DETAILED ACTION
Notice of Pre-AIA or AIA Status
This is in response to application no.18/855,935 filed on 10/10/2024. The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Claim Rejections - 35 USC § 102
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 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.
Claim(s) 1, 2, 4, 6-10, 12 and 14-21 is/are rejected under 35 U.S.C. 102(a)(2) as being anticipated by Kim et al. (US 20230105112 A1).
Regarding claim 1, Kim teaches a method of encoding a tensor including a first set of feature maps and a second set of feature maps, a feature map in the first set having a first size (¶0113-0116, Figs. 9-12: feature maps P2, P3, P4, P5), and a feature map in the second set having a second size lager than the first size (See Figs. 9-12: the size of P2-P5 in a decreasing order), the method comprising: upsampling the first set of feature maps (See Figs. 11-12: down/up-sampling steps on P2 and P3); deriving basis vectors by performing a predetermined process on a tensor including the upsampled first set of feature maps (¶0108, 0113-0116: performing down-sampling to the size of a smaller transform unit or up-sampling to the size of a larger transform unit, and a transform vector may be derived using the transform units. See Fig. 11: down/up-sampling step on P2 followed by a transform vector derivation) and the second set of feature maps (a transform vector derivation on P3-P5); and deriving coefficients for the tensor using the derived basis vectors to encode the tensor (Figs. 11-12, ¶0113: outputting transform coefficients P2-P5 based on the derived transform vectors. See Figs. 3 illustrating encoding steps of the feature map).
Regarding claim 2, Kim teaches the method according to claim 1, the method further comprising: determining whether the up-sampling the first set of feature maps is executed (¶0065, 0111: transforming the feature map at step S120 may include down-sampling or up-sampling the transform unit when the size of the transform vector differs from the size of the transform unit).
Regarding claim 4, Kim teaches the method according to claim 1, the method further comprising: determining whether the upsampling the first set of feature maps is to be executed; and determining whether downsampling the second set of feature maps is to be executed (¶0065, 0111: transforming the feature map at step S120 may include down-sampling or up-sampling the transform unit when the size of the transform vector differs from the size of the transform unit), wherein the predetermined process is executed on the tensor including the upsampled first set of feature maps and the second set of feature maps, if the up-sampling is determined to be executed (See Figs. 11-12: down/up-sampling steps), wherein, if the downsampling of the second set of feature maps is determined to be executed, the method further comprises: downsampling the second set of feature maps (¶0114-0115: P2 is down-sampled to the size of P3); deriving basis vectors by performing the predetermined process on a tensor including the first set of feature maps and the down-sampled second set of feature maps (¶0113-0116: a transform vector derivation on a down-sampled feature map P2), and deriving coefficients for the tensor using the derived basis vectors (¶0113: outputting transform coefficients P2-P5).
Regarding claim 6, Kim teaches the method according to claim 1, wherein the derived basis vectors are used for deriving both coefficients for the first set of feature maps and coefficients for the second set of feature maps (Fig. 11, ¶0115-0116: transform vector derivation for P2 and P3 and outputting transform coefficients P2, P3).
Regarding claim 7, Kim teaches the method according to claim 11wherein the predetermined process is a PCA (principal component analysis) process (¶0107: the optimum transform vector for a transform unit group may be derived using all or some of the transform units in the transform unit group through a method such as PCA).
Regarding claim 8, Kim teaches a method of decoding, from encoded data, a first set of feature maps comprising: decoding basis vectors and coefficients from the encoded data (Figs. 14-17: P2-P5 transform coefficients, ¶0139, 0142- 0143: FIGS. 15 to 16 are examples of operation of an inverse feature-map transformer according to different inputs…because the feature maps P2, P3, P4, and P5 are included in different transform unit groups, different transform vector sets may be input to the respective inverse feature-map transformers); deriving a tensor using at least the decoded basis vectors and the decoded coefficients (¶0143-0144, Fig. 15-17: i.e., feature maps P2-P3 generated by inputting P2-P5 transform coefficients and different transform vectors into the respective inverse feature-map transformers); dividing the derived tensor into at least a first part of the derived tensor and a second part of the derived tensor (¶0151: feature map P2 may be generated by up-sampling or down-sampling the reconstructed feature map P3. See Fig. 17 illustrating feature maps P2 and P3 generated from P3 transform coefficient/transform vector); and deriving the first set of feature maps by downsampling the first part of the derived tensor (Fig. 17: ¶0151: feature map P2 may be generated by up-sampling or down-sampling the reconstructed feature map P3).
Regarding claim 9, Kim teaches the method according to claim 8, wherein the derived tensor includes a second set of feature maps, wherein a feature map in the second set has a second size larger than the first size (See Figs. 15-17: feature maps P2-P5 having different sizes of decreasing order).
Regarding claim 10, Kim teaches the method according to claim 8, the method further comprising: determining whether the downsampling is executed, wherein, the down-sampling is executed, based on a determination that the downsampling is executed (¶0151: feature map P2 may be generated by up-sampling or down-sampling the reconstructed feature map P3).
Regarding claim 12, Kim teaches the method according to claim 8, the method further comprising: determining whether the downsampling is executed, determining whether upsampling a second part of the derived tensor is executed (Fig. 17, ¶0151: feature map P2 may be generated by up-sampling or down-sampling the reconstructed feature map P3); wherein, the downsampling is executed (Fig. 17, ¶0151: feature map P2 may be generated by up-sampling or down-sampling the reconstructed feature map P3), if the up-sampling is determined to be executed (¶0115: Figs. 11-12: P3 may be up-sampled to the size of P2), wherein, if the upsampling of the second part of the derived tensor is determined to be executed, the method further comprises: deriving a second set of feature maps by upsampling the second part of the derived tensor (Fig. 17, ¶0151: feature map P2 may be generated by up-sampling or down-sampling the reconstructed feature map P3), wherein a feature map in the second set has a second size larger than the first size (See Fig. 17: P2 having a size larger than P3).
