Twin identification over viewpoint change: A deep convolutional neural network surpasses humans

• URL: http://arxiv.org/abs/2207.05316v1
• Date: Tue, 12 Jul 2022 04:59:53 GMT
• Title: Twin identification over viewpoint change: A deep convolutional neural network surpasses humans
• Authors: Connor J. Parde, Virginia E. Strehle, Vivekjyoti Banerjee, Ying Hu, Jacqueline G. Cavazos, Carlos D. Castillo, Alice J. O'Toole
• Abstract summary: Deep convolutional neural networks have achieved human-level accuracy in face identification. It is unclear how accurately they discriminate highly-similar faces. A DCNN trained for face identification was tested on the same image pairs presented to humans. Machine performance mirrored the pattern of human accuracy, but with performance at or above all humans in all but one condition.
• Score: 2.9363019325439255
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deep convolutional neural networks (DCNNs) have achieved human-level accuracy in face identification (Phillips et al., 2018), though it is unclear how accurately they discriminate highly-similar faces. Here, humans and a DCNN performed a challenging face-identity matching task that included identical twins. Participants (N=87) viewed pairs of face images of three types: same-identity, general imposter pairs (different identities from similar demographic groups), and twin imposter pairs (identical twin siblings). The task was to determine whether the pairs showed the same person or different people. Identity comparisons were tested in three viewpoint-disparity conditions: frontal to frontal, frontal to 45-degree profile, and frontal to 90-degree profile. Accuracy for discriminating matched-identity pairs from twin-imposters and general imposters was assessed in each viewpoint-disparity condition. Humans were more accurate for general-imposter pairs than twin-imposter pairs, and accuracy declined with increased viewpoint disparity between the images in a pair. A DCNN trained for face identification (Ranjan et al., 2018) was tested on the same image pairs presented to humans. Machine performance mirrored the pattern of human accuracy, but with performance at or above all humans in all but one condition. Human and machine similarity scores were compared across all image-pair types. This item-level analysis showed that human and machine similarity ratings correlated significantly in six of nine image-pair types [range r=0.38 to r=0.63], suggesting general accord between the perception of face similarity by humans and the DCNN. These findings also contribute to our understanding of DCNN performance for discriminating high-resemblance faces, demonstrate that the DCNN performs at a level at or above humans, and suggest a degree of parity between the features used by humans and the DCNN.

Related papers

• Evaluating Multiview Object Consistency in Humans and Image Models [68.36073530804296]
  We leverage an experimental design from the cognitive sciences which requires zero-shot visual inferences about object shape. We collect 35K trials of behavioral data from over 500 participants. We then evaluate the performance of common vision models.
  arXiv  Detail & Related papers  (2024-09-09T17:59:13Z)
• SwinFace: A Multi-task Transformer for Face Recognition, Expression Recognition, Age Estimation and Attribute Estimation [60.94239810407917]
  This paper presents a multi-purpose algorithm for simultaneous face recognition, facial expression recognition, age estimation, and face attribute estimation based on a single Swin Transformer. To address the conflicts among multiple tasks, a Multi-Level Channel Attention (MLCA) module is integrated into each task-specific analysis. Experiments show that the proposed model has a better understanding of the face and achieves excellent performance for all tasks.
  arXiv  Detail & Related papers  (2023-08-22T15:38:39Z)
• Human-Machine Comparison for Cross-Race Face Verification: Race Bias at the Upper Limits of Performance? [0.7036032466145111]
  Face recognition algorithms perform more accurately than humans in some cases, though humans and machines both show race-based accuracy differences. We constructed a challenging test of 'cross-race' face verification and used it to compare humans and two state-of-the-art face recognition systems. We conclude that state-of-the-art systems for identity verification between two frontal face images of Black and White individuals can surpass the general population.
  arXiv  Detail & Related papers  (2023-05-25T19:41:13Z)
• End-to-End Context-Aided Unicity Matching for Person Re-identification [100.02321122258638]
  We propose an end-to-end person unicity matching architecture for learning and refining the person matching relations. We use the samples' global context relationship to refine the soft matching results and reach the matching unicity through bipartite graph matching. Given full consideration to real-world person re-identification applications, we achieve the unicity matching in both one-shot and multi-shot settings.
  arXiv  Detail & Related papers  (2022-10-20T07:33:57Z)
• Benchmarking Human Face Similarity Using Identical Twins [5.93228031688634]
  The problem of distinguishing identical twins and non-twin look-alikes in automated facial recognition (FR) applications has become increasingly important. This work presents an application of one of the largest twin datasets compiled to date to address two FR challenges.
  arXiv  Detail & Related papers  (2022-08-25T01:45:02Z)
• The Influence of the Other-Race Effect on Susceptibility to Face Morphing Attacks [0.0]
  Facial morphs created between two identities resemble both of the faces used to create the morph. Humans and machines are prone to mistake morphs made from two identities for either of the faces used to create the morph. This vulnerability has been exploited in "morph attacks" in security scenarios.
  arXiv  Detail & Related papers  (2022-04-26T20:59:08Z)
• Do DNNs trained on Natural Images acquire Gestalt Properties? [0.6091702876917281]
  Deep Neural Networks (DNNs) trained on natural images have been proposed as compelling models of human vision. We compared human and DNN responses in discrimination judgments. We found that network trained on natural images exhibited sensitivity to shapes at the last stage of classification.
  arXiv  Detail & Related papers  (2022-03-14T17:06:11Z)
• Comparing Human and Machine Bias in Face Recognition [46.170389064229354]
  We release improvements to the LFW and CelebA datasets which will enable future researchers to obtain measurements of algorithmic bias. We also use these new data to develop a series of challenging facial identification and verification questions. We find that both computer models and human survey participants perform significantly better at the verification task.
  arXiv  Detail & Related papers  (2021-10-15T22:26:20Z)
• Convolutional neural net face recognition works in non-human-like ways [0.0]
  Convolutional neural networks (CNNs) give state of the art performance in many pattern recognition problems. We report that CNN face recognition systems also make surprising "errors" Best CNNs perform almost perfectly on the human face matching tasks, but also declare the most matches for faces of a different apparent race or sex.
  arXiv  Detail & Related papers  (2020-04-08T15:42:14Z)
• Learning Attentive Pairwise Interaction for Fine-Grained Classification [53.66543841939087]
  We propose a simple but effective Attentive Pairwise Interaction Network (API-Net) for fine-grained classification. API-Net first learns a mutual feature vector to capture semantic differences in the input pair. It then compares this mutual vector with individual vectors to generate gates for each input image. We conduct extensive experiments on five popular benchmarks in fine-grained classification.
  arXiv  Detail & Related papers  (2020-02-24T12:17:56Z)
• Learning Preference-Based Similarities from Face Images using Siamese Multi-Task CNNs [78.24964622317633]
  Key challenge for online dating platforms is to determine suitable matches for their users. Deep learning approaches have shown that a variety of properties can be predicted from human faces to some degree. We investigate the feasibility of bridging image-based matching and matching with personal interests, preferences, and attitude.
  arXiv  Detail & Related papers  (2020-01-25T23:08:12Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.