Papers with Code 아카이브

Fine-Grained Image Classification

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

하위 태스크: 1
평가표: 35
보존된 평가 기록: 374

Fine-Grained Image Classification is a task in computer vision where the goal is to classify images into subcategories within a larger category. For example, classifying different species of birds or different types of flowers. This task is considered to be fine-grained because it requires the model to distinguish between subtle differences in visual appearance and patterns, making it more challenging than regular image classification tasks.

<span style="color:grey; opacity: 0.6">( Image credit: Looking for the Devil in the Details )</span>

코드

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

https://github.com/anguyen8/nearest-neighbor-XAI

공식 코드

PCNN: Probable-Class Nearest-Neighbor Explanations Improve Fine-Grained Image Classification Accuracy for AIs and Humans

https://github.com/anguyen8/visual-correspondence-xai

공식 코드

Visual correspondence-based explanations improve AI robustness and human-AI team accuracy

https://github.com/apple2373/MetaIRNet

공식 코드

Meta-Reinforced Synthetic Data for One-Shot Fine-Grained Visual Recognition

https://github.com/archiplab-linfengzhang/contrastive-deep-supervision

공식 코드

Contrastive Deep Supervision

https://github.com/ardhendubehera/sr-gnn

공식 코드

SR-GNN: Spatial Relation-aware Graph Neural Network for Fine-Grained Image Categorization

https://github.com/bfshi/toast

공식 코드

TOAST: Transfer Learning via Attention Steering

https://github.com/boa2004plaust/vimd

공식 코드

Vision Mamba Distillation for Low-resolution Fine-grained Image Classification

https://github.com/bytedance/TWIST

공식 코드

Self-Supervised Learning by Estimating Twin Class Distributions

https://github.com/chaomaer/FBSD

공식 코드

Feature Boosting, Suppression, and Diversification for Fine-Grained Visual Classification

https://github.com/chengqingli/ficnet

공식 코드

Few-shot Fine-grained Image Classification via Multi-Frequency Neighborhood and Double-cross Modulation

https://github.com/chou141253/FGVC-HERBS

공식 코드

Fine-grained Visual Classification with High-temperature Refinement and Background Suppression

https://github.com/chou141253/fgvc-pim

공식 코드

A Novel Plug-in Module for Fine-Grained Visual Classification

https://github.com/cl-premonition/premonition

공식 코드

Premonition: Using Generative Models to Preempt Future Data Changes in Continual Learning

https://github.com/clovaai/assembled-cnn

공식 코드

Compounding the Performance Improvements of Assembled Techniques in a Convolutional Neural Network

https://github.com/csiro-robotics/isice

공식 코드

Learning Partial Correlation based Deep Visual Representation for Image Classification

https://github.com/cswluo/SEF

공식 코드

Learning Semantically Enhanced Feature for Fine-Grained Image Classification

https://github.com/cvl-umass/adaptclipzs

공식 코드

Improved Zero-Shot Classification by Adapting VLMs with Text Descriptions

https://github.com/cvl-umass/counting-clusters

공식 코드

Human-in-the-Loop Visual Re-ID for Population Size Estimation

https://github.com/davidzhangyuanhan/bamboo

공식 코드

Bamboo: Building Mega-Scale Vision Dataset Continually with Human-Machine Synergy

https://github.com/demidovd98/fgic_lowd

공식 코드

Extract More from Less: Efficient Fine-Grained Visual Recognition in Low-Data Regimes

https://github.com/demidovd98/sm-vit

공식 코드

Salient Mask-Guided Vision Transformer for Fine-Grained Classification

https://github.com/dichao-liu/anti-noise_fgvr

공식 코드

Progressive Multi-task Anti-Noise Learning and Distilling Frameworks for Fine-grained Vehicle Recognition

https://github.com/diffusion-classifier/diffusion-classifier

공식 코드

Your Diffusion Model is Secretly a Zero-Shot Classifier

https://github.com/dipuk0506/SpinalNet

공식 코드

SpinalNet: Deep Neural Network with Gradual Input

https://github.com/dipuk0506/uq

공식 코드

Reduction of Class Activation Uncertainty with Background Information

https://github.com/dongliangchang/Mutual-Channel-Loss

공식 코드

The Devil is in the Channels: Mutual-Channel Loss for Fine-Grained Image Classification

https://github.com/dongliangchang/Top-Down-Spatial-Attention-Loss

공식 코드

Fine-Grained Visual Classification via Simultaneously Learning of Multi-regional Multi-grained Features

https://github.com/dqshuai/metaformer

공식 코드

MetaFormer: A Unified Meta Framework for Fine-Grained Recognition

https://github.com/emu1729/gist

공식 코드

GIST: Generating Image-Specific Text for Fine-grained Object Classification

https://github.com/eyalmichaeli/saspa-aug

공식 코드

Advancing Fine-Grained Classification by Structure and Subject Preserving Augmentation

https://github.com/facebookresearch/FixRes

공식 코드

Fixing the train-test resolution discrepancy

https://github.com/facebookresearch/SWAG

공식 코드

Revisiting Weakly Supervised Pre-Training of Visual Perception Models

https://github.com/facebookresearch/deit

공식 코드

Training data-efficient image transformers & distillation through attention

https://github.com/facebookresearch/dinov2

공식 코드

DINOv2: Learning Robust Visual Features without Supervision

https://github.com/facebookresearch/vissl

공식 코드

Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision

https://github.com/faresbougourzi/ccfg-net

공식 코드

Extremely Fine-Grained Visual Classification over Resembling Glyphs in the Wild

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