Related papers: Everything old is new again: A multi-view learning…
Multi-task learns multiple tasks, while sharing knowledge and computation among them. However, it suffers from catastrophic forgetting of previous knowledge when learned incrementally without access to the old data. Most existing object…
We propose to accelerate the rate of convergence of the pattern recognition task by directly minimizing the variance diameters of certain hypothesis spaces, which are critical quantities in fast-convergence results.We show that the variance…
Knowledge distillation is a popular technique to transfer knowledge from large teacher models to a small student model. Typically, the student learns to imitate the teacher by minimizing the KL divergence of its output distribution with the…
Model merging offers an effective way to integrate the capabilities of multiple fine-tuned models. However, the performance degradation of the merged model remains a challenge, particularly when none or few data are available. This paper…
Knowledge distillation, transferring knowledge from a teacher model to a student model, has emerged as a powerful technique in neural machine translation for compressing models or simplifying training targets. Knowledge distillation…
Incremental learning methods can learn new classes continually by distilling knowledge from the last model (as a teacher model) to the current model (as a student model) in the sequentially learning process. However, these methods cannot…
Much of the focus in the area of knowledge distillation has been on distilling knowledge from a larger teacher network to a smaller student network. However, there has been little research on how the concept of distillation can be leveraged…
Explicit density learners are becoming an increasingly popular technique for generative models because of their ability to better model probability distributions. They have advantages over Generative Adversarial Networks due to their…
Knowledge distillation is initially introduced to utilize additional supervision from a single teacher model for the student model training. To boost the student performance, some recent variants attempt to exploit diverse knowledge sources…
Class-incremental with repetition (CIR), where previously trained classes repeatedly introduced in future tasks, is a more realistic scenario than the traditional class incremental setup, which assumes that each task contains unseen…
Modern deep learning approaches have achieved great success in many vision applications by training a model using all available task-specific data. However, there are two major obstacles making it challenging to implement for real life…
Distillation addresses the slow sampling problem in diffusion models by creating models with smaller size or fewer steps that approximate the behavior of high-step teachers. In this work, we propose a reinforcement learning based…
Knowledge distillation is typically conducted by training a small model (the student) to mimic a large and cumbersome model (the teacher). The idea is to compress the knowledge from the teacher by using its output probabilities as…
Lifelong imitation learning for manipulation tasks poses significant challenges due to distribution shifts that occur in incremental learning steps. Existing methods often focus on unsupervised skill discovery to construct an ever-growing…
Knowledge distillation (KD) is one of the prominent techniques for model compression. In this method, the knowledge of a large network (teacher) is distilled into a model (student) with usually significantly fewer parameters. KD tries to…
Depth estimation and scene segmentation are two important tasks in intelligent transportation systems. A joint modeling of these two tasks will reduce the requirement for both the storage and training efforts. This work explores how the…
Partial observability is a notorious challenge in reinforcement learning (RL), due to the need to learn complex, history-dependent policies. Recent empirical successes have used privileged expert distillation--which leverages availability…
One of the most efficient methods for model compression is hint distillation, where the student model is injected with information (hints) from several different layers of the teacher model. Although the selection of hint points can…
In the surveillance and defense domain, multi-target detection and classification (MTD) is considered essential yet challenging due to heterogeneous inputs from diverse data sources and the computational complexity of algorithms designed…
Pre-trained language-vision models have shown remarkable performance on the visual question answering (VQA) task. However, most pre-trained models are trained by only considering monolingual learning, especially the resource-rich language…