US 11,669,745 B2
Proposal learning for semi-supervised object detection
Chetan Ramaiah, San Bruno, CA (US); Peng Tang, Mountain View, CA (US); and Caiming Xiong, Menlo Park, CA (US)
Assigned to salesforce.com, inc., San Francisco, CA (US)
Filed by salesforce.com, inc., San Francisco, CA (US)
Filed on Oct. 26, 2020, as Appl. No. 17/80,276.
Claims priority of provisional application 62/960,630, filed on Jan. 13, 2020.
Prior Publication US 2021/0216828 A1, Jul. 15, 2021
Int. Cl. G06F 18/21 (2023.01); G06N 3/082 (2023.01); G06F 18/214 (2023.01)
CPC G06F 18/2178 (2023.01) [G06F 18/2155 (2023.01); G06N 3/082 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method for generating a neural network for detecting one or more objects in images, comprising:
generating one or more region proposals that may contain objects for each image of a set of unlabeled images;
determining one or more proposal features for each of the region proposals and corresponding proposal feature predictions using a proposal convolutional feature map;
adding noise to the proposal convolutional feature map to generate a noisy proposal convolutional feature map;
generating one or more noisy proposal features using the noisy proposal convolutional feature map;
generating one or more self-supervised proposal learning losses based on the one or more proposal features and corresponding proposal feature predictions, and the one or more noisy proposal features and corresponding noisy proposal feature predictions;
generating one or more consistency-based proposal learning losses based on noisy proposal feature predictions and the corresponding proposal predictions without noise;
generating a combined loss using the one or more self-supervised proposal learning losses and one or more consistency-based proposal learning losses; and
updating the neural network based on the combined loss.