Research map / Detection and segmentation / Weakly supervised detection and segmentation
TRACE: Your Diffusion Model is Secretly an Instance Edge Detector
Sanghyun Jo, Ziseok Lee, Wooyeol Lee, Jonghyun Choi, Jaesik Park, Kyungsu Kim
This paper tried a common change: Add a reconstruction / auxiliary loss
add reconstruction loss during distillation · COCO 2014 · AP^mk: 8.9 -> 9.4 Improved
What 987 accepted papers report for this change
- 882 improved
- 41 no clear effect
- 20 mixed
- 44 hurt
- OPTION: Optimal Transport–Guided Flow Matching for Incomplete and Unaligned Multi-View Clustering ICML 2026 · add reconstruction loss L_rec · Scene-15 (aligned, 70% missing) · ACC: 32.4 -> 37.5Improved
- Detached Skip-Links and $R$-Probe: Decoupling Feature Aggregation from Gradient Propagation for MLLM OCR ICML 2026 · add R-probe auxiliary loss · OCRBench · score: 714.0 -> 721.0Improved
- Rethinking Time-Series Imputation as Conditional Inference along Temporal Evolution ICML 2026 · add reconstruction loss on observed entries (joint vs missing-only supervision) · ETTh1 10% missing · Masked MAE: 0.2002 -> 0.1658Improved
See this change in detailMatched by the wording of each paper's own result, read by AI from the full text. Papers report gains more often than failures, so this shows what gets published, not the chance a change works.
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 changed | Where | Measured | Effect |
|---|---|---|---|
| apply ABDiv at a semantic timestep without IEP (ablation) | TRACE on ProMerge · COCO 2014 | AP^mk: 3.1 -> 3.2 | No clear effect |
| add Instance Emergence Point timestep selection (ablation) | ABDiv · COCO 2014 | AP^mk: 3.2 -> 4.8 | Improved |
| add one-step self-distillation with edge decoder (ablation) | IEP + ABDiv · COCO 2014 | AP^mk: 4.8 -> 8.2 | Improved |
| add reconstruction loss during distillation (ablation) | TRACE edge decoder · COCO 2014 | AP^mk: 8.9 -> 9.4 | Improved |
| use MSE instead of KL divergence for IEP (ablation) | TRACE · COCO 2014 | AP^mk: 9.4 -> 3.8 | Hurt |
| use JSD instead of KL divergence for IEP (ablation) | TRACE · COCO 2014 | AP^mk: 9.4 -> 9.4 | No clear effect |
| use non-diffusion backbones (ABDiv only) instead of diffusion backbones (ablation) | TRACE · COCO 2014 | AP^mk: 7.1 (PixArt-alpha 0.6B) vs 4.1 (Qwen2.5-VL 72B) | Hurt |
| use larger diffusion backbone (ablation) | TRACE · COCO 2014 | AP^mk: 6.8 (SD1.5) -> 8.3 (FLUX.1) | Improved |
| replace TRACE edges with conventional edge detectors in BGP (ablation) | TRACE pipeline · COCO 2014 | AP^mk: 9.4 -> 1.2 (Canny), 4.3 (DiffusionEdge) | Hurt |
| add TRACE edges to tag-supervised DHR | DHR panoptic · VOC 2012 (ResNet-50) | PQ: 45.0 -> 56.9 | Improved |
| use 8-neighborhood instead of 4-neighborhood in ABDiv (ablation) | TRACE · COCO | AP^mk | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- ProMerge — ProMerge: Prompt and Merge for Unsupervised Instance Segmentation (ECCV 2024) · better on 2 of 2 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
- InstanceDiffusion: Instance-level Control for Image Generation (CVPR 2024 · similarity 0.89)
- The Devil is in the Object Boundary: Towards Annotation-free Instance Segmentation using Foundation Models (ICLR 2024 · similarity 0.87)
- Prompting Diffusion Models for Zero-Shot Instance Segmentation (NeurIPS 2026 · similarity 0.87)
- High-Precision Dichotomous Image Segmentation via Probing Diffusion Capacity (ICLR 2025 · similarity 0.87)
- The Crystal Ball Hypothesis in diffusion models: Anticipating object positions from initial noise (ICLR 2025 · similarity 0.86)
- Edge-Aware 3D Instance Segmentation Network with Intelligent Semantic Prior (CVPR 2024 · similarity 0.86)
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.
