DETAILED ACTION
This action is in response to the amendments and remarks filed 07/14/2026. Claims 1-3, 5-6, 8-13, 15-16, and 18-19 are pending and have been examined.
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on 07/14/2026 has been entered.
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 § 112
The following is a quotation of the first paragraph of 35 U.S.C. 112(a):
(a) IN GENERAL.—The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor or joint inventor of carrying out the invention.
The following is a quotation of the first paragraph of pre-AIA 35 U.S.C. 112:
The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor of carrying out his invention.
Claims 1-3, 5-6, 8-13, 15-16, and 18-19 are rejected under 35 U.S.C. 112(a) or 35 U.S.C. 112 (pre-AIA ), first paragraph, as failing to comply with the written description requirement. The claim(s) contains subject matter which was not described in the specification in such a way as to reasonably convey to one skilled in the relevant art that the inventor or a joint inventor, or for applications subject to pre-AIA 35 U.S.C. 112, the inventor(s), at the time the application was filed, had possession of the claimed invention.
Any negative limitation or exclusionary proviso must have basis in the original disclosure. If alternative elements are positively recited in the specification, they may be explicitly excluded in the claims … The mere absence of a positive recitation is not basis for an exclusion. However, a lack of literal basis in the specification for a negative limitation may not be sufficient to establish a prima facie case for lack of descriptive support. Ex parte Parks, 30 USPQ2d 1234, 1236 (Bd. Pat. App. & Inter. 1993). "Rather, as with positive limitations, the disclosure must only 'reasonably convey[] to those skilled in the art that the inventor had possession of the claimed subject matter as of the filing date.' ... While silence will not generally suffice to support a negative claim limitation, there may be circumstances in which it can be established that a skilled artisan would understand a negative limitation to necessarily be present in a disclosure." Novartis Pharms. Corp. v. Accord Healthcare, Inc., 38 F.4th 1013, 2022 USPQ2d 569 (Fed. Cir. 2022) (quoting Ariad Pharm. Inc. v. Eli Lilly & Co., 589 F.3d 1336, 1351, 94 USPQ2d 1161, 1172). Any claim containing a negative limitation which does not have basis in the original disclosure should be rejected under 35 U.S.C. 112(a) or pre-AIA 35 U.S.C. 112, first paragraph, as failing to comply with the written description requirement. See MPEP § 2163 - § 2163.07(b) for a discussion of the written description requirement of 35 U.S.C. 112(a) and pre-AIA 35 U.S.C. 112, first paragraph (MPEP 2173.05(i)).
Claim 1 recites “neither the feature map extracted from the last layer of the teacher network, nor the feature map extracted from the last layer of the student network, nor training data of a source domain on which the pretrained model was trained, is stored in the teacher network representation memory or the student network representation memory” in its sixth limitation. While the instant specification doesn’t disclose storing feature maps or training data in the representation memories, it fails to disclose explicitly not storing these elements in the memories.
Thus, claim 1 contains new matter not described in the instant specification, and fails to comply with the written description requirement. This deficiency is present in substantially similar independent claims 10-11 and is inherited by all dependent claims.
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claims 2-3 and 12-13 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Claim 2 recites “wherein the teacher network and the student network designate models trained in a previous task as a teacher model and a student model of a current task respectively” as its second limitation. It’s unclear whether this is intended to convey that the teacher and student networks of the current task were also trained as, respectively, teacher and student networks of a previous task, or whether it’s intended to convey that the teacher network was trained as a model for the previous task while the student network is of a current task. Thus, the scope of the claim is rendered indefinite. This deficiency is present in substantially similar claim 12. This limitation is interpreted as conveying the latter meaning, conveying that the teacher network was trained as a teacher model in a previous task while the student network is a student model of the current task.
Claim 3 recites “wherein the step (b) includes … generating representation memories as many as the number of classes for storing the feature representation values”. It’s unclear whether these “representation memories” are intended to coincide with the representation memories generated in step (b) of parent claim 1. Thus, the scope of the claim is rendered indefinite. This deficiency is present in substantially similar claim 13. The generated “representation memories” of this claim are interpreted as potentially being either synonymous with the representation memories of parent claim 1 or distinct from them.
Allowable Subject Matter
Claims 1-3, 5-6, 8-13, 15-16, and 18-19 would be allowable over the prior art of record if rewritten or amended to overcome the rejection(s) under 35 U.S.C. 112(a) and 112(b) set forth in this Office action.
Regarding claim 1, “wherein the feature representation values stored in each of the teacher-network representation memory and the student-network representation memory consist of the average values of the max-pooled feature maps calculated in the steps (c) and (d), such that neither the feature map extracted from the last layer of the teacher network, nor the feature map extracted from the last layer of the student network, nor training data of a source domain on which the pretrained model was trained, is stored in the teacher-network representation memory or the student network representation memory” is not taught by the prior art of record. The closest prior arts of record are Cermelli (Prototype-based Incremental Few-Shot Semantic Segmentation, published 10/18/2021, arXiv:2012.01415v2) and Peng (IMAGE RECOGNITION METHOD, APPARATUS, SERVER, AND STORAGE MEDIUM, published 7/11/2019, US 2019/0213448 A1).
