AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

Polyhistor: Parameter-Efficient Multi-Task Adaptation for Dense Vision Tasks

Yen-Cheng Liu, Chih-Yao Ma, Junjiao Tian, Zijian He, Zsolt Kira

NeurIPS 2022 · Architectures and efficiency › Pruning and efficient tuning · approach: Adapter-based parameter-efficient tuning · 14 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 decomposed low-rank hypernetworks (Polyhistor vs Hyperformer)Hyperformer · PASCAL-Contextavg relative improvement (%): 2.64 -> 2.34 with 72.77M -> 6.41M encoder paramsNo clear effect
add layer-wise scaling kernels and cross-layer hypernetwork sharing (Polyhistor-Lite) (ablation)Polyhistor · PASCAL-Contextavg relative improvement (%): 2.34 -> 1.74 with 6.41M -> 0.41M encoder paramsMixed
increase task embedding size from 16 to 64 (ablation)Polyhistor-Lite · PASCAL-Contextavg relative improvement (%): -0.15 -> 1.74Improved
increase hypernetwork output rank from 1 to n/2 (ablation)Polyhistor · PASCAL-Contextavg relative improvement (%): 0.52 -> 2.84Improved
shrink Hyperformer hypernetwork (rho 8 to 32) (ablation)Hyperformer · PASCAL-Contextavg relative improvement (%): 2.64 -> -0.14Hurt
use larger backbone Swin-B instead of Swin-T (both IN-1k) (ablation)Polyhistor-Lite · PASCAL-Contextavg relative improvement (%): 1.74 -> 6.38 (rho=1 on Swin-B)Improved
pretrain backbone on ImageNet-22k instead of 1k (ablation)Polyhistor-Lite · PASCAL-Contextavg relative improvement (%): 6.38 -> 8.08 (rho=1)Improved
tune adapter hidden size of baselines (Adapter, Compacter, Shared Adapter) (ablation)baseline adapters · PASCAL-Contextavg relative improvement (%): -2.71 -> -3.03 (Adapter rho 2 -> 4)No clear effect
VPT input-space prompts vs decoders onlyVPT-deep · PASCAL-Contextavg relative improvement (%): -11.02 -> -10.85No clear effect

Later papers that compared with this method

2 later accepted papers report Polyhistor as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

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