AI Paper Atlas

Research map / Detection and segmentation / Weakly supervised detection and segmentation

Large Scale Visual Recognition through Adaptation using Joint Representation and Multiple Instance Learning

Judy Hoffman, Deepak Pathak, Eric Tzeng, Jonathan Long, Sergio Guadarrama, Trevor Darrell, Kate Saenko

JMLR 2016 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised detection · 0 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
adapt all layers (1-7, fcS) plus background layer with strongly labeled data (ablation)classification network · ILSVRC13 det val2 (weak categories)mAP (%): 10.31 -> 15.85Improved
adapt the background category layer only (ablation)classification network · ILSVRC13 det val2 (weak categories)mAP (%): 10.31 -> 12.22Improved
adapt fc6 in addition to fcbgrnd (ablation)LSDA rep only · ILSVRC13 det val2 (weak categories)mAP (%): 12.22 -> 13.72Improved
adapt fc7 in addition to fcbgrnd (ablation)LSDA rep only · ILSVRC13 det val2 (weak categories)mAP (%): 12.22 -> 14.57Improved
adapt the category-specific layer fcS in addition to fcbgrnd (ablation)LSDA rep only · ILSVRC13 det val2 (weak categories)mAP (%): 12.22 -> 11.74No clear effect
adapt convolutional layers 1-5 in addition to fc layers (ablation)LSDA rep only · ILSVRC13 det val2 (weak categories)mAP (%): 14.42 -> 15.85Improved
add kNN-adapted category-specific layer (k=10) (ablation)LSDA rep only · ILSVRC13 det val2 (weak categories)mAP (%): 15.85 -> 16.15Improved
jointly retrain category-specific weights with discovered boxes (fcW) (ablation)LSDA rep only · ILSVRC13 det val2 (weak categories)mAP (%): 15.85 -> 17.01Improved
jointly retrain all layers and category weights with MIL-discovered boxes (ablation)LSDA rep only · ILSVRC13 det val2 (weak categories)mAP (%): 15.85 -> 18.08Improved
add strongly labeled auxiliary data adaptationclassification network · ILSVRC13 det val1 discovered boxeslocalization mAP (%) ov=0.5: 13.13 -> 22.81Improved
add strongly labeled auxiliary data adaptationclassification network · ILSVRC13 det val1 discovered boxesCorLoc (%) ov=0.5: 26.10 -> 28.81Improved
adapt the network with LSDA instead of classification-only network for segmentationFCN-32s AlexNet · PASCAL VOC 2011 val segmentationmean IU (%): 11.6 -> 21.3Improved

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