Cermelli discloses a method, wherein the feature representation values stored in each of the teacher-network representation memory and the student-network representation memory consist of the average values of the max-pooled feature maps calculated in the steps (c) and (d), such that neither the feature map extracted from the last layer of the teacher network, nor the feature map extracted from the last layer of the student network, nor training data of a source domain on which the pretrained model was trained, is stored in the teacher-network representation memory or the student network representation memory:
“Initializing prototypes (feature representation values) of new classes. Given a dataset
D
t
, let us denote as
K
t
the set of new classes, i.e.
K
t
=
C
t
\
C
t
-
1
. After the base step, features of a class
k
∈
K
t
provide an estimate of the prototype
w
k
. Thus, we compute the new class prototypes by aggregating the features (feature map[s]) extracted for each pixel of the class k present in images of
D
t
. Inspired by [8, 43, 49], we use masked average pooling (MAP) to initialize the prototypes:
PNG
media_image1.png
172
952
media_image1.png
Greyscale
”(Cermelli, page 5, paragraph 2). The student network uses its extracted features to calculate prototypes at step t.
“we set
Φ
(teacher network)
=
ϕ
^
t
, where
ϕ
^
t
=
g
^
t
∘
f
t
-
1
and the parameters
W
^
t
=
[
w
^
1
t
,
…
,
w
^
C
t
t
]
(feature representation values) of
g
^
t
as:
PNG
media_image2.png
152
585
media_image2.png
Greyscale
” (Cermelli, page 5, paragraph 4). The teacher network uses the feature map extractor of time step t-1 when teaching the student model at time t.
Cermelli does not disclose computing max-pooled feature maps or a system in which feature maps from the last layer of a network and training data of a source domain of a pretrained model is excluded from student and teacher network representation memories.
Peng discloses a method, wherein the feature representation values stored in each of the teacher-network representation memory and the student-network representation memory consist of the average values of the max-pooled feature maps calculated in the steps (c) and (d), such that neither the feature map extracted from the last layer of the teacher network, nor the feature map extracted from the last layer of the student network, nor training data of a source domain on which the pretrained model was trained, is stored in the teacher-network representation memory or the student network representation memory:
“the convolution operation and the maximum pooling operation are performed on a last convolution layer and a feature vector (feature map) in the last convolution layer is obtained” (Peng, [0047])
Peng does not disclose storing feature representation values in student and teacher network representation memories, nor does it disclose exclusions of feature map data or training data in memory storage.
Therefore, the prior art of record, individually or in combination, does not disclose the entirety of claim 1 as a whole. Independent claims 10 and 11 are similarly not disclosed in their entirety by the prior art of record. All dependent claims would be allowable at least due to their dependence on the independent claims.
Response to Arguments
The following responses address arguments and remarks made in the instant remarks dated 07/14/2026.
112 Rejections
On pages 17-18 of the instant remarks, the Applicant argues that the amended claims are supported by the instant specification:
“Traceability Mapping for Max Pooling
The following mapping is provided solely to demonstrate written description support
for the amended claim language. No limitation from the Specification is intended to be read
into the claims, and the claims are not limited to the specific embodiments described in the
cited passages. Accordingly, the mapping is presented for the Examiner's convenience as
illustrative support only, and is neither intended to be exhaustive nor to limit the scope of the
claims to any particular embodiment described in the Specification.
PNG
media_image3.png
32
826
media_image3.png
Greyscale
…
PNG
media_image4.png
214
826
media_image4.png
Greyscale
”
The Examiner respectfully disagrees that all limitations of the amended claims are supported by the instant specification.
While paragraphs [81-82] of the instant specification fail to disclose storing extracted feature maps into representation memory, the specification fails to disclose the negative limitation of not storing extracted feature maps in either student or teacher network memory representations.
Similarly, while paragraphs [5-9] fail to disclose storing training data in the student or teacher representation memories, they fail to disclose the negative limitation of not storing training data in either memory representation. While paragraphs [31-36] describe excluding source domain data from the knowledge distillation process, they fail to describe specifically not storing source domain training data in the representation memories.
Thus, amended claim 1 is found to contain new matter not supported by the written description, and is rejected under 35 U.S.C. 112(a). This deficiency is present in substantially similar independent claims 10-11, and inherited by all dependent claims.
Additionally, claims 2-3 and 12-13 are found to be indefinite, and are rejected under 35 U.S.C. 112(b).
103 Rejections & Allowable Subject Matter
In light of the instant amendments, previous rejections under 35 U.S.C. 103 have been withdrawn.
Claims 1-3, 5-6, 8-13, 15-16, and 18-19 would be allowable over the prior art of record if rewritten or amended to overcome the rejection(s) under 35 U.S.C. 112(a) and 112(b) set forth in this Office action.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure:
Rebuffi et al. (iCaRL: Incremental Classifier and Representation Learning, published 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition pp. 5533 – 5542) discloses a method of incremental learning through prototypical feature representations
Jeon et al. (T-GD: Transferable GAN-generated Images Detection Framework, published 8/10/2020, arXiv:2008.04115v1) discloses a method of using knowledge distillation to produce a domain-adapted GAN
Bengio et al. (Representation Learning: A Review and New Perspectives, published 2014, arXiv:1206.5538v3) discloses a survey of methods for CNN representation learning
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Aaron P Gormley whose telephone number is (571)272-1372. The examiner can normally be reached Monday - Friday 12:00 PM - 8:00 PM EST.
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, Michelle T Bechtold can be reached at (571) 431-0762. 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.
/AG/Examiner, Art Unit 2148 /MICHELLE T BECHTOLD/Supervisory Patent Examiner, Art Unit 2148
Prosecution Insights