DETAILED ACTION
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 .
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 03/21/2024 is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner.
Claim Rejections - 35 USC § 102
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claims 1-4 and 6-8 are rejected under 35 U.S.C. 102(a)(2) as being anticipated by Zhao et al (“Zhao” hereinafter U.S. Publication No. 2024/0386280 A1).
As per claim 1, Zhao discloses a knowledge distillation method for compressing an image segmentation model (abstract & paragraph [0045]) that is performed in a computing device (computing device 10 in figure 1B) including one or more processors and a memory storing one or more programs executed by the one or more processors (see processor and memory in figure 1A), the knowledge distillation method comprising: training a first image segmentation model (teacher model 306 in figure 3A) including a first image encoder (encoder 323), a first image embedding layer (hidden layers 330), and a first mask decoder (decoder 324); constructing a second image segmentation model (student model 304) including a second image encoder (encoder 322), a second image embedding layer (hidden layers 308), and a second mask decoder (decoder 325) according to preset constraints (as shown in figure 3A); and performing knowledge distillation for the second image embedding layer of the second image segmentation model based on the trained first image segmentation model (figure 4, numerals 406 & 408).
As per claim 2, Zhao discloses wherein the second image segmentation model is lighter model than the first image segmentation model (student model 304 is lighter than teacher model 306).
As per claim 3, Zhao discloses wherein the first mask decoder includes a prompt encoder configured to receive at least one of a dot, a box, and text (the input in teacher model can be anything from text, audio to visual data) and output a prompt embedding vector (output of initial layers 326), the first image embedding layer outputs an image embedding vector based on a value output from the first image encoder by using a training image as input (the output of initial layer 326 is inputted to encoder 323 as an image embedding vector), and the first mask decoder generates a mask for segmenting an image based on the output image embedding vector and the output prompt embedding vector (Decoder 324 is capable of decoding embedded messages in the image for segmentation as explained in paragraph [0052]).
As per claim 4, Zhao discloses wherein the constructing of the second image segmentation model further includes: constructing the second image encoder and the second image embedding layer according to the preset constraints (the encoder and hidden layers in student model is constructed according to the teacher model as shown in figure 3A); and constructing the second mask decoder to be identical to the first mask decoder of the trained first image segmentation model by copying the first mask decoder (the decoders in teacher model and student model are identical as shown in figure 3A).
As per claim 6, see explanation claim 1.
As per claim 7, see explanation in claim 2.
As per claim 8, see explanation in claim 4.
Allowable Subject Matter
Claims 5 and 9 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.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to TOM Y LU whose telephone number is (571)272-7393. The examiner can normally be reached Monday - Friday, 9AM - 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, Matthew Bella can be reached at (571) 272 - 7778. 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.
/TOM Y LU/Primary Examiner, Art Unit 2667