Internet usage growth generates massive data, prompting adoption of supervised/semi-supervised machine learning. Pre-deployment model evaluation, considering worst-case recall and fairness, is crucial. Current techniques lack on non-decomposable objectives; theoretical methods demand building new models for each. Introducing SelMix—a selective mixup-based, cost-effective fine-tuning for pre-trained models. SelMix optimizes specific objectives through feature mixup between class samples. Outperforming existing methods on imbalanced classification benchmarks, SelMix significantly enhances practical, non-decomposable objectives.

SelMix is a fine-tuning technique designed to enhance machine learning models' performance on imbalanced data with non-decomposable objectives, such as fairness criteria. It optimizes feature mixup between specific classes to address class imbalance and outperforms existing methods on benchmark datasets.

This work introduces the Cost-Sensitive Self-Training (CSST) framework, which extends self-training-based methods to optimize non-decomposable metrics in practical machine learning systems. The CSST framework proves effective in improving non-decomposable metric optimization using unlabeled data, leading to better results in various vision and NLP tasks compared to the state-of-the-art methods.

In Submission

In Submission

An information processing apparatus includes one or more memories; and one or more processors coupled to the one or more memories, the one or more processors being configured to decide a gain matrix based on an input metric, perform selection of first training data from a plurality of unlabeled training data, to be used for training a machine learning model, based on the gain matrix, and perform training of the machine learning model based on the first training data, a predicted label that is predicted from the first training data, and a loss function including the gain matrix.

An information processing apparatus includes one or more memories; and one or more processors coupled to the one or more memories, the one or more processors being configured to decide a gain matrix based on an input metric, perform selection of first training data from a plurality of unlabeled training data, to be used for training a machine learning model, based on the gain matrix, and perform training of the machine learning model based on the first training data, a predicted label that is predicted from the first training data, and a loss function including the gain matrix.

The project aims at achieving an image transformation from a low exposure image taen in a dimly lit environment to that taken by a long exposure camera.the dataset that has been used is the SID. Dataset prepared thanks to C. Chen et. al. For detailed analysis please refer to the project report named report.pdf .

This work involves the use of an encoder decoder architecture CNN for semantic segmentation of the image. We took inspiration from LinkNet for the same and trained our model oon both the mapillary dataset and the Berkley Deep Drive dataset.

This project incorporates a supervised super-resolution scheme by having the process of super-resolving the image to a slightly lesser resoltion. This approach allows the model to learn necessary features at each scale of resolution.This work is highly inspired by Yifan Wang et-al who followed a simillar progressive super-resolution approach.