Fine-Grained Visual Recognition
35 papers with code • 0 benchmarks • 5 datasets
Benchmarks
These leaderboards are used to track progress in Fine-Grained Visual Recognition
Libraries
Use these libraries to find Fine-Grained Visual Recognition models and implementations
MTL-AQA
WHOI-Plankton
WebFG-496
FeathersV1
WikiChurches
Latest papers
On the Eigenvalues of Global Covariance Pooling for Fine-grained Visual Recognition
KingJamesSong/DifferentiableSVD
•
•
Inspired by this observation, we propose a network branch dedicated to magnifying the importance of small eigenvalues.
CLIP-Art: Contrastive Pre-training for Fine-Grained Art Classification
KeremTurgutlu/self_supervised
•
•
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops 2021
Existing computer vision research in artwork struggles with artwork's fine-grained attributes recognition and lack of curated annotated datasets due to their costly creation.
Do Vision-Language Pretrained Models Learn Composable Primitive Concepts?
tttyuntian/vlm_primitive_concepts
•
•
CompMap first asks a VL model to generate primitive concept activations with text prompts, and then learns to construct a composition model that maps the primitive concept activations (e. g. the likelihood of black tail or red wing) to composite concepts (e. g. a red-winged blackbird).
Generalized Category Discovery
sgvaze/generalized-category-discovery
•
•
CVPR 2022
Here, the unlabelled images may come from labelled classes or from novel ones.
Few-shot Keypoint Detection with Uncertainty Learning for Unseen Species
alanlusun/few-shot-keypoint-detection
•
•
CVPR 2022
Current non-rigid object keypoint detectors perform well on a chosen kind of species and body parts, and require a large amount of labelled keypoints for training.
Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification
Unlike most existing methods that learn visual attention based on conventional likelihood, we propose to learn the attention with counterfactual causality, which provides a tool to measure the attention quality and a powerful supervisory signal to guide the learning process.
Exploiting Web Images for Fine-Grained Visual Recognition by Eliminating Noisy Samples and Utilizing Hard Ones
NUST-Machine-Intelligence-Laboratory/Advanced-Softly-Update-Drop
•
•
Labeling objects at a subordinate level typically requires expert knowledge, which is not always available when using random annotators.
Data-driven Meta-set Based Fine-Grained Visual Classification
NUST-Machine-Intelligence-Laboratory/dmbfgvr
•
•
To this end, we propose a data-driven meta-set based approach to deal with noisy web images for fine-grained recognition.
ECML: An Ensemble Cascade Metric Learning Mechanism towards Face Verification
Embedding RMML into the proposed ECML mechanism, our metric learning paradigm (EC-RMML) can run in the one-pass learning manner.
Interpretable and Accurate Fine-grained Recognition via Region Grouping
zxhuang1698/interpretability-by-parts
•
•
CVPR 2020
Our results compare favorably to state-of-the-art methods on classification tasks, and our method outperforms previous approaches on the localization of object parts.
