Related papers: Self-supervised Character-to-Character Distillatio…

The unsupervised visual inspection of defects in industrial products poses a significant challenge due to substantial variations in product surfaces. Current unsupervised models struggle to strike a balance between detecting texture and…

Short text clustering is a challenging problem due to its sparseness of text representation. Here we propose a flexible Self-Taught Convolutional neural network framework for Short Text Clustering (dubbed STC^2), which can flexibly and…

Deep convolutional neural networks have achieved remarkable progress on a variety of medical image computing tasks. A common problem when applying supervised deep learning methods to medical images is the lack of labeled data, which is very…

Connectionist Temporal Classification (CTC) is a widely used method for automatic speech recognition (ASR), renowned for its simplicity and computational efficiency. However, it often falls short in recognition performance. In this work, we…

Conventionally, autoencoders are unsupervised representation learning tools. In this work, we propose a novel discriminative autoencoder. Use of supervised discriminative learning ensures that the learned representation is robust to…

Contrastive Language-Image Pretraining (CLIP) achieves strong generalization in vision-language tasks by aligning images and texts in a shared embedding space. However, recent findings show that CLIP-like models still underutilize…

We tackle the problem of unsupervised synthetic-to-real domain adaptation for single image depth estimation. An essential building block of single image depth estimation is an encoder-decoder task network that takes RGB images as input and…

Multi-label classification is crucial for comprehensive image understanding, yet acquiring accurate annotations is challenging and costly. To address this, a recent study suggests exploiting unsupervised multi-label classification…

Character re-identification, recognizing characters consistently across different panels in comics, presents significant challenges due to limited annotated data and complex variations in character appearances. To tackle this issue, we…

Convolutional neural networks rely on image texture and structure to serve as discriminative features to classify the image content. Image enhancement techniques can be used as preprocessing steps to help improve the overall image quality…

Semi-supervised regression (SSR), which aims to predict continuous scores for samples while reducing the reliance on large-scale labeled data, has recently attracted considerable attention across various applications, including computer…

Customized image generation, which seeks to synthesize images with consistent characters, holds significant relevance for applications such as storytelling, portrait generation, and character design. However, previous approaches have…

Recently, significant advancements have been made in diffusion-based visual text generation models. Although the effectiveness of these methods in visual text rendering is rapidly improving, they still encounter challenges such as…

Multi-change captioning aims to describe complex and coupled changes within an image pair in natural language. Compared with single-change captioning, this task requires the model to have higher-level cognition ability to reason an…

The task of image captioning aims to generate captions directly from images via the automatically learned cross-modal generator. To build a well-performing generator, existing approaches usually need a large number of described images,…

Self-supervised learning has become a popular approach in recent years for its ability to learn meaningful representations without the need for data annotation. This paper proposes a novel image augmentation technique, overlaying images,…

Recent image tone adjustment (or enhancement) approaches have predominantly adopted supervised learning for learning human-centric perceptual assessment. However, these approaches are constrained by intrinsic challenges of supervised…

In recent years, scene text recognition is always regarded as a sequence-to-sequence problem. Connectionist Temporal Classification (CTC) and Attentional sequence recognition (Attn) are two very prevailing approaches to tackle this problem…

Recent text-to-image generation models have demonstrated impressive capability of generating text-aligned images with high fidelity. However, generating images of novel concept provided by the user input image is still a challenging task.…

During the last half decade, convolutional neural networks (CNNs) have triumphed over semantic segmentation, which is one of the core tasks in many applications such as autonomous driving. However, to train CNNs requires a considerable…