AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Tokenize Anything via Prompting

Ting Pan, Lulu Tang, Xinlong Wang, Shiguang Shan

ECCV 2024 · Detection and segmentation › Open-set and few-shot detection · approach: Open-vocabulary 3D and world perception · 41 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add concept-prediction loss (KL to CLIP concept distribution) on semantic token (ablation)TAP promptable tokenizer · VG region captioning (partial-FT)CIDEr: 105.2 -> 154.7Improved
use concept alignment instead of feature alignment for CLIP priors (ablation)TAP promptable tokenizer · LVIS zero-shot classificationAP: 39.1 -> 59.1Improved
use concept alignment instead of feature alignment (ablation)TAP promptable tokenizer · COCO zero-shot classificationAP: 62.0 -> 77.0Improved
use semantic token instead of mask token to prompt text decoder (ablation)TAP captioning · VG region captioning (partial-FT)CIDEr: 138.9 -> 154.7Improved
add semantic prediction to pre-training (ablation)TAP promptable tokenizer · COCO/LVIS segmentationmask AP: 46.1 -> 46.0 (COCO), 43.2 -> 43.0 (LVIS)No clear effect
scale text decoder depth and width (ablation)TAP-L captioning · VG region captioningCIDEr: 153.2 -> 154.7No clear effect
unfreeze image encoder-decoder and fine-tune end to end (full-FT)TAP-L captioning · Visual Genome region captioningCIDEr: 154.7 -> 164.7Improved
increase point prompts from 1 to 5 instead of box prompt (ablation)TAP-L classification · LVISAP_cls: 48.1 -> 58.7 (box 59.1)Improved
use compact TAP-L tokenizer instead of 5B EVA-CLIP crop classifierRegion classification · LVIS zero-shot classificationAP: 64.3 -> 59.1Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy