Search Results for author:
Found 10 papers, 4 papers with code
Understanding and Mitigating Human-Labelling Errors in Supervised Contrastive Learning
In this paper, we show that human-labelling errors not only differ significantly from synthetic label errors, but also pose unique challenges in SCL, different to those in traditional supervised learning methods.
CFIR: Fast and Effective Long-Text To Image Retrieval for Large Corpora
Text-to-image retrieval aims to find the relevant images based on a text query, which is important in various use-cases, such as digital libraries, e-commerce, and multimedia databases.
CLCE: An Approach to Refining Cross-Entropy and Contrastive Learning for Optimized Learning Fusion
State-of-the-art pre-trained image models predominantly adopt a two-stage approach: initial unsupervised pre-training on large-scale datasets followed by task-specific fine-tuning using Cross-Entropy loss~(CE).
CrisisViT: A Robust Vision Transformer for Crisis Image Classification
We leverage the new Incidents1M crisis image dataset to develop a range of new transformer-based image classification models.
Elucidating and Overcoming the Challenges of Label Noise in Supervised Contrastive Learning
However, while the detrimental effects of noisy labels in supervised learning are well-researched, their influence on SCL remains largely unexplored.
Large Multi-modal Encoders for Recommendation
In recent years, the rapid growth of online multimedia services, such as e-commerce platforms, has necessitated the development of personalised recommendation approaches that can encode diverse content about each item.
RoboLLM: Robotic Vision Tasks Grounded on Multimodal Large Language Models
Robotic vision applications often necessitate a wide range of visual perception tasks, such as object detection, segmentation, and identification.
Ranked #4 on
Instance Segmentation
on ARMBench
MultiWay-Adapater: Adapting large-scale multi-modal models for scalable image-text retrieval
As Multimodal Large Language Models (MLLMs) grow in size, adapting them to specialized tasks becomes increasingly challenging due to high computational and memory demands.
When hard negative sampling meets supervised contrastive learning
State-of-the-art image models predominantly follow a two-stage strategy: pre-training on large datasets and fine-tuning with cross-entropy loss.
LaCViT: A Label-aware Contrastive Fine-tuning Framework for Vision Transformers
Vision Transformers (ViTs) have emerged as popular models in computer vision, demonstrating state-of-the-art performance across various tasks.
