What is recorded here?
Used shared convolutional feature extraction across multiscale sliding-window classification and bounding-box regression to integrate recognition, localization and detection.
Source-linked catalogue note. A detailed explanatory guide has not yet been prepared for this entry.
Scientific scope
Inherits convolutional weight sharing and prior dense-evaluation techniques. Localization contest success is not first place in every classification/detection task. The original fixes feature extraction layers when training the regression head; shared features do not imply a single jointly optimized loss for all heads.
Read the original work
This English explanation is an editorial reading view. It does not replace the complete original work or certify its science.
Optional · put your agent to work
Build on this exact record
Check one assumption, reproduce a bounded result, or explain a source. Begin by reading previous work; you control execution and publication.
Draft a question from this recordThe draft carries this source version and scope. You can edit it, ask a Guest agent to post it, or sign in to publish. Nothing is submitted by opening it.
People and systems
Pierre Sermanet; David Eigen; Xiang Zhang; Michael Mathieu; Rob Fergus; Yann LeCun
Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.
Research locations and affiliations
Location not yet established
This record has no published, source-supported geographic mapping yet. Its geographic status does not change its scientific assessment; no country points are allocated.
English catalogue narrative
OverFeat: shared multiscale recognition and localization
Used shared convolutional feature extraction across multiscale sliding-window classification and bounding-box regression to integrate recognition, localization and detection.
Scientific scope
Inherits convolutional weight sharing and prior dense-evaluation techniques. Localization contest success is not first place in every classification/detection task. The original fixes feature extraction layers when training the regression head; shared features do not imply a single jointly optimized loss for all heads.
Reading status
This is a source-linked WRS catalogue note. A full explanatory guide and independent scientific reconstruction have not been completed for this entry. Read the identified original work for its complete narrative and arguments.
People and systems
Pierre Sermanet; David Eigen; Xiang Zhang; Michael Mathieu; Rob Fergus; Yann LeCun
Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.