HumanLiker: A Human-like Object Detector to Model the Manual Labeling Process
Nov 28, 2022
Speakers
Haoran Wei
Speaker · 0 followers
About
Popular object detection models generate bounding boxes in a different way than we humans. As an example, modern detectors yield object box either upon the regression of its center and width/height (center-guided detector), or by grouping paired estimated corners (corner-guided detector). However, that is not the pattern we manually label an object due to high degrees of freedom in searching centers or low efficiency of grouping corners. Empirically, humans run two steps to locate an object bounding box manually: 1) click the mouse at the top-left corner of object, and then drag the mouse to the bottom-right corner; 2) refine the corner positions to make the bounding box more precisely, if necessary. Inspired by this manual labeling process, we propose a novel human-like detector, termed as HumanLiker, which is devised as a two-stage end-to-end detector to simulate the two aforementioned. Like we humans in manual labeling, HumanLiker can effectively avert both the thorny center searching and heuristic corner grouping. Different from the mainstream detector branches, i.e., the center/corner-guided methods, the HumanLiker provides a new paradigm which integrates the advantages of both branches to balance the detection efficiency and bounding box quality. On MS-COCO test-dev set, HumanLiker can achieve 50.2Popular object detection models generate bounding boxes in a different way than we humans. As an example, modern detectors yield object box either upon the regression of its center and width/height (center-guided detector), or by grouping paired estimated corners (corner-guided detector). However, that is not the pattern we manually label an object due to high degrees of freedom in searching centers or low efficiency of grouping corners. Empirically, humans run two steps to locate an object boun…
Organizer
NeurIPS 2022
Account · 963 followers
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
Closing Remarks
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
SymbolicGPT: A Generative Transformer Model for Symbolic Regression
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
SoftTreeMax: Policy Gradient with Tree Search
Watch later
Gal Dalal, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
MARS: Meta-Learning as Score Matching in the Function Space
Watch later
Kruno Lehman, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Learning Structure from the Ground up—Hierarchical Representation Learning by Chunking
Watch later
Shuchen Wu, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Estimation of prediction error with covariate information
Watch later
Hui Xu, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%