Related papers: Supervised Metric Learning to Rank for Retrieval v…

Label noise and class imbalance commonly coexist in real-world data. Previous works for robust learning, however, usually address either one type of the data biases and underperform when facing them both. To mitigate this gap, this work…

Image features for retrieval-based localization must be invariant to dynamic objects (e.g. cars) as well as seasonal and daytime changes. Such invariances are, up to some extent, learnable with existing methods using triplet-like losses,…

The goal of this work is to localize sound sources in visual scenes with a self-supervised approach. Contrastive learning in the context of sound source localization leverages the natural correspondence between audio and visual signals…

This paper describes one objective function for learning semantically coherent feature embeddings in multi-output classification problems, i.e., when the response variables have dimension higher than one. In particular, we consider the…

Multimodal contrastive learning is a methodology for linking different data modalities; the canonical example is linking image and text data. The methodology is typically framed as the identification of a set of encoders, one for each…

In this paper, we propose the coarse-to-fine optimization for the task of speech enhancement. Cosine similarity loss [1] has proven to be an effective metric to measure similarity of speech signals. However, due to the large variance of the…

Collecting labeled data for the task of semantic segmentation is expensive and time-consuming, as it requires dense pixel-level annotations. While recent Convolutional Neural Network (CNN) based semantic segmentation approaches have…

In many applications involving multi-media data, the definition of similarity between items is integral to several key tasks, e.g., nearest-neighbor retrieval, classification, and recommendation. Data in such regimes typically exhibits…

Metric learning has become an attractive field for research on the latest years. Loss functions like contrastive loss, triplet loss or multi-class N-pair loss have made possible generating models capable of tackling complex scenarios with…

Ensembles of Convolutional neural networks have shown remarkable results in learning discriminative semantic features for image classification tasks. Though, the models in the ensemble often concentrate on similar regions in images. This…

State-of-the-art natural language understanding classification models follow two-stages: pre-training a large language model on an auxiliary task, and then fine-tuning the model on a task-specific labeled dataset using cross-entropy loss.…

We present a novel semi-supervised learning framework that intelligently leverages the consistency regularization between the model's predictions from two strongly-augmented views of an image, weighted by a confidence of pseudo-label,…

Often, the data used to train ranking models is subject to label noise. For example, in web-search, labels created from clickstream data are noisy due to issues such as insufficient information in item descriptions on the SERP, query…

Generating accurate and coherent image captions in a continual learning setting remains a major challenge due to catastrophic forgetting and the difficulty of aligning evolving visual concepts with language over time. In this work, we…

Dense Retrieval (DR) models have proven to be effective for Document Retrieval and Information Grounding tasks. Usually, these models are trained and optimized for improving the relevance of top-ranked documents for a given query. Previous…

The task of large-scale retrieval-based image localization is to estimate the geographical location of a query image by recognizing its nearest reference images from a city-scale dataset. However, the general public benchmarks only provide…

Learning to hash is an efficient paradigm for exact and approximate nearest neighbor search from massive databases. Binary hash codes are typically extracted from an image by rounding output features from a CNN, which is trained on a…

Learning with few labeled data has been a longstanding problem in the computer vision and machine learning research community. In this paper, we introduced a new semi-supervised learning framework, SimMatch, which simultaneously considers…

Robust loss minimization is an important strategy for handling robust learning issue on noisy labels. Current robust loss functions, however, inevitably involve hyperparameter(s) to be tuned, manually or heuristically through cross…

Convolutional neural networks (CNNs) have been successfully applied to solve the problem of correspondence estimation between semantically related images. Due to non-availability of large training datasets, existing methods resort to…