Regarding claim 14, Kim teaches the method according to claim 9,wherein the decoded basis vectors are used for deriving both the first set of feature maps and the second set of feature maps (¶0143-0144, Fig. 15-17: i.e., feature maps P2-P3 generated by inputting P2-P5 transform coefficients and different transform vectors into the respective inverse feature-map transformers).
Regarding claim 15, Kim teaches the method according to claim 8, wherein the basis vectors are derived by a PCA (principal component analysis) process (¶0107: the optimum transform vector for a transform unit group may be derived using all or some of the transform units in the transform unit group through a method such as PCA ).
Regarding claim 16, the claim is drawn to an encoder claim and recites the limitation analogous to claim 1, and is rejected due to the same reason set forth above with respect to claim 1.
Regarding claim 17, the claim is drawn to a non-transitory computer-readable storage medium claim and recites the limitation analogous to claim 1, and is rejected due to the same reason set forth above with respect to claim 1.
Regarding claim 18, the claim is drawn to a system claim and recites the limitation analogous to claim 1, and is rejected due to the same reason set forth above with respect to claim 1.
Regarding claim 19, the claim is drawn to a decoder claim and recites the limitation analogous to claim 8, and is rejected due to the same reason set forth above with respect to claim 8.
Regarding claim 20, the claim is drawn to a non-transitory computer-readable storage medium claim and recites the limitation analogous to claim 8, and is rejected due to the same reason set forth above with respect to claim 8.
Regarding claim 21, the claim is drawn to a system claim and recites the limitation analogous to claim 8, and is rejected due to the same reason set forth above with respect to claim 8.
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.
Claim(s) 3, 5, 11 and 13 is/are rejected under 35 U.S.C. 103 as being unpatentable over Kim et al. (US 20230105112 A1) in view of Gao et al. (US 20230336736 A1).
Regarding claim 3, Kim does not explicitly disclose the method further comprising: encoding information specifying that a decoded first set of feature maps is to be down-sampled in a decoding method, if a determination is made to upsample the first set of feature maps.
However, Gao teaches encoding information specifying that a decoded first set of feature maps is to be down-sampled in a decoding method, if a determination is made to upsample the first set of feature maps (¶0267, 0281: The decoder then performs up-sampling the luma component if the flag indicates that the luma has been subject to down-sampling on the encoder side. In turn, the decoder performs down-sampling of the chroma components if the flag indicates that the chroma components have been subject to up-sampling on the encoder side).
It would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to modify Kim’s method/apparatus for encoding/decoding feature map by incorporating the teaching of Gao as noted above, in order to match the originally coded feature map by performing resizing operation at the decoder (¶0267).
Regarding claim 5, Kim does not explicitly teach the method further comprising: encoding, into the bitstream, information specifying that a decoded second set of feature maps is to be up-sampled in a decoding method, based on a determination that down-sampling the second set of feature maps is executed.
However, Gao teaches the method further comprising: encoding, into the bitstream, information specifying that a decoded second set of feature maps is to be up-sampled in a decoding method, based on a determination that down-sampling the second set of feature maps is executed (¶0267, 0281: The decoder then performs up-sampling the luma component if the flag indicates that the luma has been subject to down-sampling on the encoder side. In turn, the decoder performs down-sampling of the chroma components if the flag indicates that the chroma components have been subject to up-sampling on the encoder side).
It would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to modify Kim’s method/apparatus for encoding/decoding feature map by incorporating the teaching of Gao as noted above, in order to match the originally coded feature map by performing resizing operation at the decoder (¶0267).
Regarding claim 11, Kim does not explicitly disclose decoding information specifying that the first part of the derived tensor is to be downsampled.
However, Gao teaches decoding information specifying that the first part of the derived tensor is to be downsampled (¶0267, 0281: The decoder then performs up-sampling the luma component if the flag indicates that the luma has been subject to down-sampling on the encoder side. In turn, the decoder performs down-sampling of the chroma components if the flag indicates that the chroma components have been subject to up-sampling on the encoder side).
It would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to modify Kim’s method/apparatus for encoding/decoding feature map by incorporating the teaching of Gao as noted above, in order to match the originally coded feature map by performing resizing operation at the decoder (¶0267).
Regarding claim 13, Kim does not explicitly disclose decoding information specifying that the second part of the derived tensor is to be upsampled.
However, Gao teaches decoding information specifying that the second part of the derived tensor is to be upsampled (¶0267, 0281: The decoder then performs up-sampling the luma component if the flag indicates that the luma has been subject to down-sampling on the encoder side. In turn, the decoder performs down-sampling of the chroma components if the flag indicates that the chroma components have been subject to up-sampling on the encoder side).
It would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to modify Kim’s method/apparatus for encoding/decoding feature map by incorporating the teaching of Gao as noted above, in order to match the originally coded feature map by performing resizing operation at the decoder (¶0267).
The following is the prior art made of record and not relied upon is considered pertinent to applicant’s disclosure.
Liu et al. (US 20220392202 A1) describes “performing feature extraction on an image to be processed to obtain a first feature map of the image to be processed and performing weight prediction on the first feature map to obtain a weight feature map of the first feature map.” Abstract.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to NATHNAEL AYNALEM whose telephone number is (571)270-1482. The examiner can normally be reached M-F 9AM-5:30 PM ET.
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, SATH PERUNGAVOOR can be reached at 571-272-7455. 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.
/NATHNAEL AYNALEM/Primary Examiner, Art Unit 2488
Prosecution Insights