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/nexer8/se3d
공식 코드SE3D: A Framework For Saliency Method Evaluation In 3D Imaging
https://github.com/nupurkmr9/Attributional-Robustness
공식 코드Attributional Robustness Training using Input-Gradient Spatial Alignment
https://github.com/nust-machine-intelligence-laboratory/ssc
공식 코드Spatial Structure Constraints for Weakly Supervised Semantic Segmentation
https://github.com/nyukat/GMIC
공식 코드https://github.com/opengvlab/all-seeing
공식 코드The All-Seeing Project V2: Towards General Relation Comprehension of the Open World
https://github.com/opengvlab/visionllm
공식 코드https://github.com/opennlplab/acr_wsss
공식 코드All-pairs Consistency Learning for Weakly Supervised Semantic Segmentation
https://github.com/qq456cvb/oneloc
공식 코드https://github.com/rashaalshawi/dual-attention-u-net-with-feature-infusion-pushing-the-boundaries-of-multiclass-defect-segmentation
공식 코드Dual Attention U-Net with Feature Infusion: Pushing the Boundaries of Multiclass Defect Segmentation
https://github.com/raymondyeh07/tv_layers_for_cv
공식 코드https://github.com/rd20karim/mb-ores
공식 코드MB-ORES: A Multi-Branch Object Reasoner for Visual Grounding in Remote Sensing
https://github.com/real-stanford/cow
공식 코드CoWs on Pasture: Baselines and Benchmarks for Language-Driven Zero-Shot Object Navigation
https://github.com/rishavpramanik/maskedmultiqueryslot
공식 코드Masked Multi-Query Slot Attention for Unsupervised Object Discovery
https://github.com/robertwyq/panoocc
공식 코드PanoOcc: Unified Occupancy Representation for Camera-based 3D Panoptic Segmentation
https://github.com/roboflow-ai/roboflow-100-benchmark
공식 코드Roboflow 100: A Rich, Multi-Domain Object Detection Benchmark
https://github.com/rozumden/deblatting_python
공식 코드Sub-frame Appearance and 6D Pose Estimation of Fast Moving Objects
https://github.com/rstrudel/rlbc
공식 코드Learning to Augment Synthetic Images for Sim2Real Policy Transfer
https://github.com/ryh1218/fsol
공식 코드https://github.com/ryylcc/owsol
공식 코드https://github.com/sangminwoo/svol
공식 코드https://github.com/saurav-31/vitol
공식 코드ViTOL: Vision Transformer for Weakly Supervised Object Localization
https://github.com/sbelharbi/colo-cam
공식 코드CoLo-CAM: Class Activation Mapping for Object Co-Localization in Weakly-Labeled Unconstrained Videos
https://github.com/sbelharbi/fcam-wsol
공식 코드F-CAM: Full Resolution Class Activation Maps via Guided Parametric Upscaling
https://github.com/sbelharbi/tcam-wsol-video
공식 코드TCAM: Temporal Class Activation Maps for Object Localization in Weakly-Labeled Unconstrained Videos
https://github.com/sbelharbi/wsol-min-max-entropy-interpretability
공식 코드Min-max Entropy for Weakly Supervised Pointwise Localization
https://github.com/seqam-lab/alwod
공식 코드ALWOD: Active Learning for Weakly-Supervised Object Detection
https://github.com/shakeebmurtaza/TrCAM
공식 코드Leveraging Transformers for Weakly Supervised Object Localization in Unconstrained Videos
https://github.com/shakeebmurtaza/dips
공식 코드https://github.com/shakeebmurtaza/tedloc
공식 코드TeD-Loc: Text Distillation for Weakly Supervised Object Localization
https://github.com/shakeebmurtaza/wsol_model_selection
공식 코드A Realistic Protocol for Evaluation of Weakly Supervised Object Localization
https://github.com/shantanuj/tdam_top_down_attention_module
공식 코드TDAM: Top-Down Attention Module for Contextually Guided Feature Selection in CNNs
https://github.com/shaofeifei11/CI-CAM
공식 코드Improving Weakly-supervised Object Localization via Causal Intervention
https://github.com/shaofeifei11/kd-ci-cam
공식 코드Knowledge-guided Causal Intervention for Weakly-supervised Object Localization
https://github.com/shiwt03/muster
공식 코드MUSTER: A Multi-scale Transformer-based Decoder for Semantic Segmentation
https://github.com/shiwt03/uperformer
공식 코드MUSTER: A Multi-scale Transformer-based Decoder for Semantic Segmentation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.