Learning reliable representations when proxy objectives fail
Darlow, Luke Nicholas
Representation learning involves using an objective to learn a mapping from data space to a representation space. When the downstream task for which a mapping must be learned is unknown, or is too costly to cast as an objective, we must rely on proxy objectives for learning. In this Thesis I focus on representation learning for images, and address three cases where proxy objectives fail to produce a mapping that performs well on the downstream tasks. When learning neural network mappings from image space to a discrete hash space for fast content-based image retrieval, a proxy objective is needed which captures the requirement for relevant responses to be nearer to the hash of any query than irrelevant ones. At the same time, it is important to ensure an even distribution of image hashes across the whole hash space for efficient information use and high discrimination. Proxy objectives fail when they do not meet these requirements. I propose composing hash codes in two parts. First a standard classifier is used to predict class labels that are converted to a binary representation for state-of-the-art performance on the image retrieval task. Second, a binary deep decision tree layer (DDTL) is used to model further intra-class differences and produce approximately evenly distributed hash codes. The DDTL requires no discretisation during learning and produces hash codes that enable better discrimination between data in the same class when compared to previous methods, while remaining robust to real-world augmentations in the data space. In the scenario where we require a neural network to partition the data into clusters that correspond well with ground-truth labels, a proxy objective is needed to define how these clusters are formed. One such proxy objective involves maximising the mutual information between cluster assignments made by a neural network from multiple views. In this context, views are different augmentations of the same image and the cluster assignments are the representations computed by a neural network. I demonstrate that this proxy objective produces parameters for the neural network that are sub-optimal in that a better set of parameters can be found using the same objective and a different training method. I introduce deep hierarchical object grouping (DHOG) as a method to learn a hierarchy (in the sense of easy-to-hard orderings, not structure) of solutions to the proxy objective and show how this improves performance on the downstream task. When there are features in the training data from which it is easier to compute class predictions (e.g., background colour), when compared to features for which it is relatively more difficult to compute class predictions (e.g., digit type), standard classification objectives (e.g., cross-entropy) fail to produce robust classifiers. The problem is that if a model learns to rely on `easy' features it will also ignore `complex' features (easy versus complex are purely relative in this case). I introduce latent adversarial debiasing (LAD) to decouple easy features from the class labels by first modelling the underlying structure of the training data as a latent representation using a vector-quantised variational autoencoder, and then I use a gradient-based procedure to adjust the features in this representation to confuse the predictions of a constrained classifier trained to predict class labels from the same representation. The adjusted representations of the data are then decoded to produce an augmented training dataset that can be used for training in a standard manner. I show in the aforementioned scenarios that proxy objectives can fail and demonstrate that alternative approaches can mitigate against the associated failures. I suggest an analytic approach to understanding the limits of proxy objectives for every use case in order to make the adjustments to the data or the objectives and ensure good performance on downstream tasks.