Related papers: Accurate Scene Text Recognition with Efficient Mod…

Object detection has advanced significantly with Detection Transformers (DETRs). However, these models are computationally demanding, posing challenges for deployment in resource-constrained environments (e.g., self-driving cars). Knowledge…

The existing solutions for object detection distillation rely on the availability of both a teacher model and ground-truth labels. We propose a new perspective to relax this constraint. In our framework, a student is first trained with…

Optical Character Recognition (OCR) systems have been widely used in various applications for extracting semantic information from images. To give the user more control over their privacy, an on-device solution is needed. The current…

In this paper, we introduce a novel knowledge distillation approach for the semantic segmentation task. Unlike previous methods that rely on power-trained teachers or other modalities to provide additional knowledge, our approach does not…

Generative priors of large-scale text-to-image diffusion models enable a wide range of new generation and editing applications on diverse visual modalities. However, when adapting these priors to complex visual modalities, often represented…

In this work, we study the problem of word-level confidence calibration for scene-text recognition (STR). Although the topic of confidence calibration has been an active research area for the last several decades, the case of structured and…

Transformer encoder with connectionist temporal classification (CTC) framework is widely used for automatic speech recognition (ASR). However, knowledge distillation (KD) for ASR displays a problem of disagreement between teacher-student…

The iterative sampling procedure employed by diffusion models (DMs) often leads to significant inference latency. To address this, we propose Stochastic Consistency Distillation (SCott) to enable accelerated text-to-image generation, where…

The field of Continual Learning (CL) has inspired numerous researchers over the years, leading to increasingly advanced countermeasures to the issue of catastrophic forgetting. Most studies have focused on the single-class scenario, where…

Scene flow estimation is the task of describing the 3D motion field between temporally successive point clouds. State-of-the-art methods use strong priors and test-time optimization techniques, but require on the order of tens of seconds to…

End-to-end text spotting has attached great attention recently due to its benefits on global optimization and high maintainability for real applications. However, the input scale has always been a tough trade-off since recognizing a small…

Scene Text Image Super-Resolution (STISR) aims to enhance the resolution and legibility of text within low-resolution (LR) images, consequently elevating recognition accuracy in Scene Text Recognition (STR). Previous methods predominantly…

In this paper, we explore the potential of the Contrastive Language-Image Pretraining (CLIP) model in scene text recognition (STR), and establish a novel Symmetrical Linguistic Feature Distillation framework (named CLIP-OCR) to leverage…

Speculative decoding (SD) accelerates large language model inference by employing a faster draft model for generating multiple tokens, which are then verified in parallel by the larger target model, resulting in the text generated according…

Acoustic scene classification (ASC) is highly important in the real world. Recently, deep learning-based methods have been widely employed for acoustic scene classification. However, these methods are currently not lightweight enough as…

By leveraging the text-to-image diffusion priors, score distillation can synthesize 3D contents without paired text-3D training data. Instead of spending hours of online optimization per text prompt, recent studies have been focused on…

Deploying language models often requires navigating accuracy vs. performance trade-offs to meet latency constraints while preserving utility. Traditional model distillation reduces size but incurs substantial costs through training separate…

Score Distillation Sampling (SDS) has emerged as the de facto approach for text-to-content generation in non-image domains. In this paper, we reexamine the SDS process and introduce a straightforward interpretation that demystifies the…

Efficiently training accurate deep models for weakly supervised semantic segmentation (WSSS) with image-level labels is challenging and important. Recently, end-to-end WSSS methods have become the focus of research due to their high…

Scene text recognition (STR) is a challenging task that requires large-scale annotated data for training. However, collecting and labeling real text images is expensive and time-consuming, which limits the availability of real data.…