While semi-supervised learning (SSL) has proven to be a promising way for leveraging unlabeled data when labeled data is scarce, the existing SSL algorithms typically assume that training class distributions are balanced. However, these SSL algorithms trained under imbalanced class distributions can severely suffer when generalizing to a balanced testing criterion, since they utilize biased pseudo-labels of unlabeled data toward majority classes. To alleviate this issue, we formulate a convex optimization problem to softly refine the pseudo-labels generated from a biased model, and develop a simple iterative algorithm, named Distribution Aligning Refinery of Pseudo-label (DARP) that solves it provably and efficiently. Under various class-imbalanced semi-supervised scenarios, we demonstrate the effectiveness of DARP and its compatibility with state-of-the-art SSL schemes.

This paper proposes an approach to semi-supervised learning for imbalanced classes. It is indeed non-trivial to combine local/global/perturbation consistency-based semi-supervised methods and fully supervised methods for imbalanced classes---this paper may be the first work along this direction. The paper is quite general and can be applied on top of any pseudo-labeling-based semi-supervised methods. It first estimates the true class-prior probability and then updates/modifies the pseudo labels by pushing their class-prior probability with a constrained convex optimization. While in the beginning the reviewers had some concerns (mainly the clarity and too few datasets), the authors did a particularly good job in their rebuttal (showing that the class-prior probability can be estimated rather than must be given).

We respond to each comment one by one. We mention this in Line 148; however, we will make it clear in the final draft. Conversely, SSL algorithms use the unlabeled data but they do not consider the class imbalance. We will make this point clear in the final draft. However, to avoid the confusion, we will substitute X, Y to α, β in the final draft.

The paper presents a semi-supervised approach for object detection that extends the consistency regularization used for image classification [14] for object detection. Concretely, it proposes using consistency losses for both classification and localization, as well as a background elimination technique that alleviates the class imbalance inherent to object detection. They evaluate their approach with two types of detectors (single and two-stage) on PASCAL VOT 2007 with unlabeled data from VOT2012 and COCO. Pros: The approach is novel, as far as I know no previous work addresses semi-supervised learning with consistency regularization for object detection. The use of JS divergence over L2 distance is justified and shown experimentally.

Making a precise annotation in a large dataset is crucial to the performance of object detection. While the object detection task requires a huge number of annotated samples to guarantee its performance, placing bounding boxes for every object in each sample is time-consuming and costs a lot. To alleviate this problem, we propose a Consistency-based Semi-supervised learning method for object Detection (CSD), which is a way of using consistency constraints as a tool for enhancing detection performance by making full use of available unlabeled data. Specifically, the consistency constraint is applied not only for object classification but also for the localization. We also proposed Background Elimination (BE) to avoid the negative effect of the predominant backgrounds on the detection performance.

This paper introduces a semi-supervised approach for object detection that extends the consistency regularization used for image classification for object detection. The proposed approach is novel and interesting. The evaluation part can be improved to make the comparison more convincing, as suggested by several reviewers.

Self-supervised (SS) learning is a powerful approach for representation learning using unlabeled data. Recently, it has been applied to Generative Adversarial Networks (GAN) training. Specifically, SS tasks were proposed to address the catastrophic forgetting issue in the GAN discriminator. In this work, we perform an in-depth analysis to understand how SS tasks interact with learning of generator. From the analysis, we identify issues of SS tasks which allow a severely mode-collapsed generator to excel the SS tasks.

We thank all the reviewers for their valuable suggestions. Our response to individual reviewers' concerns are as follows. The usage of AU relationship is different. The performance of our semi-supervised learning method is lower than [1] on BP4D. F1 score, which is higher than that of [1] (55.9%).

Sparse coding is an important method for unsupervised learning of task-independent features in theoretical neuroscience models of neural coding. While a number of algorithms exist to learn these representations from the statistics of a dataset, they largely ignore the information bottlenecks present in fiber pathways connecting cortical areas. For example, the visual pathway has many fewer neurons transmitting visual information to cortex than the number of photoreceptors. Both empirical and analytic results have recently shown that sparse representations can be learned effectively after performing dimensionality reduction with randomized linear operators, producing latent coefficients that preserve information. Unfortunately, current proposals for sparse coding in the compressed space require a centralized compression process (i.e., dense random matrix) that is biologically unrealistic due to local wiring constraints observed in neural circuits. The main contribution of this paper is to leverage recent results on structured random matrices to propose a theoretical neuroscience model of randomized projections for communication between cortical areas that is consistent with the local wiring constraints observed in neuroanatomy. We show analytically and empirically that unsupervised learning of sparse representations can be performed in the compressed space despite significant local wiring constraints in compression matrices of varying forms (corresponding to different local wiring patterns). Our analysis verifies that even with significant local wiring constraints, the learned representations remain qualitatively similar, have similar quantitative performance in both training and generalization error, and are consistent across many measures with measured macaque V1 receptive fields.

The reviewers agree that this work is novel and interesting, and makes an interesting contribution to the literature. Please take the reviewer comments into account while preparing the camera-ready version.