfeng/localization-by-ordembed
공식 코드Learning Transferable Reward for Query Object Localization with Policy Adaptation
https://github.com/lizhecheng02/vlm4font
공식 코드Texture or Semantics? Vision-Language Models Get Lost in Font Recognition
https://github.com/loris2222/ExplainingMLLMs
공식 코드Explaining Multi-modal Large Language Models by Analyzing their Vision Perception
https://github.com/loris2222/concept-visualization
공식 코드Concept Visualization: Explaining the CLIP Multi-modal Embedding Using WordNet
https://github.com/luiszeni/Boosted-OICR
공식 코드Distilling Knowledge from Refinement in Multiple Instance Detection Networks
https://github.com/lwzeng/GC-Net
공식 코드https://github.com/mcahny/object_localization_network
공식 코드Learning Open-World Object Proposals without Learning to Classify
https://github.com/mguti97/soccernet-v3d
공식 코드SoccerNet-v3D: Leveraging Sports Broadcast Replays for 3D Scene Understanding
https://github.com/microsoft/UniTAB
공식 코드UniTAB: Unifying Text and Box Outputs for Grounded Vision-Language Modeling
https://github.com/microsoft/YOLaT-VectorGraphicsRecognition
공식 코드https://github.com/minghanqin/LangSplat
공식 코드https://github.com/minhlong94/random-mixup
공식 코드Expeditious Saliency-guided Mix-up through Random Gradient Thresholding
https://github.com/mischad/chest-distillation
공식 코드Trade-offs in Fine-tuned Diffusion Models Between Accuracy and Interpretability
https://github.com/mlzxy/flowdino
공식 코드Optical Flow boosts Unsupervised Localization and Segmentation
https://github.com/monjurulkarim/rol_dataset
공식 코드https://github.com/mxbh/robust_object_detection
공식 코드https://github.com/naver-ai/calm
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.