AI Paper Atlas

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

Effective Adaptation in Multi-Task Co-Training for Unified Autonomous Driving

Xiwen Liang, Yangxin Wu, Jianhua Han, Hang Xu, Chunjing Xu, Xiaodan Liang

NeurIPS 2022 · Detection and segmentation › Open-set and few-shot detection · approach: Object-level representation learning · 16 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 an adaptation stage before fine-tuningMoCo-v2 on BDD100K Disjoint-normal · BDD100K Disjoint-normalmIoU (SS): 10.3 -> 61.2Improved
Add an adaptation stage before fine-tuningDenseCL on BDD100K Disjoint-normal · BDD100K Disjoint-normalmIoU (SS): 20.0 -> 60.7Improved
Add an adaptation stage before fine-tuningSimCLR on BDD100K Disjoint-normal · BDD100K Disjoint-normalmIoU (SS): 60.3 -> 60.1No clear effect
Add learned task-specific CLIP prompts (ablation)LV-Adapter on BDD100K Disjoint-normal · BDD100K Disjoint-normalmIoU (SS): 61.5 -> 61.8Improved
Replace learned prompts alone with vision-to-language adaptation (ablation)LV-Adapter on BDD100K Disjoint-normal · BDD100K Disjoint-normalmIoU (SS): 61.8 -> 61.3Hurt
Add language-to-vision alignment of text and visual features (ablation)LV-Adapter on BDD100K Disjoint-normal · BDD100K Disjoint-normalmIoU (SS): 61.8 -> 62.2Improved
Use learned prompts instead of prompt engineering (ablation)CLIP-based LV-Adapter on BDD100K Disjoint-normal · BDD100K Disjoint-normalmIoU (SS): 61.4 -> 62.2Improved
Use learned prompts instead of prompt ensembling (ablation)CLIP-based LV-Adapter on BDD100K Disjoint-normal · BDD100K Disjoint-normalmIoU (SS): 61.7 -> 62.2Improved
Use 1 adaptation epoch and 35 fine-tuning epochs instead of 12 and 24 (ablation)Pretrain-adapt-finetune · BDD100K Disjoint-normalmIoU (SS): 59.5 -> 61.5Improved
Increase adaptation epochs from 6 to 12 while fixing fine-tuning at 35 epochs (ablation)Pretrain-adapt-finetune · BDD100K Disjoint-normalmIoU (SS): 61.3 -> 61.9Improved
Replace the FPN adapter with alternative adapter designs (ablation)SimCLR adaptation on BDD100K Disjoint-normal · BDD100K Disjoint-normalmIoU (SS): FPN 60.1; pre-adapter 60.2; post-adapter 60.2; learnable scalar 59.9; learnable vector 59.8No clear effect
Add LV-Adapter to single-task modelsMaskFormer on BDD100K Disjoint-balance · BDD100K Disjoint-balancemIoU (SS): 57.1 -> 61.3Improved

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