English
Related papers

Related papers: Self-Distillation of Hidden Layers for Self-Superv…

200 papers

Knowledge distillation from large language models (LLMs) assumes that the teacher's output distribution is a high-quality training signal. On reasoning tasks, this assumption is frequently violated. A model's intermediate representations…

Computation and Language · Computer Science 2026-03-16 Ryan Brown , Chris Russell

Despite the remarkable success of Self-Supervised Learning (SSL), its generalization is fundamentally hindered by Shortcut Learning, where models exploit superficial features like texture instead of intrinsic structure. We experimentally…

Computer Vision and Pattern Recognition · Computer Science 2025-09-23 Siming Fu , Sijun Dong , Xiaoliang Meng

This paper introduces a cutting-edge method for enhancing recommender systems through the integration of generative self-supervised learning (SSL) with a Residual Graph Transformer. Our approach emphasizes the importance of superior data…

Information Retrieval · Computer Science 2025-04-16 Eya Mhedhbi , Youssef Mourchid , Alice Othmani

The performance of autoregressive models on natural language generation tasks has dramatically improved due to the adoption of deep, self-attentive architectures. However, these gains have come at the cost of hindering inference speed,…

Computation and Language · Computer Science 2020-10-30 Alexander Lin , Jeremy Wohlwend , Howard Chen , Tao Lei

In this work, we introduce a self-supervised feature representation learning framework DreamTeacher that utilizes generative networks for pre-training downstream image backbones. We propose to distill knowledge from a trained generative…

Computer Vision and Pattern Recognition · Computer Science 2023-07-17 Daiqing Li , Huan Ling , Amlan Kar , David Acuna , Seung Wook Kim , Karsten Kreis , Antonio Torralba , Sanja Fidler

Invariance-based and generative methods have shown a conspicuous performance for 3D self-supervised representation learning (SSRL). However, the former relies on hand-crafted data augmentations that introduce bias not universally applicable…

Computer Vision and Pattern Recognition · Computer Science 2024-09-25 Naiwen Hu , Haozhe Cheng , Yifan Xie , Shiqi Li , Jihua Zhu

It has been recently demonstrated that multi-generational self-distillation can improve generalization. Despite this intriguing observation, reasons for the enhancement remain poorly understood. In this paper, we first demonstrate…

Machine Learning · Computer Science 2020-10-23 Zhilu Zhang , Mert R. Sabuncu

Supervised training of deep neural networks for classification typically relies on hard targets, which promote overconfidence and can limit calibration, generalization, and robustness. Self-distillation methods aim to mitigate this by…

Computer Vision and Pattern Recognition · Computer Science 2026-02-06 Anton Adelöw , Matteo Gamba , Atsuto Maki

Knowledge distillation is considered as a training and compression strategy in which two neural networks, namely a teacher and a student, are coupled together during training. The teacher network is supposed to be a trustworthy predictor…

Computation and Language · Computer Science 2020-12-29 Peyman Passban , Yimeng Wu , Mehdi Rezagholizadeh , Qun Liu

Most self-supervised learning (SSL) methods learn continuous visual representations by aligning different views of the same input, offering limited control over how information is structured across representation dimensions. In this work,…

Computer Vision and Pattern Recognition · Computer Science 2026-02-11 Kawtar Zaher , Ilyass Moummad , Olivier Buisson , Alexis Joly

Real-world contains an overwhelmingly large number of object classes, learning all of which at once is infeasible. Few shot learning is a promising learning paradigm due to its ability to learn out of order distributions quickly with only a…

Computer Vision and Pattern Recognition · Computer Science 2020-08-05 Jathushan Rajasegaran , Salman Khan , Munawar Hayat , Fahad Shahbaz Khan , Mubarak Shah

In this paper, we introduce a novel self-supervised learning (SSL) loss for image representation learning. There is a growing belief that generalization in deep neural networks is linked to their ability to discriminate object shapes. Since…

Computer Vision and Pattern Recognition · Computer Science 2023-03-14 Sepehr Sameni , Simon Jenni , Paolo Favaro

With the advancement of self-supervised learning (SSL), fine-tuning pretrained SSL models for mean opinion score (MOS) prediction has achieved state-of-the-art performance. However, during fine-tuning, these SSL-based MOS prediction models…

Sound · Computer Science 2026-01-21 Jianing Yang , Wataru Nakata , Yuki Saito , Hiroshi Saruwatari

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…

Computer Vision and Pattern Recognition · Computer Science 2023-07-18 Chao Wang , Zheng Tang

This paper proposes the DistillCSE framework, which performs contrastive learning under the self-training paradigm with knowledge distillation. The potential advantage of DistillCSE is its self-enhancing feature: using a base model to…

Computation and Language · Computer Science 2023-12-25 Jiahao Xu , Wei Shao , Lihui Chen , Lemao Liu

Self-supervised learning (SSL) has rapidly emerged as a transformative approach in computer vision, enabling the extraction of rich feature representations from vast amounts of unlabeled data and reducing reliance on costly manual…

Computer Vision and Pattern Recognition · Computer Science 2025-05-19 Nikolaos Giakoumoglou , Tania Stathaki , Athanasios Gkelias

Deep learning has achieved remarkable progress for visual recognition on large-scale balanced datasets but still performs poorly on real-world long-tailed data. Previous methods often adopt class re-balanced training strategies to…

Computer Vision and Pattern Recognition · Computer Science 2021-09-10 Tianhao Li , Limin Wang , Gangshan Wu

Knowledge distillation is an effective transfer of knowledge from a heavy network (teacher) to a small network (student) to boost students' performance. Self-knowledge distillation, the special case of knowledge distillation, has been…

Computer Vision and Pattern Recognition · Computer Science 2022-09-07 Duc-Quang Vu , Trang Phung , Jia-Ching Wang

Pre-trained speech language models such as HuBERT and WavLM leverage unlabeled speech data for self-supervised learning and offer powerful representations for numerous downstream tasks. Despite the success of these models, their high…

Audio and Speech Processing · Electrical Eng. & Systems 2024-06-24 Yingying Gao , Shilei Zhang , Chao Deng , Junlan Feng

We present DistillFlow, a knowledge distillation approach to learning optical flow. DistillFlow trains multiple teacher models and a student model, where challenging transformations are applied to the input of the student model to generate…

Computer Vision and Pattern Recognition · Computer Science 2021-06-09 Pengpeng Liu , Michael R. Lyu , Irwin King , Jia Xu