Datasets › CC3M-TagMask

CC3M-TagMask

Introduced by Sanghyun Jo et al. in TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias30 Mar 2024 archive 2025-07-28

The dataset offers tag and mask annotations for image-text pairs from the CC3M validation set. Tag annotations denote words that aptly describe the relationship between the image and the corresponding text. These annotations provide valuable insights into the semantic connection between each pair's visual and textual elements.

Benchmarks archive 2025-07-28

All 2 leaderboards whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.

First row (archive order)PaperCode
Multi-Label Text Classification CC3M-TagMask TTD (w/ fine-tuning) Precision 88.3 TTD: Text-Tag Self-Distillation Enhancing Image-Text... shjo-april/TTD 6 Compare
Semantic Segmentation CC3M-TagMask TTD (TCL) mIoU 65.5 TTD: Text-Tag Self-Distillation Enhancing Image-Text... shjo-april/TTD 4 Compare

Papers archive 2025-07-28

5 shown of 5 papers with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 5. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.

DateSamples run Syntology
TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias 1 4 30 Mar 2024 ran 1 of 1 samples (0 unverified; 1 pointer-only for licence)
Qwen Technical Report 2 1 28 Sep 2023 ran 2 of 4 samples (2 unverified)
Learning to Generate Text-grounded Mask for Open-world Semantic Segmentation from Only Image-Text Pairs 1 1 1 Dec 2022 ran 1 of 8 samples (7 unverified)
Extract Free Dense Labels from CLIP 1 1 2 Dec 2021 not harvested
NLTK: The Natural Language Toolkit 1 1 17 May 2002 not harvested

Dataset loaders archive 2025-07-28

No loader listed in the archive.

Tasks archive 2025-07-28

License archive 2025-07-28

No licence recorded in the archive. Absence here is not a statement about the dataset's terms.

Modalities archive 2025-07-28

Languages archive 2025-07-28

Variants archive 2025-07-28

  • CC3M-TagMask

1 variant name, as the archive lists them.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections