paper-with-me

Papers

Cross-Paced Representation Learning with Partial Curricula for Sketch-based Image Retrieval

2018-03-05 · Dan Xu, Xavier Alameda-Pineda, Jingkuan Song, Elisa Ricci, Nicu Sebe

In this paper we address the problem of learning robust cross-domain representations for sketch-based image retrieval (SBIR). While most SBIR approaches focus on extracting low- and mid-level descriptors for direct feature matching, recent works have shown the benefit of learning coupled feature representations to describe data from two related sources. However, cross-domain representation learning methods are typically cast into non-convex minimization problems that are difficult to optimize, leading to unsatisfactory performance. Inspired by self-paced learning, a learning methodology designed to overcome convergence issues related to local optima by exploiting the samples in a meaningful order (i.e. easy to hard), we introduce the cross-paced partial curriculum learning (CPPCL) framework. Compared with existing self-paced learning methods which only consider a single modality and cannot deal with prior knowledge, CPPCL is specifically designed to assess the learning pace by jointly handling data from dual sources and modality-specific prior information provided in the form of partial curricula. Additionally, thanks to the learned dictionaries, we demonstrate that the proposed CPPCL embeds robust coupled representations for SBIR. Our approach is extensively evaluated on four publicly available datasets (i.e. CUFS, Flickr15K, QueenMary SBIR and TU-Berlin Extension datasets), showing superior performance over competing SBIR methods.

📄 PDF Abstract BibTeX arXiv:1803.01504

Code (0)

등록된 구현이 없습니다.

Tasks

Image RetrievalRepresentation LearningRetrievalSketch-Based Image Retrieval

Similar Papers 제목 키워드 기반

A Probabilistic Interpretation of Self-Paced Learning with Applications to Reinforcement Learning

2021-02-25 · Pascal Klink, Hany Abdulsamad, Boris Belousov, Carlo D'Eramo 외

Across machine learning, the use of curricula has shown strong empirical potential to improve learning from data by avoiding local optima of training objectives. For reinforcement learning (RL), curricula are especially …

reinforcement-learningReinforcement Learning (RL)

SCANet: Self-Paced Semi-Curricular Attention Network for Non-Homogeneous Image Dehazing

2023-04-17 · Yu Guo, Yuan Gao, Ryan Wen Liu, Yuxu Lu 외

The presence of non-homogeneous haze can cause scene blurring, color distortion, low contrast, and other degradations that obscure texture details. Existing homogeneous dehazing methods struggle to handle the non-uniform…

Image Dehazing

Confidence-Aware Paced-Curriculum Learning by Label Smoothing for Surgical Scene Understanding

2022-12-22 · Mengya Xu, Mobarakol Islam, Ben Glocker, Hongliang Ren

Curriculum learning and self-paced learning are the training strategies that gradually feed the samples from easy to more complex. They have captivated increasing attention due to their excellent performance in robotic v…

Multi-Label ClassificationMUlTI-LABEL-ClASSIFICATIONScene UnderstandingSemantic Segmentation

Reward-Machine-Guided, Self-Paced Reinforcement Learning

2023-05-25 · Cevahir Koprulu, Ufuk Topcu

Self-paced reinforcement learning (RL) aims to improve the data efficiency of learning by automatically creating sequences, namely curricula, of probability distributions over contexts. However, existing techniques for s…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Self-Paced Absolute Learning Progress as a Regularized Approach to Curriculum Learning

2023-06-09 · Tobias Niehues, Ulla Scheler, Pascal Klink

The usability of Reinforcement Learning is restricted by the large computation times it requires. Curriculum Reinforcement Learning speeds up learning by defining a helpful order in which an agent encounters tasks, i.e. …

reinforcement-learningReinforcement Learning