Related papers: ProS: Facial Omni-Representation Learning via Prot…

Numerous self-supervised learning paradigms, such as contrastive learning and masked image modeling, learn powerful representations from unlabeled data but are typically pretrained in isolation, overlooking complementary insights and…

Existing few-shot learning (FSL) methods rely on training with a large labeled dataset, which prevents them from leveraging abundant unlabeled data. From an information-theoretic perspective, we propose an effective unsupervised FSL method,…

Traditional approaches to RL have focused on learning decision policies directly from episodic decisions, while slowly and implicitly learning the semantics of compositional representations needed for generalization. While some approaches…

Transformer-based architectures have become the de-facto standard models for diverse vision tasks owing to their superior performance. As the size of the models continues to scale up, model distillation becomes extremely important in…

Optimizing a deep neural network is a fundamental task in computer vision, yet direct training methods often suffer from over-fitting. Teacher-student optimization aims at providing complementary cues from a model trained previously, but…

Complex emotion recognition is a cognitive task that has so far eluded the same excellent performance of other tasks that are at or above the level of human cognition. Emotion recognition through facial expressions is particularly difficult…

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…

In real application scenarios, it is often challenging to obtain a large amount of labeled data for speaker representation learning due to speaker privacy concerns. Self-supervised learning with no labels has become a more and more…

Although larger datasets are crucial for training large deep models, the rapid growth of dataset size has brought a significant challenge in terms of considerable training costs, which even results in prohibitive computational expenses.…

Learning effective representations in image-based environments is crucial for sample efficient Reinforcement Learning (RL). Unfortunately, in RL, representation learning is confounded with the exploratory experience of the agent -- learning…

Recent advancements in timestep-distilled diffusion models have enabled high-quality image generation that rivals non-distilled multi-step models, but with significantly fewer inference steps. While such models are attractive for…

Existing feature distillation methods commonly adopt the One-to-one Representation Matching between any pre-selected teacher-student layer pair. In this paper, we present N-to-One Representation (NORM), a new two-stage knowledge…

Understanding the severity of conditions shown in images in medical diagnosis is crucial, serving as a key guide for clinical assessment, treatment, as well as evaluating longitudinal progression. This paper proposes Con- PrO: a novel…

The goal of self-supervised visual representation learning is to learn strong, transferable image representations, with the majority of research focusing on object or scene level. On the other hand, representation learning at part level has…

In this paper, we are interested in understanding self-supervised pretraining through studying the capability that self-supervised representation pretraining methods learn part-aware representations. The study is mainly motivated by that…

Self-supervised learning on point clouds has gained a lot of attention recently, since it addresses the label-efficiency and domain-gap problems on point cloud tasks. In this paper, we propose a novel self-supervised framework to learn…

Advances in self-distillation have shown that when knowledge is distilled from a teacher to a student using the same deep learning (DL) architecture, the student performance can surpass the teacher particularly when the network is…

We study how to transfer representations pretrained on source tasks to target tasks in visual percept based RL. We analyze two popular approaches: freezing or finetuning the pretrained representations. Empirical studies on a set of popular…

Super-resolution (SR) aims to reconstruct high-resolution (HR) images from their low-resolution (LR) counterparts, often relying on effective downsampling to generate diverse and realistic training pairs. In this work, we propose a…

We introduce SODA, a self-supervised diffusion model, designed for representation learning. The model incorporates an image encoder, which distills a source view into a compact representation, that, in turn, guides the generation of related…