AI Paper Atlas

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

CoT-PL: Chain-of-Thought Pseudo-Labeling for Open-Vocabulary Object Detection

Hojun Choi, Youngsun Lim, Jaeyo Shin, Hyunjung Shim

ECCV 2026 · Detection and segmentation › Open-set and few-shot detection · approach: Open-vocabulary object detection · 0 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 SAM and MLLM 1-step pseudo-labeling (ablation)BARON baseline · OV-COCOAP50 novel: 34.0 -> 37.6Improved
use 3-step reasoning instead of 1-step (ablation)MSPL · OV-COCOAP50 novel: 37.6 -> 41.6Improved
add RTA (fine-grained linguistic attributes) (ablation)MSPL · OV-COCOAP50 novel: 41.6 -> 42.5Improved
add CBL (contrastive background learning) (ablation)MSPL · OV-COCOAP50 novel: 42.5 -> 43.4Improved
use SAM instead of Mask R-CNN proposals (ablation)MSPL · OV-COCOAP50 novel: 40.9 -> 43.4Improved
use SAM instead of MAVL proposals (ablation)MSPL · OV-COCOAP50 novel: 42.2 -> 43.4Improved
use MIN threshold for semantic anchors instead of RANDOM (ablation)MSPL · OV-COCOAP50 novel: 41.7 -> 43.4Improved
use MIN threshold instead of AVERAGE (ablation)MSPL · OV-COCOAP50 novel: 42.6 -> 43.4Improved
use Qwen2 7B instead of BLIP2 2.7B as MLLM (ablation)MSPL · OV-COCOAP50 novel: 39.6 -> 43.4Improved
use Qwen2 7B instead of InstructBLIP 7B (ablation)MSPL · OV-COCOAP50 novel: 42.6 -> 43.4No clear effect
use blur and gray context instead of black mask (ablation)MSPL · OV-COCOAP50 novel: 38.7 -> 43.4Improved
use blur and gray context instead of bounding box (ablation)MSPL · OV-COCOAP50 novel: 33.2 -> 43.4Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 4 of 4 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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