Related papers: RCA-NOC: Relative Contrastive Alignment for Novel …
Accurate segmentation of retinal fluids in 3D Optical Coherence Tomography images is key for diagnosis and personalized treatment of eye diseases. While deep learning has been successful at this task, trained supervised models often fail…
Dense correspondence across semantically related images has been extensively studied, but still faces two challenges: 1) large variations in appearance, scale and pose exist even for objects from the same category, and 2) labeling…
Image-Text Retrieval (ITR) is challenging in bridging visual and lingual modalities. Contrastive learning has been adopted by most prior arts. Except for limited amount of negative image-text pairs, the capability of constrastive learning…
Noise contrastive learning is a popular technique for unsupervised representation learning. In this approach, a representation is obtained via reduction to supervised learning, where given a notion of semantic similarity, the learner tries…
Fully supervised object detection has achieved great success in recent years. However, abundant bounding boxes annotations are needed for training a detector for novel classes. To reduce the human labeling effort, we propose a novel webly…
In recent years, driven by the need for safer and more autonomous transport systems, the automotive industry has shifted toward integrating a growing number of Advanced Driver Assistance Systems (ADAS). Among the array of sensors employed…
Contrastive learning (CL) has achieved astonishing progress in computer vision, speech, and natural language processing fields recently with self-supervised learning. However, CL approach to the supervised setting is not fully explored,…
Aligning image and text encoders from scratch using contrastive learning requires large amounts of paired image-text data. We alleviate this need by aligning individually pre-trained language and vision representation models using a much…
We focus on the problem of segmenting a certain object referred by a natural language sentence in video content, at the core of formulating a pinpoint vision-language relation. While existing attempts mainly construct such relation in an…
Learning scientific document representations can be substantially improved through contrastive learning objectives, where the challenge lies in creating positive and negative training samples that encode the desired similarity semantics.…
Despite recent success, most contrastive self-supervised learning methods are domain-specific, relying heavily on data augmentation techniques that require knowledge about a particular domain, such as image cropping and rotation. To…
Large-scale contrastive vision-language pre-training has shown significant progress in visual representation learning. Unlike traditional visual systems trained by a fixed set of discrete labels, a new paradigm was introduced in…
Contrastive learning has been adopted as a core method for unsupervised visual representation learning. Without human annotation, the common practice is to perform an instance discrimination task: Given a query image crop, this task labels…
We present ReCo, a contrastive learning framework designed at a regional level to assist learning in semantic segmentation. ReCo performs semi-supervised or supervised pixel-level contrastive learning on a sparse set of hard negative…
Recently, 3D object detection algorithms based on radar and camera fusion have shown excellent performance, setting the stage for their application in autonomous driving perception tasks. Existing methods have focused on dealing with…
Recent representation learning approaches enhance neural topic models by optimizing the weighted linear combination of the evidence lower bound (ELBO) of the log-likelihood and the contrastive learning objective that contrasts pairs of…
This paper presents a solution to the challenges faced by contrastive learning in sequential recommendation systems. In particular, it addresses the issue of false negative, which limits the effectiveness of recommendation algorithms. By…
Session-based recommendation aims to predict intents of anonymous users based on limited behaviors. With the ability in alleviating data sparsity, contrastive learning is prevailing in the task. However, we spot that existing contrastive…
We propose a simple yet effective and robust method for contrastive captioning: generating discriminative captions that distinguish target images from very similar alternative distractor images. Our approach is built on a pragmatic…
Fine-tuning a pre-trained language model via the contrastive learning framework with a large amount of unlabeled sentences or labeled sentence pairs is a common way to obtain high-quality sentence representations. Although the contrastive…