Prosecution Insights
Last updated: April 19, 2026
Application No. 18/122,565

ONLINE TRAINING-BASED ENCODER TUNING IN NEURAL IMAGE COMPRESSION

Non-Final OA §102§103
Filed
Mar 16, 2023
Examiner
WENG, PEI YONG
Art Unit
2141
Tech Center
2100 — Computer Architecture & Software
Assignee
Tencent America LLC
OA Round
1 (Non-Final)
79%
Grant Probability
Favorable
1-2
OA Rounds
3y 3m
To Grant
99%
With Interview

Examiner Intelligence

Grants 79% — above average
79%
Career Allow Rate
506 granted / 637 resolved
+24.4% vs TC avg
Strong +23% interview lift
Without
With
+23.1%
Interview Lift
resolved cases with interview
Typical timeline
3y 3m
Avg Prosecution
18 currently pending
Career history
655
Total Applications
across all art units

Statute-Specific Performance

§101
12.4%
-27.6% vs TC avg
§103
49.3%
+9.3% vs TC avg
§102
19.2%
-20.8% vs TC avg
§112
8.8%
-31.2% vs TC avg
Black line = Tech Center average estimate • Based on career data from 637 resolved cases

Office Action

§102 §103
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 . DETAILED ACTION This action is responsive to the following communication: Non-Provisional Application filed Mar. 16, 2023. Claims 1-20 are pending in the case. Claims 1 and 11 are independent claims. 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)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention. Claims 1-8 and 11-18 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Besenbruch et al. (hereinafter Besenbruch) WO 2021/220008. With respect to independent claim 1, Besenbruch teaches a method for image coding, comprising: performing, based on one or more input images, an online training of a neural image compression (NIC) framework, the NIC framework being an end-to-end framework (see e.g., Page 8-9 – “the first computer system is a server, e.g. a dedicated server, e.g a machine in the cloud with dedicated GPUs e.g Amazon Web Services, Microsoft Azure, etc, or any other cloud computing services … the recipient device is a laptop computer, desktop computer, a tablet computer, a smart TV or a smart phone.” ) that comprises both (i) one or more first neural networks in an encoding portion and (ii) one or more second neural networks in a decoding portion, the online training determining a plurality of updated values to one or more tunable parameters in the one or more first neural networks, wherein the one or more second neural networks have non-tunable parameters (see e.g., Page 24 – “The method may be one wherein encoding the input image using the first trained neural network includes using one or more univariate or multivariate Padé activation units … The method may be one wherein using the second trained neural network to produce an output image from the quantized latent includes using one or more univariate or multivariate Padé activation units.” Page 94 - “Therefore, we incorporate more flexibility in entropy modelling by using parametric distributions as factorised prior. We achieve this by employing distributions with many degrees of freedom in the parametrisation, including shape, asymmetry and skewness. Note that the innovation is formulated irrespective of the method with which the parameters f are produced; these may be learned directly as fixed parameters (fully factorised prior), predicted by a hypernetwork (hyperprior) or by a context model (conditional model).” Page 132 - “The extent of the penalty can be adjusted with the cr parameter, which becomes a tunable hyperparameter.”); updating the one or more tunable parameters in the one or more first neural networks according to the plurality of updated values (see e.g., Page 25, 132 – “The method may be one wherein when back-propagating the gradient of the loss function through the second neural network and through the first neural network, parameters of the one or more univariate or multivariate Pade activation units of the first neural network are updated, and parameters of the one or more univariate or multivariate Pade activation units of the second neural network are updated.”); and encoding, by the encoding portion of the NIC framework with the one or more tunable parameters in the one or more first neural networks being updated, the one or more input images into a bitstream (see e.g. Page 3 – “entropy encoding the quantized latent into a bitstream”). With respect to dependent claim 2, Besenbruch teaches the non-tunable parameters of the one or more second neural networks are fixed at pretrained values from an offline training of the NIC framework (see e.g. Page 123 – “We propose to use any combination and number of losses here, for examples, one possible combination is to DMOS using deep pre-trained features whose weights are learnt using linear regression along with PSNR.”). With respect to dependent claim 3, Besenbruch teaches the NIC framework comprises a specific neural network in both of the encoding portion and the decoding portion, and the specific neural network comprises first parameters that are fixed during the online training (see e.g. Abstract and Page 10, 123). With respect to dependent claim 4, Besenbruch teaches the specific neural network comprises a hyper decoder network (see e.g. Page 59 – “”). With respect to dependent claim 5, Besenbruch teaches the performing the online training of the NIC framework further comprises: performing the online training with each of parameters in a main encoder network and a hyper encoder network of the NIC framework being tunable (see e.g. Page 133 – “' /QN can be initialised at beginning of network training of the original autoencoder, but optimised separately in a two-step training process. After a full forward and backward propagation, firstly the parameters for the autoencoder are updated with the first set of optimisation configurations.”). With respect to dependent claim 6, Besenbruch teaches the performing the online training of the NIC framework further comprises: performing the online training with a subset of parameters in a main encoder network and a hyper encoder network of the NIC framework being tunable (see e.g. Page 198 – “When only a small portion of latents are needed each iteration, the entire finetuning process can be parallelized. That is, on each iteration a “batch” of many small subsets of the latent vector are processed in parallel.”). With respect to dependent claim 7, Besenbruch teaches the performing the online training of the NIC framework further comprises: performing the online training with parameters of a layer in a main encoder network or a hyper encoder network of the NIC framework being tunable (see e.g. Page 133 – “Encoder or Decoder layers of a compression network train on rate on the rate distortion loss objective. Essentially we are using the layers of a trained compression network rather then one trained on classification.”). With respect to dependent claim 8, Besenbruch teaches the performing the online training of the NIC framework further comprises: performing the online training with parameters of a channel in a layer in a main encoder network or a hyper encoder network of the NIC framework being tunable (see e.g. Page 68, 121. 133 – “Figure 111 shows an example of a channel- wise fully connected convolutional network. Network layers (convolutional operations) proceed from top to bottom in the diagram. The output of each layer depends on all previous channels.”). Claim 11 is rejected for the similar reasons discussed above with respect to claim 1. Claim 12 is rejected for the similar reasons discussed above with respect to claim 2. Claim 13 is rejected for the similar reasons discussed above with respect to claim 3. Claim 14 is rejected for the similar reasons discussed above with respect to claim 4. Claim 15 is rejected for the similar reasons discussed above with respect to claim 5. Claim 16 is rejected for the similar reasons discussed above with respect to claim 6. Claim 17 is rejected for the similar reasons discussed above with respect to claim 7. Claim 18 is rejected for the similar reasons discussed above with respect to claim 8. Claim Rejections - 35 USC § 103 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. Claims 9-10 and 19-20 are rejected under 35 U.S.C. 103 as being unpatentable over Besenbruch in view of Kulkarni (hereinafter Kulkarni) U.S. Patent Publication No. 2013/0293738. With respect to claim 9, Besenbruch does not expressly show the performing the online training of the NIC framework further comprises: splitting an input image into a plurality of blocks; assigning respective step sizes to the plurality of blocks; and performing the online training of the NIC framework according to the plurality of blocks with the respective step sizes. However, Kulkarni teaches similar feature (see e.g. Para [19]-[24] – “The fixed-rate bitstream may be a fixed-rate bitstream at the granularity of image blocks. Each image block may be encoded into a portion of the bitstream that has a common size (e.g., a common number of available bits) and that is output at a common rate. However. within each image block, available bits may be allocated differently from the way in which available bits are allocated in other image blocks. The available bits may be allocated based on the content of the image data in that image block.”) Both Besenbruch and Kulkarni are directed to image compression methods. Accordingly, it would have been obvious to the skilled artisan before the effective filing date of the claimed invention having Besenbruch and Kulkarni in front of them to modify the system of Besenbruch to include the above feature. The motivation to combine Besenbruch and Kulkarni comes from Kulkarni. Kulkarni discloses the motivation to process image in blocks so that bits can be allocated differently based on blocks so that the efficiency can be improved (see e.g. Kulkarni Para [19]-[24]). With respect to claim 10, the modified Besenbruch teaches the performing the online training of the NIC framework further comprises: assigning a step size to an input image based on a type of content in the input image; and performing the online training of the NIC framework according to the input image with the step size (see e.g. Kulkarni Para [19]-[24]). Claim 19 is rejected for the similar reasons discussed above with respect to claim 9. Claim 20 is rejected for the similar reasons discussed above with respect to claim 10. Conclusion Any inquiry concerning this communication or earlier communications from the examiner should be directed to PEIYONG WENG whose telephone number is (571)270-1660. The examiner can normally be reached on Mon.-Fri. 8 am to 5 pm. If attempts to reach the examiner by telephone are unsuccessful, the examiner's supervisor, Matthew Ell, can be reached on (571) 270-3264. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300. Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see http://portal.uspto.gov/external/portal. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). /PEI YONG WENG/Primary Examiner, Art Unit 2141
Read full office action

