Related papers: Pre-train a Discriminative Text Encoder for Dense …
To improve performance in visual feature representation from photos or videos for practical applications, we generally require large-scale human-annotated labeled data while training deep neural networks. However, the cost of gathering and…
To date, most existing self-supervised learning methods are designed and optimized for image classification. These pre-trained models can be sub-optimal for dense prediction tasks due to the discrepancy between image-level prediction and…
Self-supervised representation learning for visual pre-training has achieved remarkable success with sample (instance or pixel) discrimination and semantics discovery of instance, whereas there still exists a non-negligible gap between…
Scene text recognition (STR) pre-training methods have achieved remarkable progress, primarily relying on synthetic datasets. However, the domain gap between synthetic and real images poses a challenge in acquiring feature representations…
Recently, pre-trained transformer-based models have achieved great success in the task of definition generation (DG). However, previous encoder-decoder models lack effective representation learning to contain full semantic components of the…
We propose to solve the natural language inference problem without any supervision from the inference labels via task-agnostic multimodal pretraining. Although recent studies of multimodal self-supervised learning also represent the…
The cross-entropy objective has proved to be an all-purpose training objective for autoregressive language models (LMs). However, without considering the penalization of problematic tokens, LMs trained using cross-entropy exhibit text…
Passage retrieval aims to retrieve relevant passages from large collections of the open-domain corpus. Contextual Masked Auto-Encoding has been proven effective in representation bottleneck pre-training of a monolithic dual-encoder for…
Detectingandsegmentingobjectswithinwholeslideimagesis essential in computational pathology workflow. Self-supervised learning (SSL) is appealing to such annotation-heavy tasks. Despite the extensive benchmarks in natural images for dense…
The encoder-decoder models for unsupervised sentence representation learning tend to discard the decoder after being trained on a large unlabelled corpus, since only the encoder is needed to map the input sentence into a vector…
Contrastive learning has moved the state of the art for many tasks in computer vision and information retrieval in recent years. This poster is the first work that applies supervised contrastive learning to the task of product matching in…
Learning good representations without supervision is still an open issue in machine learning, and is particularly challenging for speech signals, which are often characterized by long sequences with a complex hierarchical structure. Some…
Self-supervised pretraining for Automated Speech Recognition (ASR) has shown varied degrees of success. In this paper, we propose to jointly learn representations during pretraining from two different modalities: speech and text. The…
Dense retrieval systems are commonly used for information retrieval (IR). They rely on learning text representations through an encoder and usually require supervised modeling via labelled data which can be costly to obtain or simply…
A new trend uses LLMs as dense text encoders via contrastive learning. However, since LLM embeddings predict the probability distribution of the next token, they are inherently generative and distributive, conflicting with contrastive…
Dominant dual-encoder models enable efficient image-text retrieval but suffer from limited accuracy while the cross-encoder models offer higher accuracy at the expense of efficiency. Distilling cross-modality matching knowledge from…
Multi-task learning of dense prediction tasks, by sharing both the encoder and decoder, as opposed to sharing only the encoder, provides an attractive front to increase both accuracy and computational efficiency. When the tasks are similar,…
This paper investigates efficient methods for utilizing text-only data to improve speech recognition, focusing on encoder-dominated models that facilitate faster recognition. We provide a comprehensive comparison of techniques to integrate…
Contrastive learning has gained significant attention in short text clustering, yet it has an inherent drawback of mistakenly identifying samples from the same category as negatives and then separating them in the feature space (false…
Dense embeddings deliver strong retrieval performance but often lack interpretability and controllability. This paper introduces a novel approach using sparse autoencoders (SAE) to interpret and control dense embeddings via the learned…