Papers with Code 아카이브

Object Recognition

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

하위 태스크: 3
평가표: 9
보존된 평가 기록: 31

Object recognition is a computer vision technique for detecting + classifying objects in images or videos. Since this is a combined task of object detection plus image classification, the state-of-the-art tables are recorded for each component task here and here.

<span style="color:grey; opacity: 0.6">( Image credit: Tensorflow Object Detection API )</span>

코드

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

https://github.com/deepmind/ssl_hsic

공식 코드

Self-Supervised Learning with Kernel Dependence Maximization

https://github.com/dfki-av/mikasa-3dvg

공식 코드

MiKASA: Multi-Key-Anchor & Scene-Aware Transformer for 3D Visual Grounding

https://github.com/dgarreau/image_lime_theory

공식 코드

What does LIME really see in images?

https://github.com/dgl-prc/rnn2automata

공식 코드

Towards Interpreting Recurrent Neural Networks through Probabilistic Abstraction

https://github.com/dicarlolab/cornet

공식 코드

Brain-Like Object Recognition with High-Performing Shallow Recurrent ANNs

https://github.com/dicarlolab/neurips2019

공식 코드

Brain-Like Object Recognition with High-Performing Shallow Recurrent ANNs

https://github.com/dicarlolab/vonenet

공식 코드

Matching the Neuronal Representations of V1 is Necessary to Improve Robustness in CNNs with V1-like Front-ends

https://github.com/disen-hu/fasterrcnn_fpn_dcn

공식 코드

Object recognition in atmospheric turbulence scenes

https://github.com/divadi/detmatch

공식 코드

DetMatch: Two Teachers are Better Than One for Joint 2D and 3D Semi-Supervised Object Detection

https://github.com/dkoguciuk/ensemble_learning_for_point_clouds

공식 코드

3D Object Recognition with Ensemble Learning --- A Study of Point Cloud-Based Deep Learning Models

https://github.com/dlr-rm/recall

공식 코드

RECALL: Rehearsal-free Continual Learning for Object Classification

https://github.com/doctor-public-submission/DOCTOR

공식 코드

DOCTOR: A Simple Method for Detecting Misclassification Errors

https://github.com/easezyc/deep-transfer-learning

공식 코드

Deep Subdomain Adaptation Network for Image Classification

https://github.com/easywalk-prin/opennav

공식 코드

OpenNav: Efficient Open Vocabulary 3D Object Detection for Smart Wheelchair Navigation

https://github.com/eeyhsong/nice-eeg

공식 코드

Decoding Natural Images from EEG for Object Recognition

https://github.com/eigenailab/Element-Wise-Zero-Shot-Image-Recognition

공식 코드

On the Element-Wise Representation and Reasoning in Zero-Shot Image Recognition: A Systematic Survey

https://github.com/emanuelevivoli/cdf

공식 코드

Comics Datasets Framework: Mix of Comics datasets for detection benchmarking

https://github.com/eminorhan/human-ssl

공식 코드

How much human-like visual experience do current self-supervised learning algorithms need in order to achieve human-level object recognition?

https://github.com/eminorhan/humanlike-vits

공식 코드

Scaling may be all you need for achieving human-level object recognition capacity with human-like visual experience

https://github.com/eminorhan/video-models

공식 코드

Self-supervised learning of video representations from a child's perspective

https://github.com/epflneuroailab/scaling-primate-vvs

공식 코드

Scaling Laws for Task-Optimized Models of the Primate Visual Ventral Stream

https://github.com/eric-mitchell/macaw

공식 코드

Offline Meta-Reinforcement Learning with Advantage Weighting

https://github.com/ethliup/SelfDeblur

공식 코드

Self-Supervised Linear Motion Deblurring

https://github.com/ethz-asl/lcd

공식 코드

LCD -- Line Clustering and Description for Place Recognition

https://github.com/eugleo/vista-dataset

공식 코드

ViSTa Dataset: Do vision-language models understand sequential tasks?

https://github.com/evocargo/lidar-annotation-is-all-you-need

공식 코드

Lidar Annotation Is All You Need

https://github.com/explain3d/exp-one-point-atk-pc

공식 코드

Explainability-Aware One Point Attack for Point Cloud Neural Networks

https://github.com/facebookresearch/DepthContrast

공식 코드

Self-Supervised Pretraining of 3D Features on any Point-Cloud

https://github.com/facebookresearch/dollarstreet_factors

공식 코드

Pinpointing Why Object Recognition Performance Degrades Across Income Levels and Geographies

https://github.com/facebookresearch/omni3d

공식 코드

Omni3D: A Large Benchmark and Model for 3D Object Detection in the Wild

https://github.com/facebookresearch/unibench

공식 코드

UniBench: Visual Reasoning Requires Rethinking Vision-Language Beyond Scaling

https://github.com/fanconic/this-does-not-look-like-that

공식 코드

This Looks Like That... Does it? Shortcomings of Latent Space Prototype Interpretability in Deep Networks

https://github.com/fate3439/dscnn

공식 코드

Dominant Set Clustering and Pooling for Multi-View 3D Object Recognition

https://github.com/flytxtds/scene-recognition

공식 코드

Scene Recognition by Combining Local and Global Image Descriptors

https://github.com/fmcarlucci/JigenDG

공식 코드

Domain Generalization by Solving Jigsaw Puzzles

https://github.com/fpastorm/lstm-haptic-fusion

공식 코드

Bayesian and Neural Inference on LSTM-based Object Recognition from Tactile and Kinesthetic Information

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