AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

SHERL: Synthesizing High Accuracy and Efficient Memory for Resource-Limited Transfer Learning

Haiwen Diao, Bo Wan, Xu Jia, Yunzhi Zhuge, Ying Zhang, Huchuan Lu, Long Chen

ECCV 2024 · Architectures and efficiency › Pruning and efficient tuning · approach: Parameter-efficient transfer analysis · 8 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
use SHERL instead of LST on T5-base GLUET5-base · GLUE (T5-base)training memory (GB): 5.5 -> 2.9Improved
use SHERL instead of LST on T5-largeT5-large · GLUE (T5-large)average score: 87.1 -> 87.5Improved
use SHERL instead of LST on T5-3BT5-3B · GLUE (T5-3B)average score: 88.1 -> 88.2No clear effect
use SHERL instead of UniPT on MSVD video-text retrievalCLIP4Clip · MSVDRsum: 432.1 -> 429.7Hurt
use SHERL instead of UniPT on Flickr30K retrievalVSEinf · Flickr30KRsum: 537.4 -> 542.3Improved
replace redundancy-aware aggregation with max pooling, average pooling, MHSA or plain linear attention (ablation)SHERL early route · VL datasets (average accuracy)average accuracyImproved
add late regulation by the last pre-trained layer (ablation)SHERL · GLUE (T5-base)average accuracyImproved
add Prompt tuning in late layers on top of SHERL (ablation)SHERL · GLUE (T5-base)average accuracyNo clear effect
add LoRA or Adapter in late frozen layers on top of SHERL (ablation)SHERL · GLUE (T5-base)average accuracyImproved
insert blended features into multiple late decoder layers instead of a single earlier layer (ablation)SHERL · GLUE (T5-base)average accuracyImproved
use SHERL instead of Fully-FTT5-base · GLUE (T5-base)average score: 85.2 -> 84.3Hurt

Later papers that compared with this method

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

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.

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