Related papers: Conditional Pseudo-Supervised Contrast for Data-Fr…

Knowledge distillation (KD) is a widely adopted technique for transferring knowledge from a high-capacity teacher model to a smaller student model by aligning their output distributions. However, existing methods often underperform in…

Weakly-supervised semantic segmentation aims to assign category labels to each pixel using weak annotations, significantly reducing manual annotation costs. Although existing methods have achieved remarkable progress in well-lit scenarios,…

In the era of large scale pretrained models, Knowledge Distillation (KD) serves an important role in transferring the wisdom of computationally heavy teacher models to lightweight, efficient student models while preserving performance.…

We introduce Layered Self-Supervised Knowledge Distillation (LSSKD) framework for training compact deep learning models. Unlike traditional methods that rely on pre-trained teacher networks, our approach appends auxiliary classifiers to…

Knowledge distillation (KD) is widely used for training a compact model with the supervision of another large model, which could effectively improve the performance. Previous methods mainly focus on two aspects: 1) training the student to…

Knowledge distillation (KD) aims at improving the performance of a compact student model by distilling the knowledge from a high-performing teacher model. In this paper, we present an adaptive KD approach, namely AdaDistill, for deep face…

Unsupervised anomaly detection using deep learning has garnered significant research attention due to its broad applicability, particularly in medical imaging where labeled anomalous data are scarce. While earlier approaches leverage…

Despite excellent performance in image generation, Generative Adversarial Networks (GANs) are notorious for its requirements of enormous storage and intensive computation. As an awesome ''performance maker'', knowledge distillation is…

Deep learning models remain vulnerable to spurious correlations, leading to so-called Clever Hans predictors that undermine robustness even in large-scale foundation and self-supervised models. Group distributional robustness methods, such…

Large-scale language models have recently demonstrated impressive empirical performance. Nevertheless, the improved results are attained at the price of bigger models, more power consumption, and slower inference, which hinder their…

Diffusion Probabilistic Models (DPMs) have emerged as a powerful class of deep generative models, achieving remarkable performance in image synthesis tasks. However, these models face challenges in terms of widespread adoption due to their…

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…

Data-Free Knowledge Distillation (DFKD) plays a vital role in compressing the model when original training data is unavailable. Previous works for DFKD in NLP mainly focus on distilling encoder-only structures like BERT on classification…

In the context of label-efficient learning on video data, the distillation method and the structural design of the teacher-student architecture have a significant impact on knowledge distillation. However, the relationship between these…

Knowledge Distillation (KD) refers to transferring knowledge from a large model to a smaller one, which is widely used to enhance model performance in machine learning. It tries to align embedding spaces generated from the teacher and the…

Diffusion probabilistic models (DPMs) have become a popular approach to conditional generation, due to their promising results and support for cross-modal synthesis. A key desideratum in conditional synthesis is to achieve high…

Dataset distillation aims to compress information from a large-scale original dataset to a new compact dataset while striving to preserve the utmost degree of the original data informational essence. Previous studies have predominantly…

Knowledge distillation (KD) is an effective framework that aims to transfer meaningful information from a large teacher to a smaller student. Generally, KD often involves how to define and transfer knowledge. Previous KD methods often focus…

Semi-supervised regression (SSR), which aims to predict continuous scores for samples while reducing the reliance on large-scale labeled data, has recently attracted considerable attention across various applications, including computer…

Knowledge Distillation (KD) has been validated as an effective model compression technique for learning compact object detectors. Existing state-of-the-art KD methods for object detection are mostly based on feature imitation. In this…