# US 2020/0394458 A1 · Weakly-supervised object detection using one or more neural networks > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2020/0394458 A1 - Document ID: US20200394458A1 - Status: Published application - Kind: A1 - Application number: 16/443,346 - Filed: 2019-06-17 - Published: 2020-12-17 - Earliest claimed: 2019-06-17 - Assignees: NVIDIA Corporation - Applicants: Nvidia Corporation - Inventors: Zhiding Yu; Jason Ren; Xiaodong Yang; Ming-Yu Liu; Jan Kautz - Web page: https://patentgrep.com/patent/US20200394458A1 ## CPC - G06N 3/084: Backpropagation, e.g. using gradient descent - G06F 18/2113: by ranking or filtering the set of features, e.g. using a measure of variance or of feature cross-correlation - G06F 18/214: Generating training patterns; Bootstrap methods, e.g. bagging or boosting - G06F 18/217: {Validation; Performance evaluation; Active pattern learning techniques} - G06N 3/045: Combinations of networks - G06N 3/0464: Convolutional networks [CNN, ConvNet] - G06N 3/0495: Quantised networks; Sparse networks; Compressed networks - G06N 3/08: Learning methods - G06N 3/082: modifying the architecture, e.g. adding, deleting or silencing nodes or connections - G06N 3/0895: Weakly supervised learning, e.g. semi-supervised or self-supervised learning - G06V 10/25: Determination of region of interest [ROI] or a volume of interest [VOI] - G06V 10/454: {Integrating the filters into a hierarchical structure, e.g. convolutional neural networks [CNN]} - G06V 10/7753: {Incorporation of unlabelled data, e.g. multiple instance learning [MIL]} - G06V 10/82: using neural networks - G06V 20/10: Terrestrial scenes (scenes under surveillance with static cameras G06V20/52; scenes perceived from the exterior of a vehicle G06V20/56; scenes perceived from the interior of a vehicle G06V20/59) - G06N 3/047: Probabilistic or stochastic networks - G06N 3/049: Temporal neural networks, e.g. delay elements, oscillating neurons or pulsed inputs - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING ## Abstract Apparatuses, systems, and techniques to detect object in images including digital representations of those objects. In at least one embodiment, one or more objects are detected in an image based, at least in part, on one or more pseudo-labels corresponding to said one or more objects. ## Claims ### Claim 1 A processor, comprising: one or more arithmetic logic units (ALUs) to help detect one or more objects in an image based, at least in part, on one or more pseudo-labels corresponding to the one or more objects. ### Claim 2 (depends on 1) The processor of claim 1, wherein the one or more ALUs are further to be configured to: detect the one or more objects using a neural network that is trained in part by generating a region of interest (ROI) score for each of a set of object proposals, the one or more pseudo-labels determined using the ROI scores. ### Claim 3 (depends on 2) The processor of claim 2, wherein the one or more ALUs are further to be configured to: detect the one or more objects using a neural network that is trained in part by providing the ROI score to at least one refinement branch capable of producing a refined ROI score for the one or more pseudo-labels. ### Claim 4 (depends on 3) The processor of claim 3, wherein the at least one refinement branch performs at least one of ROI quantization and selection, or removal of pseudo-labels for redundant proposals. ### Claim 5 (depends on 1) The processor of claim 1, wherein the one or more ALUs are further to be configured to: detect the one or more objects using a neural network that is trained in part by selecting the one or more pseudo-labels corresponding to the one or more objects having refined ROI scores that exceed an object threshold. ### Claim 6 A system comprising: one or more processors to be configured to detect, using one or more neural networks, one or more objects in an image based, at least in part, on one or more pseudo-labels corresponding to the one or more objects; and one or more memories to store the one or more neural networks. ### Claim 7 (depends on 6) The system of claim 6, wherein the one or more processors are further to be configured to: detect the one or more objects using a neural network that is trained in part by generating a region of interest (ROI) score for each of a set of object proposals, the one or more pseudo-labels determined using the ROI scores. ### Claim 8 (depends on 7) The system of claim 7, wherein the one or more processors are further to be configured to: detect the one or more objects using a neural network that is trained in part by providing the ROI score to at least one refinement branch capable of producing a refined ROI score for the one or more pseudo-labels. ### Claim 9 (depends on 8) The system of claim 8, wherein the at least one refinement branch performs at least one of ROI quantization and selection, or removal of pseudo-labels for redundant proposals. ### Claim 10 (depends on 6) The system of claim 6, wherein the one or more processors are further to be configured to: detect the one or more objects using a neural network that is trained in part by selecting the one or more pseudo-labels