Related papers: On the Pros and Cons of Momentum Encoder in Self-S…
Self-supervised learning (SSL) is a powerful technique for learning from unlabeled data. By learning to remain invariant to applied data augmentations, methods such as SimCLR and MoCo can reach quality on par with supervised approaches.…
Papillary thyroid microcarcinoma (PTMC) is increasingly managed with radio-frequency ablation (RFA), yet accurate lesion segmentation in ultrasound videos remains difficult due to low contrast, probe-induced motion, and heat-related…
Recent self-supervised learning (SSL) models have proven to learn rich representations of speech, which can readily be utilized by diverse downstream tasks. To understand such utilities, various analyses have been done for speech SSL models…
Exponential Moving Average (EMA) is a widely used weight averaging (WA) regularization to learn flat optima for better generalizations without extra cost in deep neural network (DNN) optimization. Despite achieving better flatness, existing…
We show that bringing intermediate layers' representations of two augmented versions of an image closer together in self-supervised learning helps to improve the momentum contrastive (MoCo) method. To this end, in addition to the…
Recently, self-supervised learning (SSL) has achieved tremendous success in learning image representation. Despite the empirical success, most self-supervised learning methods are rather "inefficient" learners, typically taking hundreds of…
We study semi-supervised learning (SSL) for vision transformers (ViT), an under-explored topic despite the wide adoption of the ViT architectures to different tasks. To tackle this problem, we propose a new SSL pipeline, consisting of first…
Deep learning has emerged as the most promising approach in various fields; however, when the distributions of training and test data are different (domain shift), the performance of deep learning models can degrade. Semi-supervised domain…
Dynamic Vision Sensor (DVS) can asynchronously output the events reflecting apparent motion of objects with microsecond resolution, and shows great application potential in monitoring and other fields. However, the output event stream of…
What exactly do efficient sequence models gain over simple temporal averaging? We use exponential moving average (EMA) traces, the simplest recurrent context (no gating, no content-based retrieval), as a controlled probe to map the boundary…
Recent advancements in Deep and Self-Supervised Learning (SSL) have led to substantial improvements in Speech Emotion Recognition (SER) performance, reaching unprecedented levels. However, obtaining sufficient amounts of accurately labeled…
We study diffusion-based speech enhancement using a Schrodinger bridge formulation and extend the EDM2 framework to this setting. We employ time-dependent preconditioning of network inputs and outputs to stabilize training and explore two…
Self-supervised learning (SSL) aims to learn intrinsic features without labels. Despite the diverse architectures of SSL methods, the projection head always plays an important role in improving the performance of the downstream task. In…
The evolution of diffusion models has greatly impacted video generation and understanding. Particularly, text-to-video diffusion models (VDMs) have significantly facilitated the customization of input video with target appearance, motion,…
Self-supervised learning (SSL) has recently received significant attention due to its ability to train high-performance encoders purely on unlabeled data-often scraped from the internet. This data can still be sensitive and empirical…
As the key component in multimodal large language models (MLLMs), the ability of the visual encoder greatly affects MLLM's understanding on diverse image content. Although some large-scale pretrained vision encoders such as vision encoders…
The ability to predict the behavior of a wireless channel in terms of the frame delivery ratio is quite valuable, and permits, e.g., to optimize the operating parameters of a wireless network at runtime, or to proactively react to the…
High-speed vision sensing is essential for real-time perception in applications such as robotics, autonomous vehicles, and industrial automation. Traditional frame-based vision systems suffer from motion blur, high latency, and redundant…
Event cameras are bio-inspired vision sensors that asynchronously represent pixel-level brightness changes as event streams. Event-based monocular multi-view stereo (EMVS) is a technique that exploits the event streams to estimate…
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…