Abstract: Method and system for generating color variants for fashion apparels by providing a Fashion Apparel Regeneration—Generative Adversarial Network (FAR—GAN) to generate color variants of the fashion apparels. The FAR—GAN utilizes a two-step encoding process to encapsulate both an input image and an edge-map information along with a target color embedding branch to manipulate the color information present in the fashion apparel present in the input image that is to be changed to a desired target color. Furthermore, the color and structural information is disentangled by controlling them using a color consistency loss. The FAR—GAN can be trained end-to-end without incorporating complex multi-step process.

Abstract: The embodiments of present disclosure address unresolved problems of label inconsistency, where outputs of different levels create impossible combinations, and error propagation from previous level outputs can significantly impact its performance. Embodiments provide a method and system for a Progressive Multi-level Training framework with a Logit-masking strategy (PMTL) for a retail taxonomy classification. PMTL enables neural network models to be trained separately for each level to reduce error propagation problems. To further enhance the model's performance at each level and get the label-wise constraint from the previous level, the global representation from model of previous level is augmented. Further, a logit masking strategy is used to restrict model(s) to learning only relevant classes through part of final classification layer, thereby addressing label inconsistency issue, and incorporating benefit of parent node-based local classifier.

Abstract: Traditional systems used for fashion attribute detection struggle to generate accurate predictions due to presence of large intra-class and relatively small inter-class variations in data related to the fashion attributes. The disclosure herein generally relates to image processing, and, more particularly, to a method and system for fashion attribute detection. The method proposes F-AttNet, an attribute extraction network to leverage the performance of fine-grained localized fashion attribute recognition. F-AttNet comprises Attentive Multi-scale Feature Encoder (AMF) blocks that encapsulate multi-scale fine-grained attribute information upon adaptive recalibration of channel weights. F-AttNet is designed by hierarchically stacking the AMF encoders to extract deep fine-grained information across multiple scales.

Abstract: Unlike visual similarity, visual compatibility is a complex concept. Existing approaches for outfit compatibility prediction does not focus on methods with personalization. The present disclosure proposes a novel approach to model the user's preference for different styles. The outfit compatibility prediction module is a critical component of an outfit recommendation system. An outfit is said to be compatible if all the items are visually compatible and match the user's preferences. The present disclosure represents the outfit as a graph and uses Graph Neural Network (GNN) with attention mechanism to capture the inter-relationship between the items. A graph read-out layer generates the final outfit embedding. The proposed approach efficiently models the preferences of the users for different styles. Finally, the outfit compatibility score is generated by computing the similarity between the outfit embedding and the user embedding.

Abstract: State of the art techniques have challenges for recoloring a product, which includes non-realistic images, incorrect color mapping, structural distortion, color spilling into background, and in handling multi-color, multi-apparel and multi-product scenario images. Embodiments of the present disclosure provide a method and system for recoloring a product using a dual attention (DA) U-Net based on a generative adversarial network (GAN) framework to generate a recolored product with a target color from an input image. The disclosed DAU-Net enables recoloring (i) a single-color in a single-product scenario, (ii) a plurality of colors in a single-product scenario, and (iii) multi-product scenario with a human model.

Abstract: This disclosure relates generally to identification and mitigation of bias while training deep learning models. Conventional methods do not provide effective methods for bias identification, and they require pre-defined concepts and rules for bias mitigation. The embodiments of the present disclosure train an auto-encoder to produce a generalized representation of an input image by decomposing into a set of latent embedding. The set of latent embedding are used to learn the shape and color concepts of the input image. The feature specialization is done by training an auto-encoder to reconstruct the input image using the shape embedding modulated by color embedding. To identify the bias, permutation invariant neural network is trained for classification task and attribution scores corresponding to each concept embedding are computed. The method also performs de-biasing the classifier by training it with a set of counterfactual images generated by modifying the latent embedding learned by the auto-encoder.

Abstract: State of art techniques for color regeneration are complex and fail to provide color control. Embodiments of the present disclosure provide a method and system for generating color variants for fashion apparels by providing a Fashion Apparel Regeneration-Generative Adversarial Network (FAR-GAN) to generate color variants of the fashion apparels. The FAR-GAN utilizes a two-step encoding process to encapsulate both an input image and an edge-map information along with a target color embedding branch to manipulate the color information present in the fashion apparel present in the input image that is to be changed to a desired target color. Furthermore, the color and structural information is disentangled by controlling them using a color consistency loss. The FAR-GAN can be trained end-to-end without incorporating complex multi-step process.

Abstract: Traditional systems used for fashion attribute detection struggle to generate accurate predictions due to presence of large intra-class and relatively small inter-class variations in data related to the fashion attributes. The disclosure herein generally relates to image processing, and, more particularly, to a method and system for fashion attribute detection. The method proposes F-AttNet, an attribute extraction network to leverage the performance of fine-grained localized fashion attribute recognition. F-AttNet comprises Attentive Multi-scale Feature Encoder (AMF) blocks that encapsulate multi-scale fine-grained attribute information upon adaptive recalibration of channel weights. F-AttNet is designed by hierarchically stacking the AMF encoders to extract deep fine-grained information across multiple scales.