corresponding to the one or more objects having refined ROI scores that exceed an object threshold. ### Claim 11 A processor comprising: one or more arithmetic logic units (ALUs) to help train one or more neural networks to be used to detect one or more objects in an image based, at least in part, on one or more pseudo-labels corresponding to the one or more objects. ### Claim 12 (depends on 11) The processor of claim 11, wherein the one or more ALUs are further to be configured to: generate a region of interest (ROI) score for each of a set of object proposals, the one or more pseudo-labels determined using the ROI scores. ### Claim 13 (depends on 12) The processor of claim 12, wherein the one or more ALUs are further to be configured to: provide the ROI score to at least one refinement branch capable of producing a refined ROI score for the one or more pseudo-labels. ### Claim 14 (depends on 13) The processor of claim 13, wherein the at least one refinement branch performs at least one of ROI quantization and selection, or removal of pseudo-labels for redundant proposals. ### Claim 15 (depends on 11) The processor of claim 11, wherein the one or more ALUs are further to be configured to: select the one or more pseudo-labels corresponding to the one or more objects having refined ROI scores that exceed an object threshold. ### Claim 16 A system comprising: one or more processors to help train one or more neural networks to be used to detect one or more objects in an image based, at least in part, on one or more pseudo-labels corresponding to the one or more objects. ### Claim 17 (depends on 16) The system of claim 16, wherein the one or more processors are further to be configured to: generate a region of interest (ROI) score for each of a set of object proposals, the one or more pseudo-labels determined using the ROI scores. ### Claim 18 (depends on 17) The system of claim 17, wherein the one or more processors are further to be configured to: provide the ROI score to at least one refinement branch capable of producing a refined ROI score for the one or more pseudo-labels. ### Claim 19 (depends on 18) The system of claim 18, wherein the at least one refinement branch performs at least one of ROI quantization and selection, or removal of pseudo-labels for redundant proposals. ### Claim 20 (depends on 17) The system of claim 17, wherein the one or more processors are further to be configured to: select the one or more pseudo-labels corresponding to the one or more objects having refined ROI scores that exceed an object threshold. ### Claim 21 A method comprising: training one or more neural networks to detect one or more objects in an image based, at least in part, on one or more pseudo-labels corresponding to the one or more objects. ### Claim 22 (depends on 21) The method of claim 21, further comprising: generating a region of interest (ROI) score for each of a set of object proposals, the one or more pseudo-labels determined using the ROI scores. ### Claim 23 (depends on 22) The method of claim 22, further comprising: providing the ROI score to at least one refinement branch capable of producing a refined ROI score for the one or more pseudo-labels. ### Claim 24 (depends on 23) The method of claim 23, wherein the at least one refinement branch performs at least one of ROI quantization and selection, or removal of pseudo-labels for redundant proposals. ### Claim 25 (depends on 21) The method of claim 21, further comprising: selecting the one or more pseudo-labels corresponding to the one or more objects having refined ROI scores that exceed an object threshold. ### Claim 26 A system, comprising: a camera configured to capture an image; one or more processors to be configured to detect, using one or more neural networks, one or more objects in the image based, at least in part, on one or more pseudo-labels corresponding to the one or more objects; and a storage device to store information regarding the detected objects. ### Claim 27 (depends on 26) The system of claim 26, wherein the one or more processors are further to be configured to: detect the one or more objects using a neural network that is trained in part by generating a region of interest (ROI) score for each of a set of object proposals, the one or more pseudo-labels determined using the ROI scores. ### Claim 28 (depends on 27) The system of claim 27, wherein the one or more processors are further to be configured to: detect the one or more objects using a neural network that is trained in part by providing the ROI score to at least one refinement branch capable of producing a refined ROI score for the one or more pseudo-labels. ### Claim 29 (depends on 28) The system of claim 28, wherein the at least one refinement branch performs at least one of ROI quantization and selection, or removal of pseudo-labels for redundant proposals. ### Claim 30 (depends on 26) The system of claim 26, wherein the one or more processors are further to be configured to: detect the one or more objects using a neural network that is trained in part by selecting the one or more pseudo-labels corresponding to the one or more objects having refined ROI scores that exceed an object threshold.