Search Results for author:
Found 13 papers, 6 papers with code
L-Verse: Bidirectional Generation Between Image and Text
Unlike other models, BiART can distinguish between image (or text) as a conditional reference and a generation target.
Ranked #1 on
Image Reconstruction
on ImageNet 256x256
Enriched CNN-Transformer Feature Aggregation Networks for Super-Resolution
Recent transformer-based super-resolution (SR) methods have achieved promising results against conventional CNN-based methods.
ReConPatch : Contrastive Patch Representation Learning for Industrial Anomaly Detection
In this paper, we introduce ReConPatch, which constructs discriminative features for anomaly detection by training a linear modulation of patch features extracted from the pre-trained model.
Ranked #1 on
Anomaly Detection
on MVTec AD
Large-Scale Bidirectional Training for Zero-Shot Image Captioning
However, we find that large-scale bidirectional training between image and text enables zero-shot image captioning.
Universal Noise Annotation: Unveiling the Impact of Noisy annotation on Object Detection
For object detection task with noisy labels, it is important to consider not only categorization noise, as in image classification, but also localization noise, missing annotations, and bogus bounding boxes.
Story Visualization by Online Text Augmentation with Context Memory
Story visualization (SV) is a challenging text-to-image generation task for the difficulty of not only rendering visual details from the text descriptions but also encoding a long-term context across multiple sentences.
DLCFT: Deep Linear Continual Fine-Tuning for General Incremental Learning
We show that this allows us to design a linear model where quadratic parameter regularization method is placed as the optimal continual learning policy, and at the same time enjoying the high performance of neural networks.
Factors that affect the technological transition of firms toward the industry 4.0 technologies
Using the technology space of firms, we can identify firms that successfully develop a new industry 4. 0 technology and examine whether their accumulated capabilities in their previous technology domains positively affect their technological diversification and which factors play a critical role in their transition towards industry 4. 0.
UniCLIP: Unified Framework for Contrastive Language-Image Pre-training
Pre-training vision-language models with contrastive objectives has shown promising results that are both scalable to large uncurated datasets and transferable to many downstream applications.
Significantly Improving Zero-Shot X-ray Pathology Classification via Fine-tuning Pre-trained Image-Text Encoders
However, large-scale and high-quality data to train powerful neural networks are rare in the medical domain as the labeling must be done by qualified experts.
NICE: CVPR 2023 Challenge on Zero-shot Image Captioning
In this report, we introduce NICE (New frontiers for zero-shot Image Captioning Evaluation) project and share the results and outcomes of 2023 challenge.
Misalign, Contrast then Distill: Rethinking Misalignments in Language-Image Pretraining
Contrastive Language-Image Pretraining has emerged as a prominent approach for training vision and text encoders with uncurated image-text pairs from the web.
Expediting Contrastive Language-Image Pretraining via Self-distilled Encoders
Based on the unified text embedding space, ECLIPSE compensates for the additional computational cost of the momentum image encoder by expediting the online image encoder.
