Papers with Code 아카이브

Object Discovery

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

하위 태스크: 0
평가표: 0
보존된 평가 기록: 0

Object Discovery is the task of identifying previously unseen objects.

Source: Unsupervised Object Discovery and Segmentation of RGBD-images

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/hermannsblum/scim

공식 코드

SCIM: Simultaneous Clustering, Inference, and Mapping for Open-World Semantic Scene Understanding

https://github.com/huyvvo/LOD

공식 코드

Large-Scale Unsupervised Object Discovery

https://github.com/huyvvo/OSD

공식 코드

Unsupervised Image Matching and Object Discovery as Optimization

https://github.com/huyvvo/rOSD

공식 코드

Toward unsupervised, multi-object discovery in large-scale image collections

https://github.com/jason-lim26/dipex

공식 코드

DiPEx: Dispersing Prompt Expansion for Class-Agnostic Object Detection

https://github.com/jcoreyes/OP3

공식 코드

Entity Abstraction in Visual Model-Based Reinforcement Learning

https://github.com/jinhseo/od-wscl

공식 코드

Object Discovery via Contrastive Learning for Weakly Supervised Object Detection

https://github.com/jinyangyuan/acquired-deep-impressions

공식 코드

Knowledge-Guided Object Discovery with Acquired Deep Impressions

https://github.com/k4ntz/moc

공식 코드

Boosting Object Representation Learning via Motion and Object Continuity

https://github.com/k4ntz/oc_atari

공식 코드

OCAtari: Object-Centric Atari 2600 Reinforcement Learning Environments

https://github.com/katadam/objectscanmove

공식 코드

Objects Can Move: 3D Change Detection by Geometric Transformation Constistency

https://github.com/laurimi/ddcrp-gibbs

공식 코드

Object proposal generation applying the distance dependent Chinese restaurant process

https://github.com/loewex/complexautoencoder

공식 코드

Complex-Valued Autoencoders for Object Discovery

https://github.com/martius-lab/videosaur

공식 코드

Object-Centric Learning for Real-World Videos by Predicting Temporal Feature Similarities

https://github.com/mcahny/object_localization_network

공식 코드

Learning Open-World Object Proposals without Learning to Classify

https://github.com/mihirp1998/Slot-TTA

공식 코드

Test-time Adaptation with Slot-Centric Models

https://github.com/monniert/dti-sprites

공식 코드

Unsupervised Layered Image Decomposition into Object Prototypes

https://github.com/npucvr/wscuod

공식 코드

Weakly-supervised Contrastive Learning for Unsupervised Object Discovery

https://github.com/nust-machine-intelligence-laboratory/ktse

공식 코드

Knowledge Transfer with Simulated Inter-Image Erasing for Weakly Supervised Semantic Segmentation

https://github.com/ppengtang/dpl

공식 코드

Deep Patch Learning for Weakly Supervised Object Classification and Discovery

https://github.com/rishavpramanik/maskedmultiqueryslot

공식 코드

Masked Multi-Query Slot Attention for Unsupervised Object Discovery

https://github.com/robertwyq/lsmol

공식 코드

4D Unsupervised Object Discovery

https://github.com/ruizhaogit/MNIST-GuessNumber

공식 코드

Efficient Dialog Policy Learning via Positive Memory Retention

https://github.com/ruizhaogit/PositiveMemoryRetention

공식 코드

Efficient Dialog Policy Learning via Positive Memory Retention

https://github.com/shahaf-arica/cuvler

공식 코드

CuVLER: Enhanced Unsupervised Object Discoveries through Exhaustive Self-Supervised Transformers

https://github.com/shvdiwnkozbw/smtc

공식 코드

Semantics Meets Temporal Correspondence: Self-supervised Object-centric Learning in Videos

https://github.com/shvdiwnkozbw/ssl-uvos

공식 코드

Betrayed by Attention: A Simple yet Effective Approach for Self-supervised Video Object Segmentation

https://github.com/silky1708/locate

공식 코드

LOCATE: Self-supervised Object Discovery via Flow-guided Graph-cut and Bootstrapped Self-training

https://github.com/tedlentsch/union

공식 코드

UNION: Unsupervised 3D Object Detection using Object Appearance-based Pseudo-Classes

https://github.com/ut-amrl/coda-devkit

공식 코드

Towards Robust Robot 3D Perception in Urban Environments: The UT Campus Object Dataset

https://github.com/ut-amrl/coda-models

공식 코드

Towards Robust Robot 3D Perception in Urban Environments: The UT Campus Object Dataset

https://github.com/uvavision/chair-segments

공식 코드

Chair Segments: A Compact Benchmark for the Study of Object Segmentation

https://github.com/valeoai/LOST

공식 코드

Localizing Objects with Self-Supervised Transformers and no Labels

https://github.com/valeoai/found

공식 코드

Unsupervised Object Localization: Observing the Background to Discover Objects

https://github.com/valeoai/scalr

공식 코드

Three Pillars improving Vision Foundation Model Distillation for Lidar

https://github.com/vdigpku/formula

공식 코드

Foreground Guidance and Multi-Layer Feature Fusion for Unsupervised Object Discovery with Transformers

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.