Closing the Gap Between Classification and Retrieval Models
| dc.contributor.advisor | Davis, Larry | en_US |
| dc.contributor.advisor | Shrivastava, Abhinav | en_US |
| dc.contributor.author | Taha, Ahmed | en_US |
| dc.contributor.department | Computer Science | en_US |
| dc.contributor.publisher | Digital Repository at the University of Maryland | en_US |
| dc.contributor.publisher | University of Maryland (College Park, Md.) | en_US |
| dc.date.accessioned | 2021-07-07T05:48:20Z | |
| dc.date.available | 2021-07-07T05:48:20Z | |
| dc.date.issued | 2021 | en_US |
| dc.description.abstract | Retrieval networks learn a feature embedding where similar samples are close together, and different samples are far apart. This feature embedding is essential for computer vision applications such as face/person recognition, zero-shot learn- ing, and image retrieval. Despite these important applications, retrieval networks are less popular compared to classification networks due to multiple reasons: (1) The cross-entropy loss – used with classification networks – is stabler and converges faster compared to metric learning losses – used with retrieval networks. (2) The cross-entropy loss has a huge toolbox of utilities and extensions. For instance, both AdaCos and self-knowledge distillation have been proposed to tackle low sample complexity in classification networks; also, both CAM and Grad-CAM have been proposed to visualize attention in classification networks. To promote retrieval networks, it is important to equip them with an equally powerful toolbox. Accordingly, we propose an evolution-inspired approach to tackle low sample complexity in feature embedding. Then, we propose SVMax to regularize the feature embedding and avoid model collapse. Furthermore, we propose L2-CAF to visualize attention in retrieval networks. To tackle low sample complexity, we propose an evolution-inspired training approach to boost performance on relatively small datasets. The knowledge evolution (KE) approach splits a deep network into two hypotheses: the fit-hypothesis and the reset-hypothesis. We iteratively evolve the knowledge inside the fit-hypothesis by perturbing the reset-hypothesis for multiple generations. This approach not only boosts performance but also learns a slim (pruned) network with a smaller inference cost. KE reduces both overfitting and the burden for data collection. To regularize the feature embedding and avoid model collapse, We propose singular value maximization (SVMax) to promote a uniform feature embedding. Our formulation mitigates model collapse and enables larger learning rates. SV- Max is oblivious to both the input-class (labels) and the sampling strategy. Thus it promotes a uniform feature embedding in both supervised and unsupervised learning. Furthermore, we present a mathematical analysis of the mean singular value’s lower and upper bounds. This analysis makes tuning the SVMax’s balancing- hyperparameter easier when the feature embedding is normalized to the unit circle. To support retrieval networks with a visualization tool, we formulate attention visualization as a constrained optimization problem. We leverage the unit L2-Norm constraint as an attention filter (L2-CAF) to localize attention in both classification and retrieval networks. This approach imposes no constraints on the network architecture besides having a convolution layer. The input can be a regular image or a pre-extracted convolutional feature. The network output can be logits trained with cross-entropy or a space embedding trained with a ranking loss. Furthermore, this approach neither changes the original network weights nor requires fine-tuning. Thus, network performance remains intact. The visualization filter is applied only when an attention map is required. Thus, it poses no computational overhead during inference. L2-CAF visualizes the attention of the last convolutional layer ofGoogLeNet within 0.3 seconds. Finally, we propose a compromise between retrieval and classification networks. We propose a simple, yet effective, two-head architecture — a network with both logits and feature-embedding heads. The embedding head — trained with a ranking loss — limits the overfitting capabilities of the cross-entropy loss by promoting a smooth embedding space. In our work, we leverage the semi-hard triplet loss to allow a dynamic number of modes per class, which is vital when working with imbalanced data. Also, we refute a common assumption that training with a ranking loss is computationally expensive. By moving both the triplet loss sampling and computation to the GPU, the training time increases by just 2%. | en_US |
| dc.identifier | https://doi.org/10.13016/nul5-lq6a | |
| dc.identifier.uri | http://hdl.handle.net/1903/27316 | |
| dc.language.iso | en | en_US |
| dc.subject.pqcontrolled | Computer science | en_US |
| dc.subject.pquncontrolled | Computer vision | en_US |
| dc.subject.pquncontrolled | Deep learning | en_US |
| dc.subject.pquncontrolled | Feature embedding | en_US |
| dc.subject.pquncontrolled | Machine learning | en_US |
| dc.subject.pquncontrolled | Retrieval networks | en_US |
| dc.title | Closing the Gap Between Classification and Retrieval Models | en_US |
| dc.type | Dissertation | en_US |
Files
Original bundle
1 - 1 of 1