Related papers: Image-to-Video Re-Identification via Mutual Discri…

Recent breakthroughs in the field of semi-supervised learning have achieved results that match state-of-the-art traditional supervised learning methods. Most successful semi-supervised learning approaches in computer vision focus on…

Knowledge Distillation (KD) for object detection aims to train a compact detector by transferring knowledge from a teacher model. Since the teacher model perceives data in a way different from humans, existing KD methods only distill…

Recently, CLIP has become an important model for aligning images and text in multi-modal contexts. However, researchers have identified limitations in the ability of CLIP's text and image encoders to extract detailed knowledge from pairs of…

The recent success of denoising diffusion models has significantly advanced text-to-image generation. While these large-scale pretrained models show excellent performance in general image synthesis, downstream objectives often require…

Knowledge distillation (KD) is a common approach to compress a teacher model to reduce its inference cost and memory footprint, by training a smaller student model. However, in the context of autoregressive language models (LMs), we…

Knowledge Distillation is a technique which aims to utilize dark knowledge to compress and transfer information from a vast, well-trained neural network (teacher model) to a smaller, less capable neural network (student model) with improved…

Vision Transformers (ViTs) have achieved strong performance in video action recognition, but their high computational cost limits their practicality. Lightweight CNNs are more efficient but suffer from accuracy gaps. Cross-Architecture…

The field of Continual Learning (CL) has inspired numerous researchers over the years, leading to increasingly advanced countermeasures to the issue of catastrophic forgetting. Most studies have focused on the single-class scenario, where…

This thesis aims to investigate the feasibility of knowledge transfer between neural networks for medical image segmentation tasks, specifically focusing on the transfer from a larger multi-task "Teacher" network to a smaller "Student"…

Knowledge distillation (KD) is a technique that compresses large teacher models by training smaller student models to mimic them. The success of KD in auto-regressive language models mainly relies on Reverse KL for mode-seeking and…

Point-cloud based 3D object detectors recently have achieved remarkable progress. However, most studies are limited to the development of network architectures for improving only their accuracy without consideration of the computational…

Vehicle re-identification (Vehicle ReID) aims at retrieving vehicle images across disjoint surveillance camera views. The majority of vehicle ReID research is heavily reliant upon supervisory labels from specific human-collected datasets…

In this work, we propose Mutual Information Maximization Knowledge Distillation (MIMKD). Our method uses a contrastive objective to simultaneously estimate and maximize a lower bound on the mutual information of local and global feature…

Knowledge distillation (KD) is an efficient framework for compressing large-scale pre-trained language models. Recent years have seen a surge of research aiming to improve KD by leveraging Contrastive Learning, Intermediate Layer…

Camera-based temporal 3D object detection has shown impressive results in autonomous driving, with offline models improving accuracy by using future frames. Knowledge distillation (KD) can be an appealing framework for transferring rich…

Compared with the feature-based distillation methods, logits distillation can liberalize the requirements of consistent feature dimension between teacher and student networks, while the performance is deemed inferior in face recognition.…

Knowledge distillation (KD) exploits a large well-trained model (i.e., teacher) to train a small student model on the same dataset for the same task. Treating teacher features as knowledge, prevailing methods of knowledge distillation train…

Transformer-based encoder-decoder models have achieved remarkable success in image-to-image transfer tasks, particularly in image restoration. However, their high computational complexity-manifested in elevated FLOPs and parameter…

The Information Bottleneck (IB) provides an information theoretic principle for representation learning, by retaining all information relevant for predicting label while minimizing the redundancy. Though IB principle has been applied to a…

Knowledge distillation~(KD) is an effective learning paradigm for improving the performance of lightweight student networks by utilizing additional supervision knowledge distilled from teacher networks. Most pioneering studies either learn…