Search Results for author:
Found 19 papers, 11 papers with code
Language-only Efficient Training of Zero-shot Composed Image Retrieval
Our LinCIR (Language-only training for CIR) can be trained only with text datasets by a novel self-supervision named self-masking projection (SMP).
STELLA: Continual Audio-Video Pre-training with Spatio-Temporal Localized Alignment
Continuously learning a variety of audio-video semantics over time is crucial for audio-related reasoning tasks in our ever-evolving world.
Computational Approaches for App-to-App Retrieval and Design Consistency Check
Extracting semantic representations from mobile user interfaces (UI) and using the representations for designers' decision-making processes have shown the potential to be effective computational design support tools.
What Do Self-Supervised Vision Transformers Learn?
We present a comparative study on how and why contrastive learning (CL) and masked image modeling (MIM) differ in their representations and in their performance of downstream tasks.
CompoDiff: Versatile Composed Image Retrieval With Latent Diffusion
This paper proposes a novel diffusion-based model, CompoDiff, for solving zero-shot Composed Image Retrieval (ZS-CIR) with latent diffusion.
Ranked #3 on
Zero-Shot Composed Image Retrieval (ZS-CIR)
on CIRCO
SeiT: Storage-Efficient Vision Training with Tokens Using 1% of Pixel Storage
We need billion-scale images to achieve more generalizable and ground-breaking vision models, as well as massive dataset storage to ship the images (e. g., the LAION-4B dataset needs 240TB storage space).
UniXGen: A Unified Vision-Language Model for Multi-View Chest X-ray Generation and Report Generation
We also find that view-specific special tokens can distinguish between different views and properly generate specific views even if they do not exist in the dataset, and utilizing multi-view chest X-rays can faithfully capture the abnormal findings in the additional X-rays.
Group Generalized Mean Pooling for Vision Transformer
As ViT groups the channels via a multi-head attention mechanism, grouping the channels by GGeM leads to lower head-wise dependence while amplifying important channels on the activation maps.
Pivotal Role of Language Modeling in Recommender Systems: Enriching Task-specific and Task-agnostic Representation Learning
Recent studies have proposed unified user modeling frameworks that leverage user behavior data from various applications.
Correlation between Alignment-Uniformity and Performance of Dense Contrastive Representations
Recently, dense contrastive learning has shown superior performance on dense prediction tasks compared to instance-level contrastive learning.
An Extendable, Efficient and Effective Transformer-based Object Detector
Transformers have been widely used in numerous vision problems especially for visual recognition and detection.
ECCV Caption: Correcting False Negatives by Collecting Machine-and-Human-verified Image-Caption Associations for MS-COCO
Image-Text matching (ITM) is a common task for evaluating the quality of Vision and Language (VL) models.
Conditional Generation of Periodic Signals with Fourier-Based Decoder
Periodic signals play an important role in daily lives.
ViDT: An Efficient and Effective Fully Transformer-based Object Detector
Transformers are transforming the landscape of computer vision, especially for recognition tasks.
Ranked #12 on
Object Detection
on COCO 2017 val
ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision
Vision-and-Language Pre-training (VLP) has improved performance on various joint vision-and-language downstream tasks.
Ranked #2 on
Image Retrieval
on PhotoChat
Diversified Mutual Learning for Deep Metric Learning
Mutual learning is an ensemble training strategy to improve generalization by transferring individual knowledge to each other while simultaneously training multiple models.
Discrete InfoMax Codes for Meta-Learning
This paper analyzes how generalization works in meta-learning.
Discrete Infomax Codes for Supervised Representation Learning
In this paper we present a model that produces Discrete InfoMax Codes (DIMCO); we learn a probabilistic encoder that yields k-way d-dimensional codes associated with input data.
Learning Dynamics of Attention: Human Prior for Interpretable Machine Reasoning
Without relevant human priors, neural networks may learn uninterpretable features.
