Related papers: Large-Scale Object Detection in the Wild from Imba…

Visual attributes constitute a large portion of information contained in a scene. Objects can be described using a wide variety of attributes which portray their visual appearance (color, texture), geometry (shape, size, posture), and other…

Deep learning models for object detection in autonomous driving have recently achieved impressive performance gains and are already being deployed in vehicles worldwide. However, current models require increasingly large datasets for…

The aim of Active Learning is to select the most informative samples from an unlabelled set of data. This is useful in cases where the amount of data is large and labelling is expensive, such as in machine vision or medical imaging. Two…

Softmax-based losses have achieved state-of-the-art performances on various tasks such as face recognition and re-identification. However, these methods highly relied on clean datasets with global labels, which limits their usage in many…

Class imbalance is a pervasive issue among classification models including deep learning, whose capacity to extract task-specific features is affected in imbalanced settings. However, the challenges of handling imbalance among a large…

Assessing the blurriness of an object image is fundamentally important to improve the performance for object recognition and retrieval. The main challenge lies in the lack of abundant images with reliable labels and effective learning…

Language-based object detection is a promising direction towards building a natural interface to describe objects in images that goes far beyond plain category names. While recent methods show great progress in that direction, proper…

While deep learning strategies achieve outstanding results in computer vision tasks, one issue remains: The current strategies rely heavily on a huge amount of labeled data. In many real-world problems, it is not feasible to create such an…

Learning recommender systems with multi-class optimization objective is a prevalent setting in recommendation. However, as observed user feedback often accounts for a tiny fraction of the entire item pool, the standard Softmax loss tends to…

In multi-label classification, an instance may be associated with a set of labels simultaneously. Recently, the research on multi-label classification has largely shifted its focus to the other end of the spectrum where the number of labels…

Intellectual property protection(IPP) have received more and more attention recently due to the development of the global e-commerce platforms. brand recognition plays a significant role in IPP. Recent studies for brand recognition and…

Wildlife camera trap images are being used extensively to investigate animal abundance, habitat associations, and behavior, which is complicated by the fact that experts must first classify the images manually. Artificial intelligence…

Modern deep networks can be better generalized when trained with noisy samples and regularization techniques. Mixup and CutMix have been proven to be effective for data augmentation to help avoid overfitting. Previous Mixup-based methods…

Solving long-tail large vocabulary object detection with deep learning based models is a challenging and demanding task, which is however under-explored.In this work, we provide the first systematic analysis on the underperformance of…

Though semantic segmentation has been heavily explored in vision literature, unique challenges remain in the remote sensing domain. One such challenge is how to handle resolution mismatch between overhead imagery and ground-truth label…

Large amounts of labeled training data are one of the main contributors to the great success that deep models have achieved in the past. Label acquisition for tasks other than benchmarks can pose a challenge due to requirements of both…

Top-k error is currently a popular performance measure on large scale image classification benchmarks such as ImageNet and Places. Despite its wide acceptance, our understanding of this metric is limited as most of the previous research is…

This paper proposes a method for OOD detection. Questioning the premise of previous studies that ID and OOD samples are separated distinctly, we consider samples lying in the intermediate of the two and use them for training a network. We…

Deep learning algorithms can fare poorly when the training dataset suffers from heavy class-imbalance but the testing criterion requires good generalization on less frequent classes. We design two novel methods to improve performance in…

Identifying and handling label errors can significantly enhance the accuracy of supervised machine learning models. Recent approaches for identifying label errors demonstrate that a low self-confidence of models with respect to a certain…