To explore the age effects on facial images, we propose a Disentangled Adversarial Autoencoder (DAAE) to disentangle the facial images into three independent factors: age, identity and extraneous information.
Deep learning models in large-scale machine learning systems are often continuously trained with enormous data from production environments.
Accessing the data in the failed disk (degraded read) with low latency is crucial for an erasure-coded storage system.
Information Theory Information Theory
Visible-Infrared person re-identification (VI-ReID) aims to match cross-modality pedestrian images, breaking through the limitation of single-modality person ReID in dark environment.
IR-Softmax can generalise to any softmax and its variants (which are discriminative for open-set problem) by directly setting the weights as their class centers, naturally solving the data imbalance problem.
As a consequence, massive new diverse paired heterogeneous images with the same identity can be generated from noises.
In this paper, we rethink three freedoms of differentiable NAS, i. e. operation-level, depth-level and width-level, and propose a novel method, named Three-Freedom NAS (TF-NAS), to achieve both good classification accuracy and precise latency constraint.
In this paper, we propose an Online High-quality Anchor Mining Strategy (HAMBox), which explicitly helps outer faces compensate with high-quality anchors.
This strategy leads to severe meta shift issues across multiple tasks, meaning the learned prototypes or class descriptors are not stable as each task only involves their own support set.
Specifically, we first introduce a dual variational autoencoder to represent a joint distribution of paired heterogeneous images.
In extreme classification settings, embedding-based neural network models are currently not competitive with sparse linear and tree-based methods in terms of accuracy.
However, the video length is usually long, and there are hierarchical relationships between frames across events in the video, the performance of RNN based models are decreased.
Ranked #1 on Video Classification on YouTube-8M
In this paper, a new large-scale Multi-yaw Multi-pitch high-quality database is proposed for Facial Pose Analysis (M2FPA), including face frontalization, face rotation, facial pose estimation and pose-invariant face recognition.
UVA is the first attempt to achieve facial age analysis tasks, including age translation, age generation and age estimation, in a universal framework.
Furthermore, due to the lack of high-resolution face manipulation databases to verify the effectiveness of our method, we collect a new high-quality Multi-View Face (MVF-HQ) database.
Then, in order to ensure the identity consistency of the generated paired heterogeneous images, we impose a distribution alignment in the latent space and a pairwise identity preserving in the image space.
Ranked #1 on Face Verification on CASIA NIR-VIS 2.0
More specifically, we decompose a residual vector locally into two orthogonal components and perform uniform quantization and multiscale quantization to each component respectively.
In this paper, we propose a technique that approximates the inner product computation in hybrid vectors, leading to substantial speedup in search while maintaining high accuracy.
Visible (VIS) to near infrared (NIR) face matching is a challenging problem due to the significant domain discrepancy between the domains and a lack of sufficient data for training cross-modal matching algorithms.
Ranked #2 on Face Verification on CASIA NIR-VIS 2.0
We propose a multiscale quantization approach for fast similarity search on large, high-dimensional datasets.
This framework integrates cross-spectral face hallucination and discriminative feature learning into an end-to-end adversarial network.
This paper proposes a learning from generation approach for makeup-invariant face verification by introducing a bi-level adversarial network (BLAN).
To avoid the over-fitting problem on small-scale heterogeneous face data, a correlation prior is introduced on the fully-connected layers of WCNN network to reduce parameter space.
Ranked #3 on Face Verification on CASIA NIR-VIS 2.0
In this paper, we propose a novel Attention-Set based Metric Learning (ASML) method to measure the statistical characteristics of image sets.
CDL seeks a shared feature space in which the heterogeneous face matching problem can be approximately treated as a homogeneous face matching problem.
In this paper, the proposed framework takes a remarkably different direction to resolve the multi-scene detection problem in a bottom-up fashion.
This paper presents a Light CNN framework to learn a compact embedding on the large-scale face data with massive noisy labels.
Ranked #2 on Age-Invariant Face Recognition on CAFR