Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Priority
Receipt is acknowledged of certified copies of papers required by 37 CFR 1.55.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claim(s) 1, 15 and 19 is/are rejected under 35 U.S.C. 103 as being unpatentable over US 2023/0290128 A1 to Luo et al., hereinafter, “Luo” in view of US 2023/0316587 A1 to Ghebremusse et al., hereinafter, “Ghebremusse” and Feature Unlearning for Pre-trained GANs and VAEs to Moon et al., hereinafter, “Moon”.
Claim 1. Luo teaches A method of performing unlearning of people in a generative model, [0002] An de-identification method, FIG.8 StyleGAN2 generator
[0003] De-identification is to remove a recognizable identity feature in an image or a video
the method performed in a computing device equipped with one or more processors and a memory storing one or more programs executed by the one or more processors, the method comprising: [0010] …computing device, including a processor and a memory. The memory is configured to store a computer program. The processor is configured to invoke and run the computer program stored in the memory to perform the model training method or the de-identification method…
inputting a source image including a face of a person to be unlearned in a pre-learned generative model into an encoder to extract a source latent vector in a latent space; [0102] FIG. 8, priori identity information is generated based on a first training image Xs (interpreted to be the source image) by using a pre-trained face recognition model. Then the priori identity information is inputted to the VAE (equivalent of an encoder), and the VAE projects the priori identity information to the first space Z to obtain N latent identity vectors (interpreted to be the source latent vector in a latent space)…
Luo fails to explicitly teach setting a target latent vector so that the identity is different from that of a person corresponding to the source latent vector in the latent space. Ghebremusse, in the field of editing facial features using deep learning, teaches setting a target latent vector so that the identity is different from that of a person corresponding to the source latent vector in the latent space; [0009] applying an adjustment vector (interpreted to be setting) to a latent space point corresponding to the initial output image to generate an adjusted latent space point; and decoding the adjusted latent space point to generate an adjusted output image in accordance with the desired facial identity but with the facial expression and pose of the face in the input image altered in accordance with the adjustment vector (interpreted to be different identity)
Thus, before the effective filing date of the present application, it would have been obvious to one of ordinary skill in the art to combine the teachings of Luo with the teachings of Ghebremusse [0002] for a clear, easy way to correct swapped features.
Luo fails to explicitly teach performing unlearning to remove the identity of the person in the pre-learned model based on the source latent vector and the target latent vector. Moon, in the field of unlearning for a pre-trained generative adversarial network, teaches and performing unlearning to remove the identity of the person in the pre-learned model based on the source latent vector and the target latent vector. [Abstract] we aim to unlearn a specific feature, such as hairstyle from facial images, from the pre-trained generative models.
Figure 1: Result of unlearning various features from pre trained StyleGAN model. We utilize the same latent vector to generate images from both the original and the unlearned models.
[Unlearning Framework, pages 2-3] paired dataset with and without target features (interpreted to be source and target images), pre-trained generator (interpreted to be pre-learned model), latent representation, latent space, and latent vector (interpreted to be latent vectors)… we obtain the latent vector representation of each image from the collected dataset. Once we obtain the latent vectors, we use a vector arithmetic method proposed by Radford, Metz, and Chintala (2015) to find the latent vector representing the target feature
[Unlearning Process, page 3] Given random vector z, we first project the vector onto the target vector (target latent vector), and then the original random vector (source latent vector) is shifted by the projected vector
Thus, before the effective filing date of the present application, it would have been obvious to one of ordinary skill in the art to combine the teachings of Luo with the teachings of Moon [Introduction] to effectively remove the target feature while maintaining the image quality.
Claim 15. Reviewed and analyzed in the same way as claim 1. See the above analysis and rationale.
Claim 19. Reviewed and analyzed in the same way as claim 1. See the above analysis and rationale. Luo [0012] … a non-transitory computer-readable storage medium.
Allowable Subject Matter
Claims 2, 5 and 16 are objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims.
The innovation that makes claim 2 allowable is “and setting a target latent vector based on the source latent vector and the mean latent vector”. Prior art Expression Transfer Using Flow-based Generative Models to Valenzuela et al., hereinafter, Valenzuela teaches
Claim 2. The method according to claim 1, wherein the setting comprises: obtaining a mean latent vector in the latent space by the encoder; [Introduction] we consider the flow-based Glow model [20] and explore how the original pre-trained model can be used for expression transfer between a source face image and a target face image.
[4. Expression Transfer] We first compute the mean latent vector for both the source and target image sets
Valenzuela and other prior art search fails to explicitly teaches and setting a target latent vector based on the source latent vector and the mean latent vector.
Likewise claims 3-4 are allowed because they are dependents of claim 1.
The innovation that makes claims 5 and 16 allowable is “inputting the target feature map and the source feature map into a rendering model, respectively, to output a target generated image and a source generated image, respectively; and learning the second generator by a first loss pre-set based on the target feature map, the source feature map, the target generated image, and the source generated image, wherein the initial values of neural network parameters of the second generator are set as same as values of neural network parameters of the learned first generator.”
Likewise claims 6-14 and 17-18 are allowed because they are dependents of
claims 5 and 16, respectively.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to DELOMIA L GILLIARD whose telephone number is (571)272-1681. The examiner can normally be reached 8am-5pm.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, John Villecco can be reached at (571) 272-7319. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/DELOMIA L GILLIARD/Primary Examiner, Art Unit 2661
Prosecution Insights