Prosecution Timeline

Mar 16, 2023
Application Filed
Jan 11, 2026
Non-Final Rejection — §102, §103
Mar 03, 2026
Examiner Interview Summary
Mar 03, 2026
Applicant Interview (Telephonic)

Precedent Cases

Applications granted by this same examiner with similar technology

Patent 12602594
DIRECTED TRAJECTORIES THROUGH COMMUNICATION DECISION TREE USING ITERATIVE ARTIFICIAL INTELLIGENCE
2y 5m to grant Granted Apr 14, 2026
Patent 12579468
TRAINING DATA SCREENING DEVICE, ROBOT SYSTEM, AND TRAINING DATA SCREENING METHOD
2y 5m to grant Granted Mar 17, 2026
Patent 12572845
INTELLIGENT MACHINE-LEARNING MODEL CATALOG
2y 5m to grant Granted Mar 10, 2026
Patent 12561608
APPARATUS AND METHODS FOR PREDICTING SLIPPING EVENTS FOR MICROMOBILITY VEHICLES
2y 5m to grant Granted Feb 24, 2026
Patent 12555665
HOME EXERCISE PLAN PREDICTION
2y 5m to grant Granted Feb 17, 2026
Study what changed to get past this examiner. Based on 5 most recent grants.

AI Strategy Recommendation

Get an AI-powered prosecution strategy using examiner precedents, rejection analysis, and claim mapping.
Powered by AI — typically takes 5-10 seconds

Prosecution Projections

1-2
Expected OA Rounds
79%
Grant Probability
99%
With Interview (+23.1%)
3y 3m
Median Time to Grant
Low
PTA Risk
Based on 637 resolved cases by this examiner. Grant probability derived from career allow rate.

Sign in with your work email

Enter your email to receive a magic link. No password needed.

Personal email addresses (Gmail, Yahoo, etc.) are not accepted.

Free tier: 3 strategy analyses per month