相关论文: Compressive Visual Representations

While recent neural codecs achieve strong performance at low bitrates when optimized for perceptual quality, their effectiveness deteriorates significantly under ultra-low bitrate conditions. To mitigate this, generative compression methods…

Continual learning algorithms aim to learn from a sequence of tasks. In order to avoid catastrophic forgetting, most existing approaches rely on heuristics and do not provide computable learning guarantees. In this paper, we introduce…

Contrastive learning is a self-supervised representation learning framework, where two positive views generated through data augmentation are made similar by an attraction force in a data representation space, while a repulsive force makes…

Representation learning has significantly been developed with the advance of contrastive learning methods. Most of those methods have benefited from various data augmentations that are carefully designated to maintain their identities so…

Real-world data typically follow a long-tailed distribution, where a few majority categories occupy most of the data while most minority categories contain a limited number of samples. Classification models minimizing cross-entropy struggle…

Recent deep learning-based methods for lossy image compression achieve competitive rate-distortion performance through extensive end-to-end training and advanced architectures. However, emerging applications increasingly prioritize semantic…

The extensive adoption of Deep Neural Networks has led to their increased utilization in challenging scientific visualization tasks. Recent advancements in building compressed data models using implicit neural representations have shown…

Contrastive learning (CL) has become a powerful approach for learning representations from unlabeled images. However, existing CL methods focus predominantly on visual appearance features while neglecting topological characteristics (e.g.,…

Self-supervised visual pretraining has shown significant progress recently. Among those methods, SimCLR greatly advanced the state of the art in self-supervised and semi-supervised learning on ImageNet. The input feature representations for…

Multimodal representation learning produces high-dimensional embeddings that align diverse modalities in a shared latent space. While this enables strong generalization, it also introduces scalability challenges, both in terms of storage…

Information Bottlenecks (IBs) learn representations that generalize to unseen data by information compression. However, existing IBs are practically unable to guarantee generalization in real-world scenarios due to the vacuous…

Self-predictive unsupervised learning methods such as BYOL or SimSiam have shown impressive results, and counter-intuitively, do not collapse to trivial representations. In this work, we aim at exploring the simplest possible mathematical…

Adversarial Imitation Learning (AIL) allows the agent to reproduce expert behavior with low-dimensional states and actions. However, challenges arise in handling visual states due to their less distinguishable representation compared to…

In this paper, we provide a detailed description on our approach designed for CVPR 2019 Workshop and Challenge on Learned Image Compression (CLIC). Our approach mainly consists of two proposals, i.e. deep residual learning for image…

Continuous unsupervised representation learning (CURL) research has greatly benefited from improvements in self-supervised learning (SSL) techniques. As a result, existing CURL methods using SSL can learn high-quality representations…

Continual learning (CL) aims to learn a sequence of tasks without forgetting the previously acquired knowledge. However, recent CL advances are restricted to supervised continual learning (SCL) scenarios. Consequently, they are not scalable…

With the explosion of digital data in recent years, continuously learning new tasks from a stream of data without forgetting previously acquired knowledge has become increasingly important. In this paper, we propose a new continual learning…

Contrastive Learning (CL), a leading paradigm in Self-Supervised Learning (SSL), typically relies on pairs of data views generated through augmentation. While multiple augmentations per instance (more than two) improve generalization in…

Multi-label image classification presents a challenging task in many domains, including computer vision and medical imaging. Recent advancements have introduced graph-based and transformer-based methods to improve performance and capture…

This paper proposes a scalable and straightforward pre-training paradigm for efficient visual conceptual representation called occluded image contrastive learning (OCL). Our OCL approach is simple: we randomly mask patches to generate…