AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

TransTIC: Transferring Transformer-based Image Compression from Human Perception to Machine Perception

Yi-Hsin Chen, Ying-Chieh Weng, Chia-Hao Kao, Cheng Chien, Wei-Chen Chiu, Wen-Hsiao Peng

ICCV 2023 · Architectures and efficiency › Pruning and efficient tuning · approach: Efficient ViT adaptation · 70 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 TransTIC prompting instead of spatial feature transform on complex tasks (detection)TIC base codec · COCO2017-val detectionBD-Rate (%): -26.56 -> -46.07Improved
use TransTIC prompting instead of SFT on classificationTIC base codec · ImageNet-val classificationBD-Rate (%): -62.10 -> -58.77No clear effect
use prompting instead of channel selectionTIC base codec · COCO2017-val detectionBD-Rate (%): 53.66 -> -46.07Improved
use full fine-tuning instead of promptingTIC base codec · ImageNet-val classificationBD-accuracy: 10.02 -> 16.24Improved
swap recognition network to VGG19 at test time (full fine-tuning vs TransTIC)full fine-tuning codec · ImageNet-val classificationaccuracy: full fine-tuning drops 15%-20%, TransTIC drops 3%-7%Hurt
instance-specific (IP-type) instead of task-specific (TP-type) prompts in encoder (ablation)TransTIC encoder · classification and detectionrate-accuracyImproved
add decoder-side task-specific prompts (ablation)TransTIC · classification and detectionrate-accuracyImproved
use spatially adaptive instead of shared instance prompts across windows (ablation)TransTIC encoder · classification and detectionrate-accuracyImproved
inject prompts to early STBs (1,2) rather than later STBs (3,4) (ablation)TransTIC encoder · classification and detectionrate-accuracyImproved
inject prompts into all four STBs instead of STB-1,2 (ablation)TransTIC encoder · classification and detectionrate-accuracyNo clear effect
increase prompts per window from 16 to 64 (ablation)TransTIC encoder · classification and detectionaccuracyNo clear effect
use ROI coding instead of learned spatially adaptive transferimage codec for machines · ImageNet-val classificationBD-Rate (%): -58.77 -> -8.67Hurt

Later papers that compared with this method

1 later accepted paper reports TransTIC as a baseline in their results tables; 1 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