Related papers: MixBCT: Towards Self-Adapting Backward-Compatible …

Most machine learning classifiers only concern classification accuracy, while certain applications (such as medical diagnosis, meteorological forecasting, and computation advertising) require the model to predict the true probability, known…

This paper explores the possibility of extending the capability of pre-trained neural image compressors (e.g., adapting to new data or target bitrates) without breaking backward compatibility, the ability to decode bitstreams encoded by the…

Lifelong person re-identification (LReID) assumes a practical scenario where the model is sequentially trained on continuously incoming datasets while alleviating the catastrophic forgetting in the old datasets. However, not only the…

Pretrained machine learning models need to be adapted to distribution shifts when deployed in new target environments. When obtaining labeled data from the target distribution is expensive, few-shot adaptation with only a few examples from…

Model merging combines task experts into one model and avoids joint training, retraining, or deploying many expert models, but the merged model often still underperforms task experts. We study this performance gap through feature drift, the…

A fundamental requirement for intelligent systems is the ability to learn continuously under changing environments. However, models trained in this regime often suffer from catastrophic forgetting. Leveraging pre-trained models has recently…

Mixed precision training (MPT) is becoming a practical technique to improve the speed and energy efficiency of training deep neural networks by leveraging the fast hardware support for IEEE half-precision floating point that is available in…

Computational cost of training state-of-the-art deep models in many learning problems is rapidly increasing due to more sophisticated models and larger datasets. A recent promising direction for reducing training cost is dataset…

Modern deep models are often pretrained on large-scale data with missing labels using composite objectives, where the relative weights of multiple loss terms act as hyperparameters. Tuning these weights with random search or Bayesian…

Deep learning usually relies on training large-scale data samples to achieve better performance. However, over-fitting based on training data always remains a problem. Scholars have proposed various strategies, such as feature dropping and…

The traditional paradigm to update retrieval models requires re-computing the embeddings of the gallery data, a time-consuming and computationally intensive process known as backfilling. To circumvent backfilling, Backward-Compatible…

Loss function is crucial for model training and feature representation learning, conventional models usually regard facial attractiveness recognition task as a regression problem, and adopt MSE loss or Huber variant loss as supervision to…

We propose a deep learning-based feature fusion approach for facial computing including face recognition as well as gender, race and age detection. Instead of training a single classifier on face images to classify them based on the…

Mining informative negative instances are of central importance to deep metric learning (DML), however this task is intrinsically limited by mini-batch training, where only a mini-batch of instances is accessible at each iteration. In this…

Domain reweighting can improve sample efficiency and downstream generalization, but data-mixture optimization for multimodal midtraining remains largely unexplored. Current multimodal training recipes tune mixtures along a single dimension,…

Federated learning benefits from cross-training strategies, which enables models to train on data from distinct sources to improve generalization capability. However, due to inherent differences in data distributions, the optimization goals…

Approximate unlearning has gained popularity as an approach to efficiently update an LLM so that it behaves (roughly) as if it was not trained on a subset of data to begin with. However, existing methods are brittle in practice and can…

Dataset Condensation (DC) aims to reduce deep neural networks training efforts by synthesizing a small dataset such that it will be as effective as the original large dataset. Conventionally, DC relies on a costly bi-level optimization…

Multi-task model merging aims to consolidate knowledge from multiple fine-tuned task-specific experts into a unified model while minimizing performance degradation. Existing methods primarily approach this by minimizing differences between…

The most existing studies in the facial age estimation assume training and test images are captured under similar shooting conditions. However, this is rarely valid in real-world applications, where training and test sets usually have…