Unlabeled data learning has attracted considerable attention recently. However, it is still elusive to extract the expected high-level semantic feature with mere unsupervised learning. In the meantime, semi-supervised learning (SSL) demonstrates a promising future in leveraging few samples. In this paper, we combine both to propose an Unsupervised Semantic Aggregation and Deformable Template Matching (USADTM) framework for SSL, which strives to improve the classification performance with few labeled data and then reduce the cost in data annotating. Specifically, unsupervised semantic aggregation based on Triplet Mutual Information (T-MI) loss is explored to generate semantic labels for unlabeled data. Then the semantic labels are aligned to the actual class by the supervision of labeled data. Furthermore, a feature pool that stores the labeled samples is dynamically updated to assign proxy labels for unlabeled data, which are used as targets for cross-entropy minimization. Extensive experiments and analysis across four standard semisupervised learning benchmarks validate that USADTM achieves top performance (e.g., 90.46% accuracy on CIFAR-10 with 40 labels and 95.20% accuracy with 250 labels).

The reviewers found the usage of the deformable templates here interesting and this work will be useful to a large part of the NeurIPS community.

Weaknesses: The paper has many weak points unfortunately. They are presented below as separate categories. Intro/Motivation: The paper focuses too much on "not using momentum encoder", "not using memory bank". All these are largely irrelevant points. Firstly, until one shows one gets no benefit from momentum encoder, it is best not to claim that "not having momentum" is a contribution / a positive aspect of the model.

The paper makes two incremental contributions in using online cluster assignments in self-supervised learning and using multiple crops in different resolutions for data augmentation. When these contributions are combined, decent gains in classification accuracy are obtained. The reviewers raise many issues with the current manuscript, including the discussion of momentum encoder, the discussion of existing clustering-based approaches, and the potential misuse of the term clustering. I ask the authors to incorporate all of these comments in the final version, but I believe the contributions even though incremental in nature, can benefit the fast growing field of self-supervised learning.

First of all, we would like to thank all the reviewers' valuable comments and their recognition (mainly from R #3 and R Obviously, γ=0.05 is relatively suitable, and the final clustering result also verifies this choice. We will try our best to improve the writing and release the code. Reviewer #3 for the details about the discriminator T. 3) The attack strategy will learn the corresponding perturbation The clustering accuracy dropped from 0.849 to 0.772.

Reconstructing observed images from fMRI brain recordings is challenging. Unfortunately, acquiring sufficient "labeled" pairs of {Image, fMRI} (i.e., images with their corresponding fMRI responses) to span the huge space of natural images is prohibitive for many reasons. We present a novel approach which, in addition to the scarce labeled data (training pairs), allows to train fMRI-to-image reconstruction networks also on "unlabeled" data (i.e., images without fMRI recording, and fMRI recording without images). The proposed model utilizes both an Encoder network (image-to-fMRI) and a Decoder network (fMRI-to-image). Concatenating these two networks back-to-back (Encoder-Decoder & Decoder-Encoder) allows augmenting the training with both types of unlabeled data. Importantly, it allows training on the unlabeled test-fMRI data.

This error may derive from two reasons. The first is that the classification branch of the model is not perfect, so the detector classifies a background region as a potted plant. The second is that the model classifier the region correctly, but regresses it to the wrong position. NMS cannot remove this kind of duplicate bounding box, resulting in an incorrect prediction. After uncertainty-aware soft target is adopted, the detector benefits from more certain regions during training.

Semi-supervised learning aims to leverage a large amount of unlabeled data for performance boosting. Existing works primarily focus on image classification. In this paper, we delve into semi-supervised learning for object detection, where labeled data are more labor-intensive to collect. Current methods are easily distracted by noisy regions generated by pseudo labels. To combat the noisy labeling, we propose noise-resistant semi-supervised learning by quantifying the region uncertainty. We first investigate the adverse effects brought by different forms of noise associated with pseudo labels. Then we propose to quantify the uncertainty of regions by identifying the noise-resistant properties of regions over different strengths. By importing the region uncertainty quantification and promoting multipeak probability distribution output, we introduce uncertainty into training and further achieve noise-resistant learning. Experiments on both PASCAL VOC and MS COCO demonstrate the extraordinary performance of our method.

The proof of Theorem 4.2 in the main paper uses the following technical lemma: Lemma 1.1 (Lemmas 4.5 and 4.6 in [1]). The proof of Lemma 1.1 follows standard covering arguments and may be sketched as follows. Full details can be found in the proofs in [1]. We can now present the proof of Theorem 4.2: Proof. X } (3) is empty, where \ denotes set difference.

In many real-world inverse problems, only incomplete measurement data are available for training which can pose a problem for learning a reconstruction function. Indeed, unsupervised learning using a fixed incomplete measurement process is impossible in general, as there is no information in the nullspace of the measurement operator. This limitation can be overcome by using measurements from multiple operators. While this idea has been successfully applied in various applications, a precise characterization of the conditions for learning is still lacking. In this paper, we fill this gap by presenting necessary and sufficient conditions for learning the underlying signal model needed for reconstruction which indicate the interplay between the number of distinct measurement operators, the number of measurements per operator, the dimension of the model and the dimension of the signals. Furthermore, we propose a novel and conceptually simple unsupervised learning loss which only requires access to incomplete measurement data and achieves a performance on par with supervised learning when the sufficient condition is verified. We validate our theoretical bounds and demonstrate the advantages of the proposed unsupervised loss compared to previous methods via a series of experiments on various imaging inverse problems, such as accelerated magnetic resonance imaging, compressed sensing and image inpainting.