PP-SSL combines CLIP text-guided distillation with original-image GradCAM guidance to improve self-supervised fine-grained recognition, reporting state-of-the-art results on seven benchmarks.
Unsupervised learning of visual features by contrasting cluster assignments
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
PP-SSL : Priority-Perception Self-Supervised Learning for Fine-Grained Recognition
PP-SSL combines CLIP text-guided distillation with original-image GradCAM guidance to improve self-supervised fine-grained recognition, reporting state-of-the-art results on seven benchmarks.